AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
docs(platform): sync GitBook documentation into dev (#13055)
Nicholas Tindlee7f197c86342
diff --git a/docs/integrations/block-integrations/ayrshare/post_to_linkedin.md b/docs/integrations/block-integrations/ayrshare/post_to_linkedin.mdindex 88a4bf0aec..2ca847a400 100644--- a/docs/integrations/block-integrations/ayrshare/post_to_linkedin.md+++ b/docs/integrations/block-integrations/ayrshare/post_to_linkedin.md@@ -10,7 +10,9 @@ Post to LinkedIn using Ayrshare### How it works<!-- MANUAL: how_it_works -->-_Add technical explanation here._+This block uses Ayrshare's social media API to post content to LinkedIn. It handles text posts, images, videos, and documents, with support for scheduling and audience targeting. The block authenticates through Ayrshare's API.++LinkedIn-specific features include visibility controls, comment management, and targeting by country, seniority, industry, and other demographics (requires 300+ followers in the target audience).<!-- END MANUAL -->### Inputs@@ -51,7 +53,11 @@ _Add technical explanation here._### Possible use case<!-- MANUAL: use_case -->-_Add practical use case examples here._+**Thought Leadership**: Automatically share blog posts or industry insights with a professional network.++**Scheduled Content**: Queue up a week's worth of LinkedIn posts with scheduled publishing times.++**Targeted Announcements**: Share company updates targeted to specific industries or seniority levels.<!-- END MANUAL -->---diff --git a/docs/integrations/block-integrations/ayrshare/post_to_youtube.md b/docs/integrations/block-integrations/ayrshare/post_to_youtube.mdindex 6bbceb6faa..094c624eed 100644--- a/docs/integrations/block-integrations/ayrshare/post_to_youtube.md+++ b/docs/integrations/block-integrations/ayrshare/post_to_youtube.md@@ -10,7 +10,9 @@ Post to YouTube using Ayrshare### How it works<!-- MANUAL: how_it_works -->-_Add technical explanation here._+This block uses Ayrshare's API to upload videos to YouTube. It handles video uploads with extensive metadata including titles, descriptions, tags, custom thumbnails, playlist assignment, category selection, and visibility controls (public, private, or unlisted).++The block supports YouTube Shorts (up to 3 minutes), geographic targeting to allow or block specific countries, subtitle files (SRT/SBV format), synthetic or AI content disclosure, kids-content labeling, and subscriber-notification controls. Videos can be scheduled for specific publish times.<!-- END MANUAL -->### Inputs@@ -55,7 +57,11 @@ _Add technical explanation here._### Possible use case<!-- MANUAL: use_case -->-_Add practical use case examples here._+**Video Publishing Pipeline**: Automate video uploads with thumbnails, descriptions, and playlist organization for content creators.++**YouTube Shorts Automation**: Publish short-form vertical videos to YouTube Shorts with proper metadata and hashtags.++**Multi-Region Content**: Upload videos with geographic restrictions for region-specific content licensing or compliance.<!-- END MANUAL -->---diff --git a/docs/integrations/block-integrations/llm.md b/docs/integrations/block-integrations/llm.mdindex bd88410b89..073adfa2e7 100644--- a/docs/integrations/block-integrations/llm.md+++ b/docs/integrations/block-integrations/llm.md@@ -714,7 +714,9 @@ Uses AI to intelligently decide what tool to use.### How it works<!-- MANUAL: how_it_works -->-_Add technical explanation here._+This block enables agentic behavior by letting an LLM decide which tools to use based on the prompt. It can execute connected tools and feed their results back to the model, creating autonomous reasoning loops.++In the default `built_in` execution mode, configure `agent_mode_max_iterations` to control loop behavior: `0` makes one decision and yields tool calls for external execution, `-1` loops until finished, and a positive number caps the iterations. The block outputs tool calls or a finished message. The `extended_thinking` mode manages its own loop and ignores this iteration setting.<!-- END MANUAL -->### Inputs@@ -746,7 +748,11 @@ _Add technical explanation here._### Possible use case<!-- MANUAL: use_case -->-_Add practical use case examples here._+**Autonomous Agents**: Build agents that can independently decide which tools to use for a task.++**Dynamic Workflows**: Create workflows that adapt their execution path based on model decisions.++**Multi-Tool Orchestration**: Let a model coordinate multiple tools to accomplish complex goals.<!-- END MANUAL -->---diff --git a/docs/platform/.gitbook/assets/agent-brief-agents-tab-hero.png b/docs/platform/.gitbook/assets/agent-brief-agents-tab-hero.pngnew file mode 100644index 0000000000..c45381d8deBinary files /dev/null and b/docs/platform/.gitbook/assets/agent-brief-agents-tab-hero.png differdiff --git a/docs/platform/.gitbook/assets/agent-brief-homescreen-hero.png b/docs/platform/.gitbook/assets/agent-brief-homescreen-hero.pngnew file mode 100644index 0000000000..d2ccef4c99Binary files /dev/null and b/docs/platform/.gitbook/assets/agent-brief-homescreen-hero.png differdiff --git a/docs/platform/.gitbook/assets/ai-chat-builder-hero.png b/docs/platform/.gitbook/assets/ai-chat-builder-hero.pngnew file mode 100644index 0000000000..61d1122d2cBinary files /dev/null and b/docs/platform/.gitbook/assets/ai-chat-builder-hero.png differdiff --git a/docs/platform/.gitbook/assets/artifacts-side-panel-hero.png b/docs/platform/.gitbook/assets/artifacts-side-panel-hero.pngnew file mode 100644index 0000000000..5ff004b5ebBinary files /dev/null and b/docs/platform/.gitbook/assets/artifacts-side-panel-hero.png differdiff --git a/docs/platform/.gitbook/assets/autopilot-upgrades-hero.png b/docs/platform/.gitbook/assets/autopilot-upgrades-hero.pngnew file mode 100644index 0000000000..1adf63dd8eBinary files /dev/null and b/docs/platform/.gitbook/assets/autopilot-upgrades-hero.png differdiff --git a/docs/platform/.gitbook/assets/code-execution-hero.png b/docs/platform/.gitbook/assets/code-execution-hero.pngnew file mode 100644index 0000000000..81d5c19b8dBinary files /dev/null and b/docs/platform/.gitbook/assets/code-execution-hero.png differdiff --git a/docs/platform/.gitbook/assets/discord-bot-hero.png b/docs/platform/.gitbook/assets/discord-bot-hero.pngnew file mode 100644index 0000000000..79b76a6873Binary files /dev/null and b/docs/platform/.gitbook/assets/discord-bot-hero.png differdiff --git a/docs/platform/.gitbook/assets/feedback-button-hero.png b/docs/platform/.gitbook/assets/feedback-button-hero.pngnew file mode 100644index 0000000000..2b0e9ded4fBinary files /dev/null and b/docs/platform/.gitbook/assets/feedback-button-hero.png differdiff --git a/docs/platform/.gitbook/assets/file-upload-hero.png b/docs/platform/.gitbook/assets/file-upload-hero.pngnew file mode 100644index 0000000000..164606e099Binary files /dev/null and b/docs/platform/.gitbook/assets/file-upload-hero.png differdiff --git a/docs/platform/.gitbook/assets/files-hero.png b/docs/platform/.gitbook/assets/files-hero.pngnew file mode 100644index 0000000000..6285baf9fbBinary files /dev/null and b/docs/platform/.gitbook/assets/files-hero.png differdiff --git a/docs/platform/.gitbook/assets/folders-hero.png b/docs/platform/.gitbook/assets/folders-hero.pngnew file mode 100644index 0000000000..507659f901Binary files /dev/null and b/docs/platform/.gitbook/assets/folders-hero.png differdiff --git a/docs/platform/.gitbook/assets/import-workflows-hero.png b/docs/platform/.gitbook/assets/import-workflows-hero.pngnew file mode 100644index 0000000000..f80ba07aecBinary files /dev/null and b/docs/platform/.gitbook/assets/import-workflows-hero.png differdiff --git a/docs/platform/.gitbook/assets/login-signup-hero.png b/docs/platform/.gitbook/assets/login-signup-hero.pngnew file mode 100644index 0000000000..991766a326Binary files /dev/null and b/docs/platform/.gitbook/assets/login-signup-hero.png differdiff --git a/docs/platform/.gitbook/assets/marketplace-hero.png b/docs/platform/.gitbook/assets/marketplace-hero.pngnew file mode 100644index 0000000000..a11ce612f1Binary files /dev/null and b/docs/platform/.gitbook/assets/marketplace-hero.png differdiff --git a/docs/platform/.gitbook/assets/marketplace-ui-v053-hero.png b/docs/platform/.gitbook/assets/marketplace-ui-v053-hero.pngnew file mode 100644index 0000000000..85984f696dBinary files /dev/null and b/docs/platform/.gitbook/assets/marketplace-ui-v053-hero.png differdiff --git a/docs/platform/.gitbook/assets/mcp-notion-hero.png b/docs/platform/.gitbook/assets/mcp-notion-hero.pngnew file mode 100644index 0000000000..c95a4438b1Binary files /dev/null and b/docs/platform/.gitbook/assets/mcp-notion-hero.png differdiff --git a/docs/platform/.gitbook/assets/notifications-hero.png b/docs/platform/.gitbook/assets/notifications-hero.pngnew file mode 100644index 0000000000..32b8890bc1Binary files /dev/null and b/docs/platform/.gitbook/assets/notifications-hero.png differdiff --git a/docs/platform/.gitbook/assets/outputs-hero.png b/docs/platform/.gitbook/assets/outputs-hero.pngnew file mode 100644index 0000000000..3332ecd52eBinary files /dev/null and b/docs/platform/.gitbook/assets/outputs-hero.png differdiff --git a/docs/platform/.gitbook/assets/reasoning-hero.png b/docs/platform/.gitbook/assets/reasoning-hero.pngnew file mode 100644index 0000000000..f6c041200fBinary files /dev/null and b/docs/platform/.gitbook/assets/reasoning-hero.png differdiff --git a/docs/platform/.gitbook/assets/settings-integrations-hero.png b/docs/platform/.gitbook/assets/settings-integrations-hero.pngnew file mode 100644index 0000000000..8896dbbb6aBinary files /dev/null and b/docs/platform/.gitbook/assets/settings-integrations-hero.png differdiff --git a/docs/platform/.gitbook/assets/settings-profile-hero.png b/docs/platform/.gitbook/assets/settings-profile-hero.pngnew file mode 100644index 0000000000..87e9f69c8bBinary files /dev/null and b/docs/platform/.gitbook/assets/settings-profile-hero.png differdiff --git a/docs/platform/.gitbook/assets/share-chat-hero.png b/docs/platform/.gitbook/assets/share-chat-hero.pngnew file mode 100644index 0000000000..fc20032f44Binary files /dev/null and b/docs/platform/.gitbook/assets/share-chat-hero.png differdiff --git a/docs/platform/.gitbook/assets/subscription-pricing-hero.png b/docs/platform/.gitbook/assets/subscription-pricing-hero.pngnew file mode 100644index 0000000000..73e26e8ca3Binary files /dev/null and b/docs/platform/.gitbook/assets/subscription-pricing-hero.png differdiff --git a/docs/platform/.gitbook/assets/usage-monitor-hero.png b/docs/platform/.gitbook/assets/usage-monitor-hero.pngnew file mode 100644index 0000000000..29a44beb92Binary files /dev/null and b/docs/platform/.gitbook/assets/usage-monitor-hero.png differdiff --git a/docs/platform/.gitbook/assets/v0654-copy-prompts-hero.png b/docs/platform/.gitbook/assets/v0654-copy-prompts-hero.pngnew file mode 100644index 0000000000..ce3e05747aBinary files /dev/null and b/docs/platform/.gitbook/assets/v0654-copy-prompts-hero.png differdiff --git a/docs/platform/.gitbook/assets/v0654-live-timer-hero.png b/docs/platform/.gitbook/assets/v0654-live-timer-hero.pngnew file mode 100644index 0000000000..e5d4f5b062Binary files /dev/null and b/docs/platform/.gitbook/assets/v0654-live-timer-hero.png differdiff --git a/docs/platform/.gitbook/assets/v0654-onboarding-hero.png b/docs/platform/.gitbook/assets/v0654-onboarding-hero.pngnew file mode 100644index 0000000000..2ddc29ac07Binary files /dev/null and b/docs/platform/.gitbook/assets/v0654-onboarding-hero.png differdiff --git a/docs/platform/.gitbook/assets/v0654-prompt-categories-hero.png b/docs/platform/.gitbook/assets/v0654-prompt-categories-hero.pngnew file mode 100644index 0000000000..1fcedad7c2Binary files /dev/null and b/docs/platform/.gitbook/assets/v0654-prompt-categories-hero.png differdiff --git a/docs/platform/.gitbook/assets/web-browsing-hero.png b/docs/platform/.gitbook/assets/web-browsing-hero.pngnew file mode 100644index 0000000000..13f689f3c2Binary files /dev/null and b/docs/platform/.gitbook/assets/web-browsing-hero.png differdiff --git a/docs/platform/SUMMARY.md b/docs/platform/SUMMARY.mdindex 0e440dd325..60bb3c31d4 100644--- a/docs/platform/SUMMARY.md+++ b/docs/platform/SUMMARY.md@@ -2,20 +2,34 @@* [What is the AutoGPT Platform?](what-is-autogpt-platform.md)-## Getting Started+## Using the Platform-* [Setting Up Auto-GPT (Local Host)](getting-started.md)+* [Getting Started (Cloud)](getting-started-cloud.md)+* [AutoPilot](autopilot.md)+* [Agent Builder Guide](agent-builder-guide.md)+* [Agent Library](agent-library.md)+* [Marketplace](marketplace.md)+* [Scheduling & Triggers](scheduling-and-triggers.md)+* [Templates](templates.md)+* [Credits & Billing](credits-and-billing.md)+* [Integrations & Credentials](integrations-and-credentials.md)+* [Data Flow & Execution](data-flow-and-execution.md)+* [Sharing & Exporting Agents](sharing-and-exporting.md)++## Self-Hosting++* [Setting Up AutoGPT (Self-Host)](getting-started.md)* [AutoGPT Platform Installer](installer.md)+* [Advanced Setup](advanced_setup.md)++## Tutorials++* [Create a Basic Agent](create-basic-agent.md)* [Edit an Agent](edit-agent.md)* [Delete an Agent](delete-agent.md)* [Download & Import an Agent](download-agent-from-marketplace-local.md)-* [Create a Basic Agent](create-basic-agent.md)* [Submit an Agent to the Marketplace](submit-agent-to-marketplace.md)-## Advanced Setup--* [Advanced Setup](advanced_setup.md)-## Building Blocks* [Agent Blocks Overview](agent-blocks.md)@@ -38,3 +52,17 @@## Contributing* [Managing LLM Models](contributing/managing-llm-models.md)++## Changelog++* [What's New](changelog/README.md)+ * [Organize files, share your work, connect Discord](changelog/june-18-july-9-2026.md)+ * [Smarter Automation, Fresher Design, Open for Business](changelog/may-7-june-10-2026.md)+ * [Artifacts, Briefings, and Builder Chat](changelog/april-10-may-1-2026.md)+ * [Smarter Starts, Faster Feedback](changelog/march-23-april-9-2026.md)+ * [Import workflows from other platforms and enjoy a polished marketplace](changelog/march-20-march-25-2026.md)+ * [Explore a new marketplace, track usage, and give instant feedback](changelog/march-13-march-20-2026.md)+ * [Organize your agents, get notified, and enjoy a cleaner chat](changelog/march-5-march-12-2026.md)+ * [Connect any app, share files, and let AutoPilot browse for you](changelog/february-26-march-4-2026.md)+ * [Telegram bots, agent folders, and a rebuilt builder](changelog/february-11-february-26-2026.md)+ * [Voice input, persistent files, and a smarter AI](changelog/january-29-february-11-2026.md)diff --git a/docs/platform/agent-builder-guide.md b/docs/platform/agent-builder-guide.mdnew file mode 100644index 0000000000..318c5ff1be--- /dev/null+++ b/docs/platform/agent-builder-guide.md@@ -0,0 +1,101 @@+# Agent Builder Guide++## Overview++The Agent Builder is the visual editor where you design and build agents by connecting blocks together on a canvas. Each block is a single action — like generating text, calling an API, or processing data — and you wire them together to create automated workflows.++**URL:** [platform.agpt.co/build](https://platform.agpt.co/build)++## The Builder Interface++When you open the builder, you'll see:++- **Canvas**: The main workspace where you place and connect blocks+- **Blocks Menu**: A panel on the left-hand side where you browse and search for blocks+- **Save Button**: Save your agent with a title and description++## Working with Blocks++### Types of Blocks++Blocks fall into three categories:++| Type | Description |+|------|-------------|+| **Input Blocks** | Define what information the agent needs when it runs. These become the input fields users fill in when starting a task. Types include text inputs, file inputs, and more. |+| **Action Blocks** | Perform operations — AI text generation, image creation, API calls, data processing, and hundreds of integrations with external platforms. |+| **Output Blocks** | Define what the agent returns as its result. These become the visible output when a task completes. |++Input and output blocks define the **schema** of your agent — they determine what users see when running the agent. All other blocks inside the agent are internal and not exposed to the user at runtime.++{% hint style="info" %}+There is also a special type of input block: **Trigger Blocks**. These allow your agent to be activated by external events via webhooks rather than manual input. See [Scheduling & Triggers](scheduling-and-triggers.md) for details.+{% endhint %}++### Adding Blocks++1. Open the **Blocks menu** on the left-hand side of the builder+2. Browse categories or use the search bar to find a specific block+3. Click on a block to add it to the canvas++There are hundreds of blocks available, integrating with many platforms and services.++### Connecting Blocks++Blocks have **input pins** and **output pins**. Pins are typed — they handle specific data types like text, numbers, files, and more.++To connect blocks:++1. Click on an **output pin** of one block+2. Drag to an **input pin** of another block (or simply click the output pin, then click the input pin)+3. A **connection line** will appear between the two pins++When the agent runs, data flows along these connections. This is visually represented by a **coloured bead** that slides along the connection line from the output pin to the input pin.++### Configuring Blocks++Many blocks have settings you can configure directly on the block. For example:++- The **AI Text Generator** block lets you choose which language model to use+- **Integration blocks** may require credentials (see [Integrations & Credentials](integrations-and-credentials.md))+- Some blocks allow you to hardcode values on their input pins instead of connecting them to other blocks++If a block requires a credential you haven't connected yet, a **credential bar** will appear prompting you to add it (via OAuth, API key, or username/password depending on the service).++## Saving Your Agent++To save your agent:++- Press **Ctrl+S** (or **Cmd+S** on Mac), or+- Click the **Save button** in the builder++Saving creates or updates the agent graph version in your library. The builder also keeps a local recovery draft while you edit; a successful save clears that draft. Publishing to the marketplace is a separate action—see [Publishing to the Marketplace](marketplace.md#publishing-an-agent).++## Navigating Back to Your Library++After saving, click the **Agents** button in the navigation bar to return to your library and find your agent.++## Editing an Existing Agent++To open an existing agent in the builder:++1. Go to your **Agent Library** (click **Agents** in the nav bar)+2. Click on the agent you want to edit+3. Click the **three dots** menu (⋯) on the far right-hand side of the screen+4. Select **Edit Agent**++This will open the agent in the builder with all its existing blocks and connections.++## Error Handling++When a block fails during execution, it produces data on its **error pin**. As the agent creator, you decide how to handle errors:++- **Surface the error**: Connect the error pin to an output block so the error is returned as the agent's result+- **Handle gracefully**: Connect the error pin to other blocks that provide fallback behaviour, ensuring the agent continues working even when individual blocks encounter problems++## Tips++- **Name your input and output blocks clearly** — these names become the labels users see when running your agent+- **Test incrementally** — save and run your agent frequently as you build to catch issues early+- **Use the search** in the blocks menu to quickly find what you need among hundreds of available blocks+- **Check the pin types** — connections only work between compatible pin typesdiff --git a/docs/platform/agent-library.md b/docs/platform/agent-library.mdnew file mode 100644index 0000000000..207b6843c1--- /dev/null+++ b/docs/platform/agent-library.md@@ -0,0 +1,91 @@+# Agent Library++## Overview++The Agent Library is your personal collection of agents. From here you can run agents, view task history, set up schedules and triggers, edit agents, and manage your collection.++**URL:** [platform.agpt.co/library](https://platform.agpt.co/library)++**Access:** Click the **Agents** button in the navigation bar.++## Library View++Your library displays all of your agents, including agents you've built yourself and agents you've added from the marketplace. Each agent shows its name and key information at a glance.++### Favorites and folders++Click the **heart icon** on an agent to add or remove it from the **Favorites** tab. Use folders to organize agents; create a folder from the library and choose **Move to folder** from an agent's menu.++## Agent Detail View++Click on any agent to open its detail view. This screen provides:++- **Tasks**: A full history of every time this agent has been executed+- **Scheduled**: A list of active schedules for this agent+- **Triggers**: Configured webhook triggers for trigger-based agents+- **Templates**: Saved task inputs and credential references for reuse++These are accessible via tabs on the left-hand side of the agent screen (e.g., `Tasks 286 | Scheduled 1 | Templates 0`).++### Agent Actions Menu++Click the **three dots** (⋯) on the far right-hand side of the agent screen to access:++| Action | Description |+|--------|-------------|+| **Edit Agent** | Opens the agent in the builder; marketplace agents are read-only until duplicated |+| **Delete Agent** | Permanently removes the agent from your library |+| **Export Agent to File** | Downloads the agent as a file you can share with others |++## Running an Agent++To run an agent manually:++1. Open the agent from your library+2. Click **New agent task**+3. Fill in the required inputs and credentials+4. Click **Start Task**++The task will begin executing immediately. You can watch the progress and view the results once it completes.++{% hint style="warning" %}+For a trigger-based agent, use the same **New agent task** dialog and click **Set up Trigger**. Trigger-based agents cannot be started manually. See [Scheduling & Triggers](scheduling-and-triggers.md) for details.+{% endhint %}++## Viewing Task Results++Every time an agent runs, it creates a **task**. To view task results:++1. Open the agent from your library+2. In the left-hand pane, browse the list of completed tasks+3. Click on a task to view its details++A task detail view shows:++- **Inputs**: The values that were provided when the task started+- **Outputs**: The results the agent produced+- **Cost**: The run's reported cost, displayed at the top of the task detail view++To share an output, click **Share results** and explicitly enable sharing; copying the authenticated task URL does not create a public link. See [Sharing & Exporting Agents](sharing-and-exporting.md#share-task-output-via-url) for visibility and revocation details.++## Importing an Agent++To import an agent from a file:++1. Go to your Agent Library+2. Click **Import**+3. Keep **AutoGPT agent** selected+4. Choose the exported JSON file, complete the requested metadata, and click **Upload**++The agent will be added to your library and can be run or edited like any other agent. This is useful for importing agents shared by other users outside of the marketplace.++## Deleting an Agent++1. Open the agent from your library+2. Click the **three dots** (⋯) on the far right+3. Select **Delete Agent**+4. Confirm the deletion when prompted++{% hint style="danger" %}+Deleting an agent is permanent and cannot be undone. Make sure you want to remove it before confirming.+{% endhint %}diff --git a/docs/platform/autopilot.md b/docs/platform/autopilot.mdnew file mode 100644index 0000000000..d868cf6b97--- /dev/null+++ b/docs/platform/autopilot.md@@ -0,0 +1,62 @@+# AutoPilot++## Overview++AutoPilot is your AI assistant built directly into the AutoGPT Platform. It can perform supported platform actions through natural conversation — from running agents to generating images, conducting research, and building agents for you.++## Accessing AutoPilot++Open AutoPilot from **Home** or **New Task** in the main navigation, or go directly to [platform.agpt.co/copilot](https://platform.agpt.co/copilot).++## What AutoPilot Can Do++AutoPilot can use supported platform tools. Here's what it can help you with:++### Run Agents++Ask AutoPilot to run a supported agent in your [Agent Library](agent-library.md). It will request any missing inputs or credentials before executing it.++### Build Agents++Describe the workflow you want and AutoPilot will create an agent for you in the builder. You can also ask it to edit your existing agents; duplicate a read-only marketplace agent before editing it. See the [Agent Builder Guide](agent-builder-guide.md) for hands-on editing.++### Browse the Marketplace++Ask AutoPilot to find agents for a specific use case and it will search the marketplace for you. You can also browse the [Marketplace](marketplace.md) directly.++### Execute Blocks Directly++AutoPilot can run supported blocks directly without building a full agent. This means you can:++- **Conduct research** with Perplexity+- **Generate images** with the latest image models+- **Edit pictures** using AI image editing blocks+- **Generate videos** using video generation blocks+- **Run supported models** on inference services such as Replicate+- **Make custom HTTP requests** to APIs you configure+- **Write and execute code** with supported coding tools++### Manage Your Library++AutoPilot can help you manage your agent library, view task results, set up schedules, and more.++## Tips for Using AutoPilot++- **Be specific**: The more detail you provide, the better AutoPilot can assist you. Instead of "make me an agent", try "build me an agent that takes a blog topic as input, generates an outline with Claude, then writes the full article".+- **Iterate**: You can refine results by asking follow-up questions or requesting changes.+- **Explore capabilities**: If you're unsure whether AutoPilot supports something, ask it or browse the available blocks.++## AutoPilot vs. the Agent Builder++AutoPilot and the Agent Builder offer complementary ways to work on the platform. AutoPilot can create and edit reusable agents through natural language and run supported blocks directly, while the builder provides hands-on control over the graph.++| | AutoPilot | Agent Builder |+|---|-----------|---------------|+| **Who is it for** | Everyone — no technical knowledge required | Technical users with a grasp of visual programming |+| **Best for** | Natural language interaction, doing things fast, and accessing blocks directly | Hands-on visual control over exactly how an agent is wired together |+| **How it works** | Conversational — describe what you want | Visual — drag, drop, and connect blocks on a canvas |+| **Can build agents** | Yes — describe what you want and it builds the agent for you | Yes — you build the agent manually |+| **Can edit agents** | Yes — for user-created or duplicated editable agents | Yes — full visual editing |+| **Block access** | Can run supported blocks directly without building an agent | Blocks must be connected into an agent workflow |++Choose whichever approach suits you. Many users use both — AutoPilot for speed, and the builder when they want fine-grained visual control over their workflow.diff --git a/docs/platform/changelog/README.md b/docs/platform/changelog/README.mdnew file mode 100644index 0000000000..1effe50556--- /dev/null+++ b/docs/platform/changelog/README.md@@ -0,0 +1,20 @@+# Changelog++What's new in AutoPilot and the AutoGPT Platform. We ship updates regularly and document everything here.++Release windows reflect how changes were grouped for publication and may overlap when work spans consecutive releases.++## 2026++| Date | Highlights |+| ---- | ---------- |+| [June 18 – July 9](june-18-july-9-2026.md) | File folders, shareable chats, Discord bot |+| [May 7 – June 10](may-7-june-10-2026.md) | AutoPilot upgrades, redesigned login, live subscriptions, rebuilt settings |+| [April 10 – May 1](april-10-may-1-2026.md) | Artifacts panel, agent briefings, AI chat in builder |+| [March 23 – April 9](march-23-april-9-2026.md) | Themed prompt categories, live timer stats, redesigned onboarding, copy your prompts |+| [March 20 – March 25](march-20-march-25-2026.md) | Import workflows from other tools, marketplace UI polish, dry-run mode, parallel AutoPilot actions |+| [March 13 – March 20](march-13-march-20-2026.md) | Refreshed marketplace, usage monitor, feedback button, personalized prompts |+| [March 5 – March 12](march-5-march-12-2026.md) | Folders, notifications, cleaner reasoning, inline outputs |+| [February 26 – March 4](february-26-march-4-2026.md) | Connect any app, share files, browse the web, run code, text-to-speech |+| [February 11 – 26](february-11-february-26-2026.md) | Telegram bots, agent folders, rebuilt flow editor, major AutoPilot upgrade |+| [January 29 – February 11](january-29-february-11-2026.md) | Voice input, persistent file workspace, Claude Opus 4.6, marketplace agent customization, rebuilt chat streaming |diff --git a/docs/platform/changelog/april-10-may-1-2026.md b/docs/platform/changelog/april-10-may-1-2026.mdnew file mode 100644index 0000000000..9619eab02e--- /dev/null+++ b/docs/platform/changelog/april-10-may-1-2026.md@@ -0,0 +1,54 @@+# Artifacts, Briefings, and Builder Chat++*April 10 – May 1, 2026*++**Platform versions:** `v0.6.55` · `v0.6.56` · `v0.6.57` · `v0.6.58`++## See your outputs come to life++AutoPilot now renders rich artifacts directly in a side panel — open reports as interactive documents, view charts, read PDFs, and even play games, all without leaving the conversation. First introduced quietly in v0.6.54, artifacts have been significantly refined with smoother rendering, better state management, and a more polished panel experience across v0.6.55 and v0.6.57. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12856)++<figure><img src="../.gitbook/assets/artifacts-side-panel-hero.png" alt="Artifacts rendered in the AutoPilot side panel"><figcaption><p>Rich artifacts — documents, charts, and interactive apps — rendered in the conversation side panel.</p></figcaption></figure>++## Agent briefings at a glance++The Home screen and Agents tab now display live briefings for each of your agents — a short, AI-generated summary of what the agent is doing, what it last completed, and what's coming next. Scheduled agents surface their upcoming run times automatically, so you always know the state of your fleet at a glance. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12764)++<figure><img src="../.gitbook/assets/agent-brief-homescreen-hero.png" alt="Agent briefings on the Home screen"><figcaption><p>Live agent briefings on the Home screen keep you up to date without opening each agent.</p></figcaption></figure>++<figure><img src="../.gitbook/assets/agent-brief-agents-tab-hero.png" alt="Agent briefings in the Agents tab"><figcaption><p>The Agents tab shows the same briefings alongside run history and scheduling details.</p></figcaption></figure>++## Chat with your builder++A new AI chat panel is now embedded directly in the flow builder. Ask questions about your graph, get help debugging a block configuration, or request changes to the workflow — all without switching context. The panel is aware of your current graph structure, making it a hands-on collaborator rather than a general assistant. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12699)++<figure><img src="../.gitbook/assets/ai-chat-builder-hero.png" alt="AI chat panel in the flow builder"><figcaption><p>The AI chat panel in the flow builder understands your graph and can suggest or apply changes inline.</p></figcaption></figure>++<details>++<summary>✨ Improvements</summary>++- **Graphiti memory** — Long-term memory via Graphiti is now available as a block for persistent agent knowledge. (v0.6.55)+- **Multi-question ask** — The `ask_question` block can now present multiple questions in a single prompt, reducing back-and-forth interruptions. (v0.6.55)+- **Standard / Advanced model toggle** — Easily switch between standard and advanced AI models per agent run. (v0.6.55)+- **xAI Grok models** — Grok models from xAI are now available in the model selector. (v0.6.57)+- **Web Push notifications** — Opt in to browser push notifications so you never miss an agent completion or action request. ([#12723](https://github.com/Significant-Gravitas/AutoGPT/pull/12723)) (v0.6.58)++</details>++<details>++<summary>🎨 UI/UX Improvements</summary>++- **Message timestamps** — Conversation messages now display timestamps for easier reference. ([#12890](https://github.com/Significant-Gravitas/AutoGPT/pull/12890)) (v0.6.58)++</details>++<details>++<summary>🐛 Bug Fixes</summary>++- **Artifact panel stability** — Fixed rendering and state management issues in the artifact side panel. ([#12856](https://github.com/Significant-Gravitas/AutoGPT/pull/12856)) (v0.6.57)+- **Scheduled agents in briefings** — Scheduled agents now correctly surface their next run time in agent briefings. ([#12818](https://github.com/Significant-Gravitas/AutoGPT/pull/12818)) (v0.6.57)++</details>diff --git a/docs/platform/changelog/february-11-february-26-2026.md b/docs/platform/changelog/february-11-february-26-2026.mdnew file mode 100644index 0000000000..e17ae68696--- /dev/null+++ b/docs/platform/changelog/february-11-february-26-2026.md@@ -0,0 +1,117 @@+# Telegram bots, agent folders, and a rebuilt builder++*February 11 – 26, 2026*++**Platform version:** `v0.6.49`++## AutoPilot got a major brain upgrade++AutoPilot is now powered by a completely new AI engine. It can hold real multi-step conversations, use tools behind the scenes, and handle complex requests that would have confused it before. When you need multiple things done at once, it runs them in parallel instead of one at a time — so everything finishes faster. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12103)++Ask it to run one of your agents and it will actually wait for the result and tell you what happened — no more "your agent started, go check later." [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12147)++{% hint style="info" %}+If your connection drops while AutoPilot is working on something, it keeps going in the background and picks up right where you left off when you reconnect. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12057)+{% endhint %}++## Automate your Telegram bots++Thirteen new Telegram blocks let you build agents that respond to messages, photos, voice notes, videos, and reactions. Set up triggers for incoming content, then reply with text, images, audio, documents, or video. Connect your bot token from [@BotFather](https://t.me/BotFather) and you're ready to go. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12141)++## The builder has been rebuilt++The old agent builder is gone. Everyone now uses the new flow editor — a cleaner, faster interface with improved node rendering and no more toggling between views. If you've been using the legacy builder, the experience should feel familiar but noticeably more polished. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12081)++## Organize agents into folders++Your agent library now supports folders. Create them with custom names, emoji icons, and colors, then drag-and-drop agents into them or right-click to move. Folders can be nested up to five levels deep, and a breadcrumb bar helps you navigate. Search still works across everything regardless of which folder you're in. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12101)++## Your files follow you everywhere++Files created during agent runs — whether from code execution, image generation, or document creation — now persist in your workspace automatically. They're accessible across conversations and sessions, and images render inline in chat. AutoPilot also retains full context about files and tools it used earlier in the conversation, so it won't "forget" what just happened. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12073) [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12164)++## Tell us what to build next++You can now submit feature requests directly through AutoPilot chat. Describe what you want — it checks for existing requests first and either creates a new one or adds your vote to a matching request so the team can see demand. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12102)++## Vague goals get refined, not rejected++If you ask AutoPilot to create an agent with a vague goal like "monitor social media," it now suggests a clearer, more actionable version instead of returning an error. Accept the suggestion with one click or refine it further. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12139)++## The stop button actually stops things++Clicking Stop now sends a real cancellation signal through the entire system. Previously it didn't always halt what was running behind the scenes — now it does. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12171)++***++<details>++<summary>Improvements</summary>++* [Delete chat sessions](https://github.com/Significant-Gravitas/AutoGPT/pull/12112) — clean up old conversations with a trash icon and confirmation dialog+* [Five new list blocks](https://github.com/Significant-Gravitas/AutoGPT/pull/12105) — Flatten, Interleave, Zip, Difference, and Intersection for agents that work with lists+* [Web search enabled for agents](https://github.com/Significant-Gravitas/AutoGPT/pull/12108) — agents can now search the web as part of their workflows+* [PDF generation support](https://github.com/Significant-Gravitas/AutoGPT/pull/12216) — agents can create and manipulate PDF documents+* [Faster, smarter block search](https://github.com/Significant-Gravitas/AutoGPT/pull/11806) — the builder search now combines keyword and semantic matching so you find what you need even without the exact name+* [Parallel tool execution](https://github.com/Significant-Gravitas/AutoGPT/pull/12165) — when an agent needs multiple tools at once, they run simultaneously instead of one at a time+* [Signup answers carry forward](https://github.com/Significant-Gravitas/AutoGPT/pull/12119) — information from your signup form pre-populates AutoPilot setup so you don't repeat yourself+* [Improved agent creation UX](https://github.com/Significant-Gravitas/AutoGPT/pull/12117) — cleaner create and edit experience with better progress feedback+* [Create agents via API](https://github.com/Significant-Gravitas/AutoGPT/pull/12208) — developers can now programmatically create agents through the external API+* [Exact timestamps on hover](https://github.com/Significant-Gravitas/AutoGPT/pull/12087) — hover over "2 hours ago" to see the full date and time+* [Credentials and inputs always visible](https://github.com/Significant-Gravitas/AutoGPT/pull/12194) — required setup steps and login prompts no longer hide inside collapsible sections+* [Clarification and save cards always visible](https://github.com/Significant-Gravitas/AutoGPT/pull/12204) — questions from AutoPilot and save confirmations are shown upfront instead of inside accordions+* [Task lists expanded by default](https://github.com/Significant-Gravitas/AutoGPT/pull/12168) — AutoPilot's to-do and task lists start open so you see everything immediately+* [Cleaner builder nodes](https://github.com/Significant-Gravitas/AutoGPT/pull/12152) — the "Advanced" switch on nodes replaced with a simpler chevron toggle+* [Easier connection deletion](https://github.com/Significant-Gravitas/AutoGPT/pull/12083) — the delete button appears when hovering anywhere on the connection line, not just a tiny target+* [Workspace files render in markdown](https://github.com/Significant-Gravitas/AutoGPT/pull/12166) — images and links from your workspace display correctly in chat messages+* [Better password reset experience](https://github.com/Significant-Gravitas/AutoGPT/pull/12123) — expired or already-used reset links now explain what happened and how to get a new one+* [Snake minigame while you wait](https://github.com/Significant-Gravitas/AutoGPT/pull/12160) — play a quick game of Snake during longer operations+* [Cleaner chat interface](https://github.com/Significant-Gravitas/AutoGPT/pull/12094) — improved spacing and styling in AutoPilot conversations++</details>++<details>++<summary>Fixes</summary>++* [Streaming completely overhauled](https://github.com/Significant-Gravitas/AutoGPT/pull/12173) — tool outputs no longer get lost, and refreshing the page preserves your conversation+* [Sessions no longer get stuck](https://github.com/Significant-Gravitas/AutoGPT/pull/12191) — fixed cases where the AI would stop responding with no way to recover+* [Long-running tasks no longer time out](https://github.com/Significant-Gravitas/AutoGPT/pull/12175) — complex tasks can run as long as needed instead of being killed after five minutes+* [Background agents no longer stall or hallucinate](https://github.com/Significant-Gravitas/AutoGPT/pull/12167) — the AI won't claim to have completed something it didn't actually do+* [Error messages are now actually helpful](https://github.com/Significant-Gravitas/AutoGPT/pull/12205) — real error details instead of generic failures, and switching between chats resumes properly+* [Reconnection preserves your messages](https://github.com/Significant-Gravitas/AutoGPT/pull/12159) — dropping and reconnecting no longer clears your chat history+* [API errors stay out of the chat](https://github.com/Significant-Gravitas/AutoGPT/pull/12063) — backend errors no longer appear as garbled text in your conversation+* [Agent creation follow-ups work](https://github.com/Significant-Gravitas/AutoGPT/pull/12062) — asking follow-up questions after creating an agent no longer causes errors+* [API key expiration default removed](https://github.com/Significant-Gravitas/AutoGPT/pull/12092) — API keys no longer auto-expire the next day; you choose whether to set an expiration+* [Text selection works in the builder](https://github.com/Significant-Gravitas/AutoGPT/pull/11955) — selecting text in input fields no longer accidentally drags the entire node+* [Website extraction errors handled](https://github.com/Significant-Gravitas/AutoGPT/pull/12048) — clear error messages when a website can't be fetched instead of silent failures+* [Content no longer overflows cards](https://github.com/Significant-Gravitas/AutoGPT/pull/12060) — block output text stays within its container instead of getting cut off+* [Workspace file listing improved](https://github.com/Significant-Gravitas/AutoGPT/pull/12190) — files display with proper names, sizes, and types instead of raw data+* ["Show all my agents" works](https://github.com/Significant-Gravitas/AutoGPT/pull/12138) — asking AutoPilot to list all your agents now actually lists them instead of returning nothing+* [External link button visible](https://github.com/Significant-Gravitas/AutoGPT/pull/12209) — the "Open link" button in the safety modal is now properly styled and clickable+* [No more crashes on logout](https://github.com/Significant-Gravitas/AutoGPT/pull/12202) — the AutoPilot page no longer breaks if you log out while it's open+* [Code highlighting performance](https://github.com/Significant-Gravitas/AutoGPT/pull/12144) — code blocks load faster and use less memory+* [Agent generation UI refreshes](https://github.com/Significant-Gravitas/AutoGPT/pull/12070) — the interface now updates when agent creation finishes instead of appearing stuck+* [Concurrent saves no longer conflict](https://github.com/Significant-Gravitas/AutoGPT/pull/12177) — sending multiple rapid messages no longer causes database errors+* [Workspace file downloads work](https://github.com/Significant-Gravitas/AutoGPT/pull/12215) — files created by the AI now include proper download links+* [Chat message spacing fixed](https://github.com/Significant-Gravitas/AutoGPT/pull/12091) — messages no longer have awkward extra whitespace++</details>++<details>++<summary>Under the hood</summary>++* [Message queue infrastructure upgraded](https://github.com/Significant-Gravitas/AutoGPT/pull/12118) — moved from an end-of-life version to a current, supported release for better reliability+* [Production dependencies updated](https://github.com/Significant-Gravitas/AutoGPT/pull/12056) — security patches and stability improvements across the stack+* [Security scanning updated](https://github.com/Significant-Gravitas/AutoGPT/pull/12033) — upgraded the tools that automatically check for vulnerabilities+* [Block search responses optimized](https://github.com/Significant-Gravitas/AutoGPT/pull/12020) — reduced data sent during block lookups so searches feel snappier+* [Legacy builder code removed](https://github.com/Significant-Gravitas/AutoGPT/pull/12082) — with the new flow editor live, the old code has been fully cleaned out+* [Legacy agent views removed](https://github.com/Significant-Gravitas/AutoGPT/pull/12088) — retired old UI components for a lighter, faster app+* [Internal module structure improved](https://github.com/Significant-Gravitas/AutoGPT/pull/12068) — reduced circular dependencies for more reliable startup+* [UI components modernized](https://github.com/Significant-Gravitas/AutoGPT/pull/12136) — replaced legacy dialog components with the current design system+* [Error logging improved](https://github.com/Significant-Gravitas/AutoGPT/pull/11942) — more detailed API error tracking so issues get found and resolved faster+* [HumanInTheLoop block docs clarified](https://github.com/Significant-Gravitas/AutoGPT/pull/12069) — clearer output descriptions for the agent builder+* [Podman compatibility note added](https://github.com/Significant-Gravitas/AutoGPT/pull/12120) — documented a known limitation for users running Podman instead of Docker++</details>diff --git a/docs/platform/changelog/february-26-march-4-2026.md b/docs/platform/changelog/february-26-march-4-2026.mdnew file mode 100644index 0000000000..1b3b5459ce--- /dev/null+++ b/docs/platform/changelog/february-26-march-4-2026.md@@ -0,0 +1,74 @@+# Connect any app, share files, and let AutoPilot browse for you++*February 26 – March 4, 2026*++**Platform version:** `v0.6.50`++## Connect to any app — instantly++That integration you've been waiting for? You don't need to wait anymore. AutoPilot now supports MCP (Model Context Protocol) — an open standard backed by hundreds of ready-made connectors for apps like Notion, Slack, Jira, Stripe, Postgres, and more. **Just tell AutoPilot what you want to connect to, and it finds and sets it up automatically** — nothing to install, nothing to configure. Search your Notion workspace, query a database, create a Jira ticket — all from the chat. If the service requires a login, you'll get the same familiar sign-in prompt you already know. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12213)++<figure><img src="../.gitbook/assets/mcp-notion-hero.png" alt="AutoPilot connecting to Notion via MCP and searching a workspace in real time"><figcaption><p>AutoPilot connecting to Notion and pulling release highlights — no integration setup required</p></figcaption></figure>++## Upload files to AutoPilot++You can now attach files directly in the AutoPilot chat — documents, images, spreadsheets, audio, and video. Hit the **+** button or drag and drop files into the chat. Once sent, your attachments display inline in the conversation and the AI can read and reference them. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12220)++<figure><img src="../.gitbook/assets/file-upload-hero.png" alt="Dragging a file into the AutoPilot chat"><figcaption><p>Drop files directly into the chat and AutoPilot picks them up instantly</p></figcaption></figure>++## AutoPilot can run code and create files for you++You can now drop a messy spreadsheet into AutoPilot and ask it to clean the data, find trends, and generate a polished chart. It can crunch numbers, build scripts, create documents, and produce downloadable files, all inside the conversation. Each step builds on the last, so you can go from raw data to finished deliverable just by asking. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12212)++<figure><img src="../.gitbook/assets/code-execution-hero.png" alt="AutoPilot analyzing business data and generating a sales performance dashboard"><figcaption><p>AutoPilot analyzing 14 months of business data and generating a dashboard — all from a single request</p></figcaption></figure>++## AutoPilot can browse the web for you++Two new browsing capabilities let AutoPilot interact with websites on your behalf. For quick lookups, it can fetch and extract content from any page in one shot. For multi-step tasks — like logging into a site, navigating through menus, and pulling data — it drives a full browser session that persists across steps within your conversation. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12230)++<figure><img src="../.gitbook/assets/web-browsing-hero.png" alt="AutoPilot browsing a website autonomously in a live browser session"><figcaption><p>AutoPilot navigating a website in a live browser session</p></figcaption></figure>++## Listen to responses or copy them instantly++Multitasking? Tap the speaker icon on any message to have AutoPilot read it aloud while you do something else. Need to save a response? Hit the copy button to grab it in one click — ready to paste into an email, doc, or chat. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12256)++## See when the AI is summarizing++When a conversation gets long enough that AutoPilot needs to summarize earlier messages to stay within its memory limits, you'll now see a clear indicator — a spinner with "Summarizing earlier messages…" — instead of it happening silently in the background. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12250)++## Redesigned chat input++The chat input bar has been rebuilt with a cleaner layout — a spacious text area that grows smoothly as you type, with tool buttons and the send button in a tidy footer row. No more jarring height jumps when composing longer messages. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12207)++***++<details>++<summary>Improvements</summary>++* [More reliable streaming](https://github.com/Significant-Gravitas/AutoGPT/pull/12254) — AutoPilot now connects directly to the backend for real-time updates, avoiding an intermediate proxy that could cause timeouts on long-running tasks+* [Faster stall recovery](https://github.com/Significant-Gravitas/AutoGPT/pull/12254) — if the connection goes quiet, AutoPilot detects it in 10 seconds instead of 30 and reconnects automatically+* [Stop button works instantly](https://github.com/Significant-Gravitas/AutoGPT/pull/12254) — clicking Stop now immediately unlocks the input so you can keep working++</details>++<details>++<summary>Fixes</summary>++* [Node output no longer overflows](https://github.com/Significant-Gravitas/AutoGPT/pull/12222) — long text and JSON in the agent builder stays within its container, with output items capped for readability+* [Workspace file saves no longer conflict](https://github.com/Significant-Gravitas/AutoGPT/pull/12267) — when two operations write to the same file at the same time, you get a clear message instead of a raw error+* [Login no longer shows a blank page](https://github.com/Significant-Gravitas/AutoGPT/pull/12285) — signing in with email and password now loads the app immediately instead of requiring a manual refresh++</details>++<details>++<summary>Under the hood</summary>++* [Observability for the AI engine](https://github.com/Significant-Gravitas/AutoGPT/pull/12228) — every AutoPilot conversation turn is now traced with token counts, costs, and timing for faster debugging+* [Broadcast tracing enabled](https://github.com/Significant-Gravitas/AutoGPT/pull/12277) — monitoring coverage extended to the AI model routing layer+* [Legacy code removed](https://github.com/Significant-Gravitas/AutoGPT/pull/12276) — ~1,200 lines of old, unmaintained chat code cleaned out and replaced with a streamlined fallback path+* [Auto-synced developer tooling](https://github.com/Significant-Gravitas/AutoGPT/pull/12211) — switching branches now automatically keeps types and dependencies in sync++</details>diff --git a/docs/platform/changelog/january-29-february-11-2026.md b/docs/platform/changelog/january-29-february-11-2026.mdnew file mode 100644index 0000000000..da053bfac3--- /dev/null+++ b/docs/platform/changelog/january-29-february-11-2026.md@@ -0,0 +1,95 @@+# Voice input, persistent files, and a smarter AI++*January 29 – February 11, 2026*++**Platform version:** `v0.6.48`++## Talk to AutoPilot with your voice++A mic button has been added to the chat input. Press it, speak your request, and your voice is transcribed instantly. The text box auto-focuses so you can hit Enter to send or tap the mic again to keep talking. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/11871)++## Your files stick around++Files generated during conversations — images, documents, anything — are now saved to your personal workspace instead of disappearing when the session ends. You can browse and manage them directly through chat, and images show up inline in the conversation. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/11867)++{% hint style="success" %}+This also unblocked **20+ blocks** (file storage, email attachments, screenshots, image generation, and more) that weren't working in chat.+{% endhint %}++## Upgraded to Claude Opus 4.6++AutoPilot now runs on Anthropic's newest and most capable model, with a larger context window and doubled output capacity. Extended thinking is enabled, so the AI reasons internally before responding — you get cleaner, more focused answers instead of raw chain-of-thought in the chat. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/11983)++{% hint style="info" %}+Claude 3.7 Sonnet has been retired. Agents using it were auto-migrated to Claude 4.5 Sonnet.+{% endhint %}++## Customize marketplace agents++Ask AutoPilot to modify any marketplace agent before adding it to your library. "Customize that newsletter writer to post to Discord instead." AutoPilot adapts the workflow, asks follow-up questions if needed, and saves the customized version for you. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/11943)++## Rebuilt chat streaming++The entire chat system has been rebuilt on the Vercel AI SDK. More reliable message delivery, better Markdown formatting, tool outputs shown in clean collapsible panels, and errors surfaced as brief notifications instead of breaking the chat. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/11901)++## Stay connected during long tasks++If your connection drops while AutoPilot is working (network hiccup, laptop sleep, switching tabs), it keeps going in the background, saves progress, and replays what you missed when you reconnect. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/11877)++## New agents reuse your existing ones++When building a new agent, AutoPilot searches your library for agents that can be incorporated as building blocks — so you don't rebuild from scratch. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/11889)++## Better agent creation++Progress bar during generation so you're not staring at a blank screen. A "Your agent is ready!" prompt with buttons to test immediately or provide your own inputs. Cleaner formatting when AutoPilot asks you clarifying questions. And helpful error messages instead of generic failures. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/11974)++## Updated homepage text++The homepage now says "Tell me about your work — I'll find what to automate" instead of assuming you already know what to build. The quick-start buttons have been rewritten too: [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/11956)++{% tabs %}++{% tab title="After" %}+* "I don't know where to start, just ask me stuff"+* "I do the same thing every week and it's killing me"+* "Help me find where I'm wasting my time"+{% endtab %}++{% tab title="Before" %}+* ~~"Show me what I can automate"~~+* ~~"Design a custom workflow"~~+* ~~"Help me with content creation"~~+{% endtab %}++{% endtabs %}++***++<details>++<summary>Improvements</summary>++* [Editing agents updates the original](https://github.com/Significant-Gravitas/AutoGPT/pull/11981) instead of creating a duplicate in your library+* ["Tasks" tab renamed to "Agents"](https://github.com/Significant-Gravitas/AutoGPT/pull/11982) to better describe what's there+* [Wallet stays closed](https://github.com/Significant-Gravitas/AutoGPT/pull/11961) — no longer pops open automatically for new users or on balance changes+* [Search suggests next steps](https://github.com/Significant-Gravitas/AutoGPT/pull/11976), like offering to create a custom agent from your query+* [Smarter block filtering](https://github.com/Significant-Gravitas/AutoGPT/pull/11892) — chat no longer shows blocks that only work in the visual builder+* [Linear search block upgraded](https://github.com/Significant-Gravitas/AutoGPT/pull/11967) — now returns status, assignee, and project info with team filtering+* [New Text Encoder block](https://github.com/Significant-Gravitas/AutoGPT/pull/11857) for escaping special characters in JSON payloads and config files++</details>++<details>++<summary>Fixes</summary>++* [Improved credential matching](https://github.com/Significant-Gravitas/AutoGPT/pull/11908) so agents reliably use the correct API keys and permissions for each provider+* [Better input validation](https://github.com/Significant-Gravitas/AutoGPT/pull/11916) — agent inputs are now validated upfront with clear feedback on available fields+* [Marketplace agents work as sub-agents](https://github.com/Significant-Gravitas/AutoGPT/pull/11920) — referencing marketplace templates in new builds no longer fails+* [YouTube transcription fixed](https://github.com/Significant-Gravitas/AutoGPT/pull/11980) — cleanly reports either success or failure, not both+* [Long conversations stay responsive](https://github.com/Significant-Gravitas/AutoGPT/pull/11937) — improved context management for longer chat sessions+* [Agent list loads faster](https://github.com/Significant-Gravitas/AutoGPT/pull/12053) — optimized the endpoint that loads your agents+* [Login redirects fixed](https://github.com/Significant-Gravitas/AutoGPT/pull/11894) — resolved an issue where hard refresh could briefly show the wrong page++</details>diff --git a/docs/platform/changelog/june-18-july-9-2026.md b/docs/platform/changelog/june-18-july-9-2026.mdnew file mode 100644index 0000000000..ff12f601a0--- /dev/null+++ b/docs/platform/changelog/june-18-july-9-2026.md@@ -0,0 +1,60 @@+# Organize files, share your work, connect Discord++*June 18 – July 9, 2026*++**Platform versions:** `v0.6.64` · `v0.6.65` · `v0.6.66`++## A home for all your files++Every file your agents create or use now lives in one place — the Files page. Organize outputs into folders so reports, images, and data are easy to find and reuse. Search across everything instantly, and filter by uploaded vs generated files. [#13359](https://github.com/Significant-Gravitas/AutoGPT/pull/13359)++<figure><img src="../.gitbook/assets/files-hero.png" alt="Files page showing folders and file organization"><figcaption><p>All your agent files in one organized workspace</p></figcaption></figure>++## Share any conversation with a link++Enable sharing and send the generated link to share an AutoPilot conversation. Anyone with the link can view the conversation without signing in. Sharing is live: new messages and files added after you share become visible too, and agent runs become visible when that option is enabled. Turning sharing off invalidates the existing link.++<figure><img src="../.gitbook/assets/share-chat-hero.png" alt="Share this chat modal with enable sharing button"><figcaption><p>Share a live conversation link — revoke it anytime</p></figcaption></figure>++## Bring AutoPilot to your Discord server++Connect AutoGPT to Discord from Settings → Bots. Add the bot to any server, link a DM channel to chat directly, upload files from Discord straight into AutoPilot, and get outputs delivered to your community in real time. [#13298](https://github.com/Significant-Gravitas/AutoGPT/pull/13298) [#13427](https://github.com/Significant-Gravitas/AutoGPT/pull/13427)++<figure><img src="../.gitbook/assets/discord-bot-hero.png" alt="Bots settings page showing Discord integration"><figcaption><p>Connect AutoPilot to your Discord server or DM channel</p></figcaption></figure>++<details>++<summary>✨ Improvements</summary>++- **Browse any agent graph** — view any public agent in the Builder without editing it, perfect for learning how automations are built. ([#13238](https://github.com/Significant-Gravitas/AutoGPT/pull/13238))+- **AutoPilot remembers where it left off** — full action history is now preserved when continuing a task across multiple sessions. ([#12673](https://github.com/Significant-Gravitas/AutoGPT/pull/12673))+- **Webhook triggers for AutoPilot** — trigger AutoPilot from external services using webhooks, with full preset lifecycle management. ([#13298](https://github.com/Significant-Gravitas/AutoGPT/pull/13298))+- **Faster builder search** — search results in the agent builder load noticeably faster. ([#13290](https://github.com/Significant-Gravitas/AutoGPT/pull/13290))+- **Reliable graph saves** — agent graphs now save atomically, with clearer error messages when credentials are missing. ([#13264](https://github.com/Significant-Gravitas/AutoGPT/pull/13264))+- **Plans default to monthly billing.** ([#13363](https://github.com/Significant-Gravitas/AutoGPT/pull/13363))++</details>++<details>++<summary>🎨 UI/UX Improvements</summary>++- **Global search polish** — loading state added and jittery animations removed. ([#13454](https://github.com/Significant-Gravitas/AutoGPT/pull/13454))+- **Schedule Run button fix** — button stays enabled while editing a schedule name. ([#13481](https://github.com/Significant-Gravitas/AutoGPT/pull/13481))+- **Builder tutorial highlight** — selected node output is now highlighted during the builder tutorial run step. ([#13483](https://github.com/Significant-Gravitas/AutoGPT/pull/13483))++</details>++<details>++<summary>🐛 Bug Fixes</summary>++- **AutoPilot responses in Discord** — fixed text blocks running together in Discord messages. ([#13424](https://github.com/Significant-Gravitas/AutoGPT/pull/13424))+- **Save-and-run uses the latest version** — fixed agents running the previous saved version instead of the one you just saved. ([#13482](https://github.com/Significant-Gravitas/AutoGPT/pull/13482))+- **AutoPilot task cancellation** — fixed chat streaming cutting off mid-message when cancelling a task. ([#13452](https://github.com/Significant-Gravitas/AutoGPT/pull/13452))+- **Agents using OpenAI extended reasoning** — fixed agents failing mid-task when OpenAI tool loops included reasoning steps. ([#13438](https://github.com/Significant-Gravitas/AutoGPT/pull/13438))+- **LLM provider stability** — fixed crashes from OpenAI and Anthropic API changes. ([#13335](https://github.com/Significant-Gravitas/AutoGPT/pull/13335), [#13342](https://github.com/Significant-Gravitas/AutoGPT/pull/13342))+- **Files page previews** — fixed code and markdown file previews not rendering correctly. ([#13304](https://github.com/Significant-Gravitas/AutoGPT/pull/13304))+- **Scheduled AutoPilot tasks** — fixed tasks not registering correctly when created. ([#13336](https://github.com/Significant-Gravitas/AutoGPT/pull/13336))++</details>diff --git a/docs/platform/changelog/march-13-march-20-2026.md b/docs/platform/changelog/march-13-march-20-2026.mdnew file mode 100644index 0000000000..4a79af89ba--- /dev/null+++ b/docs/platform/changelog/march-13-march-20-2026.md@@ -0,0 +1,77 @@+# Explore a new marketplace, track usage, and give instant feedback++*March 13 – March 20, 2026*++**Platform version:** `v0.6.52`++This week's release brings a **refreshed marketplace**, a **usage monitor** so you always know where your credits stand, and a **new feedback button**.++***++## A brand-new marketplace experience++The marketplace has been **completely redesigned** with a cleaner, more professional look. Agent cards now feature subtle borders and refined spacing, the search bar matches our design system, and everything feels polished at every screen size. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12462)++<figure><img src="../.gitbook/assets/marketplace-hero.png" alt="The redesigned AutoGPT marketplace with polished agent cards and clean layout"><figcaption><p>The redesigned marketplace — cleaner cards, better search, and a professional new look</p></figcaption></figure>++***++## Track your usage at a glance++A new **usage monitor** gives you full visibility into your credit balance and token usage. You'll see daily and weekly progress bars, reset times, and a clear breakdown of how your credits are being spent — all from a simple popover in the interface. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12385)++<figure><img src="../.gitbook/assets/usage-monitor-hero.png" alt="The new usage monitor showing credit balance and token usage"><figcaption><p>Keep tabs on your credit usage with daily and weekly breakdowns</p></figcaption></figure>++***++## Give feedback from anywhere++The **feedback button** has moved to the header, making it accessible from any page. Share your thoughts, report issues, or request features without having to navigate away from what you're doing. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12462)++<figure><img src="../.gitbook/assets/feedback-button-hero.png" alt="The new feedback button in the header"><figcaption><p>The feedback button is now always within reach in the header</p></figcaption></figure>++***++<details>++<summary>Improvements</summary>++* **Shareable prompt links** — share an AutoPilot prompt via URL so anyone can try it out with a single click — a great way to share use cases and ideas [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12406)+* **"Run now" button on schedules** — manually trigger any scheduled agent run with one click [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12388)+* **"Jump Back In" on Library** — quickly resume your most recent agent right from the Library page [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12387)+* **Rich media previews in Builder** — see images, files, and other media directly in node outputs and file inputs [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12432)+* **Graph search in Builder** — find any node or block instantly in your agent graphs [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12395)+* **Themed prompt categories** — suggestion pills are now organized into themed categories for easier discovery [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12452)+* **Nano Banana 2** — the latest image generation model is now available in the image generator, customizer, and editor blocks [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12218)+* **AgentMail integration** — new blocks for managing email workflows through AgentMail [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12417)++</details>++<details>++<summary>Fixes</summary>++* Fixed sub-folders not showing when navigating inside a folder [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12316)+* Fixed image delete button on the Edit Agent form [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12362)+* Improved handling of transient API connection errors [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12445)+* Fixed tool-result file reads failing across turns [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12399)+* Fixed long filenames being truncated incorrectly [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12025)+* Allowed falsy values in list building blocks [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12028)+* Renamed "CoPilot" to "AutoPilot" on the credits page [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12481)+* Constrained Markdown heading sizes in chat messages [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12463)++</details>++<details>++<summary>Under the hood</summary>++* Read-only SQL views layer with analytics schema [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12367)+* AutoPilot block for running AutoPilot from inside agents or as a sub-agent within AutoPilot itself [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12439)+* GitHub CLI support with automatic token injection [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12426)+* Improved end-to-end CI with reduced costs [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12437)+* New integration tests for Builder stores, components, and hooks [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12433)+* Builder end-to-end tests for the new Flow Editor [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12436)+* Collapsed navbar text to icons below 1280px [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12484)++</details>diff --git a/docs/platform/changelog/march-20-march-25-2026.md b/docs/platform/changelog/march-20-march-25-2026.mdnew file mode 100644index 0000000000..532944c5bd--- /dev/null+++ b/docs/platform/changelog/march-20-march-25-2026.md@@ -0,0 +1,68 @@+# Import workflows from other platforms and enjoy a polished marketplace++*March 20 – March 25, 2026*++**Platform version:** `v0.6.53`++This release makes it easier than ever to **bring your existing automations into AutoGPT**. You can now import workflows straight from n8n, Make.com, and Zapier, **test your agents before they go live** with a new dry-run mode, plus the marketplace gets another round of visual polish.++***++## Import workflows from n8n, Make.com & Zapier++Switching to AutoGPT no longer means starting from scratch. A new **workflow import** feature lets you bring in automations you've already built on other platforms and convert them into AutoGPT agents. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12440)++<figure><img src="../.gitbook/assets/import-workflows-hero.png" alt="Import workflows from other platforms"><figcaption><p>Import your existing workflows from n8n, Make.com, and Zapier directly into AutoGPT.</p></figcaption></figure>++***++## A more polished marketplace++The marketplace continues to get cleaner and easier to browse. Card descriptions are now **neatly truncated** to keep the layout consistent, the download button has been **repositioned** for better flow, and card overflow issues have been resolved. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12494)++<figure><img src="../.gitbook/assets/marketplace-ui-v053-hero.png" alt="UI improvements to the marketplace"><figcaption><p>Cleaner marketplace cards with consistent layout and improved button placement.</p></figcaption></figure>++***++## Test your agents before they go live++A new **dry-run mode** lets you simulate a full run of any agent without real-world side effects. Every block executes and produces realistic outputs, so you can verify your agent works correctly — before it sends emails, updates spreadsheets, or takes any real action. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12483)++This is especially powerful with AutoPilot. When AutoPilot builds an agent for you, it can now automatically test it to make sure it works and the quality is up to standard. It can also preview exactly what an agent will do before you commit to running it — so you always know what to expect.++***++<details>+<summary>Improvements</summary>++* **Parallel AutoPilot actions** — When AutoPilot needs to perform several steps at once, it now runs them simultaneously — no more waiting for each to finish before starting the next. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12472)+* **Scoped AutoPilot tools** — You can now control exactly which tools and blocks AutoPilot has access to — whether running it as a block or using sub-agents — so you can build tightly constrained agentic systems. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12482)+* **Leaner tool schemas** — Tool schema token cost has been reduced by 34%, meaning faster and cheaper AutoPilot. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12398)+* **Admin marketplace preview** — Admins can now preview and download submitted agents before approving them. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12536)++</details>+++<details>+<summary>Fixes</summary>++* Fixed blocks with complex inputs (e.g. GitHub Multi-File Commit) sometimes failing silently [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12496)+* Fixed auto top-up setup showing a generic error when no payment method is on file [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12496)+* Fixed re-uploading a file to AutoPilot failing instead of replacing the existing file [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12496)+* OAuth popup detection — the app now notices when you close an OAuth window and lets you dismiss the waiting modal [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12443)+* Added circuit breaker to prevent infinite tool-call retry loops [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12499)+* Reduced noisy error logging from user-caused LLM API errors [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12516)+* Fixed browser automation to use system Chromium on all architectures [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12473)++</details>++<details>+<summary>Under the hood</summary>++* Renamed SmartDecisionMakerBlock to OrchestratorBlock for clarity [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12511)+* Added DB_STATEMENT_CACHE_SIZE env var for Prisma engine tuning [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12521)+* Bumped stagehand ^0.5.1 → ^3.4.0 to fix yanked litellm dependency [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12539)+* Registered AutoPilot sessions with stream registry for SSE updates [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12500)+* Allowed /tmp as valid path in E2B sandbox file tools [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12501)++</details>diff --git a/docs/platform/changelog/march-23-april-9-2026.md b/docs/platform/changelog/march-23-april-9-2026.mdnew file mode 100644index 0000000000..c7ee11a555--- /dev/null+++ b/docs/platform/changelog/march-23-april-9-2026.md@@ -0,0 +1,90 @@+# Smarter Starts, Faster Feedback++*March 23 – April 9, 2026*++**Platform version:** `v0.6.54`++## Themed Prompt Categories++When you start a new AutoPilot conversation, you now see **themed prompt categories** — Learn, Create, Automate, and Organize. Each theme button opens a popover with **5 contextual prompts** tailored to the category. Personalized prompts are distributed across themes automatically. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12515)++<figure><img src="../.gitbook/assets/v0654-prompt-categories-hero.png" alt="Themed prompt categories in the AutoPilot empty session"><figcaption><p>Themed prompt categories on the new conversation screen</p></figcaption></figure>++## Live Timer Stats++A **live elapsed timer** now appears in the AutoPilot thinking indicator while the AI is processing — showing "23s", "1m 5s" and so on after a 20-second threshold so quick responses aren't cluttered. Once the response completes, a **"Thought for Xm Ys" badge** freezes in place below the message. The duration **stays with the conversation**, so you can always see how long a response took — even after refreshing the page or revisiting an older chat. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12583)++<figure><img src="../.gitbook/assets/v0654-live-timer-hero.png" alt="Live timer stats showing elapsed thinking time"><figcaption><p>Live elapsed timer and persisted thinking duration</p></figcaption></figure>++## Redesigned Onboarding++The onboarding wizard has been **completely redesigned** with an AutoPilot-first flow. A polished 4-step experience — Welcome → Role selection → Pain points → Preparing workspace — collects your role and pain points to **personalize AutoPilot suggestions** from the start. Pain points are **reordered based on your selected role** (e.g. Sales sees "Finding leads" first), and steps sync with URL params so browser back/forward just works. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12640)++<figure><img src="../.gitbook/assets/v0654-onboarding-hero.png" alt="Redesigned onboarding wizard with role selection"><figcaption><p>New 4-step onboarding wizard with role-based personalization</p></figcaption></figure>++## Copy Your Prompts++You can now **copy your own prompt messages** in AutoPilot with a single click. A copy button appears on hover — right-aligned below the message — using the same `CopyButton` component already available on assistant responses. No more manual text selection when you want to **reuse or share a prompt** you've written. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12571)++<figure><img src="../.gitbook/assets/v0654-copy-prompts-hero.png" alt="Copy button on user prompt messages"><figcaption><p>One-click copy button on your own prompt messages</p></figcaption></figure>++<details>++<summary>✨ Improvements</summary>++- **Spend credits to reset AutoPilot daily rate limit** — Hit your daily message cap? Spend credits to keep going without waiting for the reset. ([#12526](https://github.com/Significant-Gravitas/AutoGPT/pull/12526))+- **Rate-limit tiering system** — AutoPilot now supports configurable rate-limit tiers so different user plans get different message caps. ([#12581](https://github.com/Significant-Gravitas/AutoGPT/pull/12581))+- **Extended thinking execution mode** — OrchestratorBlock gains an extended thinking mode for deeper, multi-step reasoning. ([#12512](https://github.com/Significant-Gravitas/AutoGPT/pull/12512))+- **Automatic AgentMail setup** — AgentMail now works out of the box. Your email address is created automatically the first time you need it — no API keys or manual setup required. ([#12537](https://github.com/Significant-Gravitas/AutoGPT/pull/12537))+- **Session-level dry-run flag** — AutoPilot sessions can now be flagged as dry-run at the session level. ([#12582](https://github.com/Significant-Gravitas/AutoGPT/pull/12582))+- **Generic ask_question AutoPilot tool** — A new tool lets AutoPilot ask structured clarifying questions mid-conversation. ([#12647](https://github.com/Significant-Gravitas/AutoGPT/pull/12647))+- **Git committer identity from GitHub profile** — E2B sandbox commits now use the user's real GitHub name and email. ([#12650](https://github.com/Significant-Gravitas/AutoGPT/pull/12650))+- **Create → dry-run → fix agent generation loop** — Agent generation now follows an iterative create, dry-run, and fix cycle for better results. ([#12578](https://github.com/Significant-Gravitas/AutoGPT/pull/12578))+- **All 12 Z.ai GLM models via OpenRouter** — Access every Z.ai GLM model through OpenRouter integration. ([#12672](https://github.com/Significant-Gravitas/AutoGPT/pull/12672))+- **include_graph option for find_library_agent** — Fetch the full graph structure when searching library agents for debugging or editing. ([#12622](https://github.com/Significant-Gravitas/AutoGPT/pull/12622))+- **Cursor-based message pagination** — AutoPilot messages load newest-first with cursor-based pagination for faster load times. ([#12328](https://github.com/Significant-Gravitas/AutoGPT/pull/12328))+- **Codecov coverage reporting** — Coverage reporting set up across platform and classic with Playwright E2E included. ([#12655](https://github.com/Significant-Gravitas/AutoGPT/pull/12655), [#12665](https://github.com/Significant-Gravitas/AutoGPT/pull/12665))+- **React integration testing** — Vitest + React Testing Library + MSW test infrastructure added. ([#12667](https://github.com/Significant-Gravitas/AutoGPT/pull/12667))+- **Cost tracking for system credentials** — Platform now tracks costs incurred by system-managed credentials. ([#12696](https://github.com/Significant-Gravitas/AutoGPT/pull/12696))++</details>++<details>++<summary>🎨 UI/UX Improvements</summary>++- **Auto-reconnect after device sleep** — AutoPilot chat reconnects automatically after your device wakes from sleep. ([#12519](https://github.com/Significant-Gravitas/AutoGPT/pull/12519))+- **Marketplace card descriptions** — Cards now show 3-line descriptions with a fallback color when no image exists. ([#12557](https://github.com/Significant-Gravitas/AutoGPT/pull/12557))+- **Hide placeholder during voice recording** — Placeholder text hides when AutoPilot voice recording is active. ([#12534](https://github.com/Significant-Gravitas/AutoGPT/pull/12534))+- **Array field layout fix** — Fixed array field item layout and added FormRenderer Storybook stories. ([#12532](https://github.com/Significant-Gravitas/AutoGPT/pull/12532))+- **Realistic AutoPilot suggestions** — Replaced unrealistic AutoPilot suggestion prompts with practical ones. ([#12564](https://github.com/Significant-Gravitas/AutoGPT/pull/12564))+- **Show all agent outputs** — Agent results now display all outputs, not just the last one. ([#12504](https://github.com/Significant-Gravitas/AutoGPT/pull/12504))+- **Notification follow-ups** — AutoPilot notifications gain branding, UX improvements, persistence, and cross-tab sync. ([#12428](https://github.com/Significant-Gravitas/AutoGPT/pull/12428))+- **Horizontal scroll for JSON output** — Builder JSON output data now scrolls horizontally instead of overflowing. ([#12638](https://github.com/Significant-Gravitas/AutoGPT/pull/12638))+- **Onboarding polish** — Refined AutoPilot onboarding with branding, auto-advance, soft cap, and visual polish. ([#12686](https://github.com/Significant-Gravitas/AutoGPT/pull/12686))++</details>++<details>++<summary>🐛 Bug Fixes</summary>++- **Prevent graph execution stuck** — Fixed stuck graph executions and steered SDK away from bash_exec. ([#12548](https://github.com/Significant-Gravitas/AutoGPT/pull/12548))+- **Sentry error reduction** — Multiple rounds of prod Sentry error fixes to reduce on-call alert noise. ([#12560](https://github.com/Significant-Gravitas/AutoGPT/pull/12560), [#12565](https://github.com/Significant-Gravitas/AutoGPT/pull/12565))+- **Sink input validation** — AgentValidator now validates sink inputs to catch wiring errors early. ([#12514](https://github.com/Significant-Gravitas/AutoGPT/pull/12514))+- **Docker Node.js upgrade** — Upgraded from EOL Node.js v21 to v22 LTS in Docker images. ([#12561](https://github.com/Significant-Gravitas/AutoGPT/pull/12561))+- **Thinking block preservation** — Thinking blocks are now preserved during transcript compaction. ([#12574](https://github.com/Significant-Gravitas/AutoGPT/pull/12574))+- **AIConditionBlock error handling** — Errors are now raised instead of silently swallowed. ([#12593](https://github.com/Significant-Gravitas/AutoGPT/pull/12593))+- **Host-scoped credentials** — Fixed credential resolution for authenticated web requests. ([#12579](https://github.com/Significant-Gravitas/AutoGPT/pull/12579))+- **Duplicate tool name disambiguation** — OrchestratorBlock now disambiguates duplicate tool names. ([#12555](https://github.com/Significant-Gravitas/AutoGPT/pull/12555))+- **Gmail recipient validation** — Gmail blocks validate email recipients before making API calls. ([#12546](https://github.com/Significant-Gravitas/AutoGPT/pull/12546))+- **Tool call circuit breakers** — Added circuit breakers and intermediate persistence in AutoPilot. ([#12604](https://github.com/Significant-Gravitas/AutoGPT/pull/12604))+- **Prompt-too-long retry** — Automatic compaction, model-aware compression, and truncated tool call recovery. ([#12625](https://github.com/Significant-Gravitas/AutoGPT/pull/12625))+- **Credential loading fix** — Fixed AutoPilot credential loading across event loops. ([#12628](https://github.com/Significant-Gravitas/AutoGPT/pull/12628))+- **Duplicate block execution prevention** — Prevented duplicate execution from pre-launch argument mismatch. ([#12632](https://github.com/Significant-Gravitas/AutoGPT/pull/12632))+- **Tool output file reading** — Fixed tool output file reading between E2B and host. ([#12646](https://github.com/Significant-Gravitas/AutoGPT/pull/12646))+- **Dry-run mode propagation** — Dry-run mode now propagates to special blocks with LLM-powered simulation. ([#12575](https://github.com/Significant-Gravitas/AutoGPT/pull/12575))+- **Double-submit prevention** — Prevented duplicate side effects from double-submit and stale-cache races. ([#12660](https://github.com/Significant-Gravitas/AutoGPT/pull/12660))+- **Silent DataError fix** — Wrapped PlatformCostLog metadata in SafeJson to fix silent DataError. ([#12713](https://github.com/Significant-Gravitas/AutoGPT/pull/12713))++</details>diff --git a/docs/platform/changelog/march-5-march-12-2026.md b/docs/platform/changelog/march-5-march-12-2026.mdnew file mode 100644index 0000000000..27d895b700--- /dev/null+++ b/docs/platform/changelog/march-5-march-12-2026.md@@ -0,0 +1,85 @@+# Organize your agents, get notified, and enjoy a cleaner chat++*March 5 – March 12, 2026*++**Platform version:** `v0.6.51`++## Organize agents with drag-and-drop folders++Building on the folder support introduced in the previous release, you can now **drag and drop agents between folders**, rename folders, and color-code them to match your workflow. Whether you have five agents or fifty, everything stays tidy. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12290)++<figure><img src="../.gitbook/assets/folders-hero.png" alt="Organizing agents into color-coded folders in the AutoGPT library"><figcaption><p>Organizing agents into color-coded folders in the AutoGPT library</p></figcaption></figure>++## Get notified when background chats finish++AutoPilot now sends you a **notification when a background chat completes**. No more switching tabs to check — you'll see a toast alert the moment your agent finishes its work, so you can jump right back into the results. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12364)++<figure><img src="../.gitbook/assets/notifications-hero.png" alt="AutoPilot notification appearing when a background chat finishes its work"><figcaption><p>AutoPilot notification appearing when a background chat finishes its work</p></figcaption></figure>++## Cleaner reasoning & chat experience++We've redesigned how **reasoning steps and tool calls appear in chat**. Intermediate thinking is now collapsed by default, keeping your conversation clean and easy to read. Expand any step if you want the full details. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12282)++<figure><img src="../.gitbook/assets/reasoning-hero.png" alt="Collapsed reasoning steps keeping the AutoPilot conversation clean and focused"><figcaption><p>Collapsed reasoning steps keeping the AutoPilot conversation clean and focused</p></figcaption></figure>++## Give feedback and share outputs instantly++Every response now comes with **action buttons to copy, upvote, downvote, or listen to the output**. Give quick feedback on any response so AutoPilot keeps getting better, and copy or share results in one tap. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12260)++<figure><img src="../.gitbook/assets/outputs-hero.png" alt="Output action buttons for copying, rating, and sharing AutoPilot responses"><figcaption><p>Output action buttons for copying, rating, and sharing AutoPilot responses</p></figcaption></figure>++***++<details>++<summary>Improvements</summary>++- **Credential selector redesign** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12378) — Completely rebuilt the credential picker for a smoother, faster experience when connecting your accounts.++- **Pinned tool cards** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12346) — Interactive tool cards now stay pinned outside collapsed reasoning, so results are always visible without expanding steps.++- **Workspace file uploads** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12226) — Upload files directly to your workspace and reference them across agents and conversations.++- **Multimodal vision support** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12273) — AutoPilot can now analyze images and PDFs you share in chat, powered by the latest vision models.++- **Per-turn summary stats** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12257) — Each agent turn now shows a work-done summary so you can see exactly what happened at a glance.++- **Text-to-speech voice selection** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12317) — Choose from multiple AI voices when listening to agent responses, with improved quality to avoid robotic-sounding output.++- **Batch undo in agent builder** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12344) — Undo multiple changes at once when editing agents in the visual builder.++</details>++<details>++<summary>Fixes</summary>++- **Session message preservation** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12302) — Title updates no longer overwrite session messages, keeping your full conversation intact.++- **Transcript reliability** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12318) — Refactored transcripts to an atomic full-context model, preventing data loss during complex multi-step runs.++- **File download integrity** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12349) — Workspace file downloads are now buffered to prevent truncation of large files.++- **Node layout handling** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12354) — Improved how the builder handles discriminated unions and node positioning when editing agents.++- **Triggered agent runs** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12298) — Manual run attempts for triggered agents are now handled gracefully instead of failing silently.++- **Password reset flow** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12384) — Supabase error details now pass through correctly during password reset, giving clearer feedback when something goes wrong.++</details>++<details>++<summary>Under the hood</summary>++- **New models added** — Claude Sonnet 4.6, Grok 3, Mistral Large, Medium, Small & Codestral, Perplexity Sonar Reasoning Pro, Google Gemini 3.1 Flash & Pro, Phi-4, and Cohere Command A are now available.++- **File-ref protocol** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12332) — Internal file references now use a consistent protocol, making cross-block file passing more reliable.++- **Langfuse tracing** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12281) — Better observability for agent execution with enhanced trace correlation and feedback loops.++- **Sandbox auto-pause** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12330) — Code execution sandboxes now automatically pause when idle, eliminating unnecessary billing.++- **Claude Code auth** [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12288) — Added subscription authentication support for Claude Code integration in SDK mode.++</details>diff --git a/docs/platform/changelog/may-7-june-10-2026.md b/docs/platform/changelog/may-7-june-10-2026.mdnew file mode 100644index 0000000000..711d9d74e0--- /dev/null+++ b/docs/platform/changelog/may-7-june-10-2026.md@@ -0,0 +1,74 @@+# Smarter Automation, Fresher Design, Open for Business++*May 7 – June 10, 2026*++**Platform versions:** `v0.6.59` · `v0.6.60` · `v0.6.61` · `v0.6.62` · `v0.6.63`++## AutoPilot gets a major upgrade++AutoPilot — your always-on AI co-pilot — just received its biggest set of upgrades yet.++**Native scheduling** lets you run agents on a cron schedule directly from the chat. No setup required — just say when, and AutoPilot handles the rest. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/13202)++**Self-distilled skills registry** means AutoPilot now learns from its own work. After completing complex multi-step procedures, it automatically saves reusable recipes to a skills library — so it gets faster and more capable with every workflow you run together. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/13195)++**Auto-discover MCP integrations** — when no native block exists for a tool or service, AutoPilot now automatically finds and connects the right MCP integration, so you never hit a dead end mid-workflow. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/13117)++<figure><img src="../.gitbook/assets/autopilot-upgrades-hero.png" alt="AutoPilot chat showing scheduling, skills registry, and MCP auto-discovery"><figcaption><p>Native scheduling, a self-distilling skills registry, and MCP auto-discovery in AutoPilot</p></figcaption></figure>++## A completely new first impression++The login and signup experience has been rebuilt. An animated split-panel layout, aurora lighting, and a live integrations marquee welcome you the moment you arrive — and set the tone for everything behind it. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/13169)++<figure><img src="../.gitbook/assets/login-signup-hero.png" alt="New animated login screen with aurora background and integrations marquee"><figcaption><p>The redesigned login and signup experience</p></figcaption></figure>++## Unlock everything — plans are live++Subscriptions and payments are officially live. Choose the plan that fits your team, upgrade instantly, and unlock the full platform. No more waitlists or manual provisioning. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/13096)++<figure><img src="../.gitbook/assets/subscription-pricing-hero.png" alt="Plan selection screen showing available subscription tiers"><figcaption><p>Pick the plan that's right for you — billing is now fully live</p></figcaption></figure>++## Settings rebuilt & a smarter profile menu++Settings has been rebuilt with a cleaner layout, faster navigation, and a dedicated integrations tab for managing all your third-party connections in one place. The profile dropdown now surfaces quick actions — feedback, billing, and sign-out — without taking you away from your current page. [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/12976) [↗](https://github.com/Significant-Gravitas/AutoGPT/pull/13138)++<figure><img src="../.gitbook/assets/settings-profile-hero.png" alt="New profile dropdown menu with quick-access actions"><figcaption><p>Quick actions from your profile menu</p></figcaption></figure>++<figure><img src="../.gitbook/assets/settings-integrations-hero.png" alt="Rebuilt settings page showing the third-party integrations tab"><figcaption><p>Third-party integrations are now in one dedicated tab</p></figcaption></figure>++<details>++<summary>✨ Improvements</summary>++- **Trigger On Anything** — more flexible workflow triggers let agents respond to a wider range of conditions and events. ([#12740](https://github.com/Significant-Gravitas/AutoGPT/pull/12740))+- **Export Chat as Markdown** — download any AutoPilot conversation as a `.md` file. ([#13070](https://github.com/Significant-Gravitas/AutoGPT/pull/13070))+- **Auto-open artifact panel** — the artifact panel now opens automatically when an agent produces an artifact. ([#12997](https://github.com/Significant-Gravitas/AutoGPT/pull/12997))+- **Slack block** — send and receive Slack messages natively from any agent. ([#13008](https://github.com/Significant-Gravitas/AutoGPT/pull/13008))+- **Cost breakdown in briefing panel** — see exactly what each agent run costs, right in the briefing. ([#13129](https://github.com/Significant-Gravitas/AutoGPT/pull/13129))+- **Faster first response in AutoPilot** — reduced time-to-first-token for AutoPilot conversations. ([#12828](https://github.com/Significant-Gravitas/AutoGPT/pull/12828))+- **Credit top-up prompt** — when you run out of automation credits, you're now prompted to top up directly from the chat. ([#13208](https://github.com/Significant-Gravitas/AutoGPT/pull/13208))+- **AutoPilot shows its plan** — before building a new agent, AutoPilot breaks down your request step-by-step so you can review the approach first. ([#12731](https://github.com/Significant-Gravitas/AutoGPT/pull/12731))+- **Variable inputs in Execute Code block** — pass dynamic variables directly into your custom code blocks from any agent. ([#13300](https://github.com/Significant-Gravitas/AutoGPT/pull/13300))++</details>++<details>++<summary>🎨 UI/UX Improvements</summary>++- **Mobile AutoPilot parity** — full AutoPilot feature set now available on mobile. ([#13232](https://github.com/Significant-Gravitas/AutoGPT/pull/13232))+- **Chat source icons** — see which platform a message came from, shown beside the timestamp. ([#13175](https://github.com/Significant-Gravitas/AutoGPT/pull/13175), [#13303](https://github.com/Significant-Gravitas/AutoGPT/pull/13303))++</details>++<details>++<summary>🐛 Bug Fixes</summary>++- **Profile avatar display** — Fixed profile avatar not displaying correctly in the profile popover. ([#13155](https://github.com/Significant-Gravitas/AutoGPT/pull/13155))+- **Signup redirect flash** — Fixed a flash to the home screen before onboarding completed. ([#13154](https://github.com/Significant-Gravitas/AutoGPT/pull/13154))+- **OAuth error surfacing** — Integration errors now show a readable toast instead of failing silently. ([#13282](https://github.com/Significant-Gravitas/AutoGPT/pull/13282))+- **AutoPilot notification icons** — Push notification icons corrected for desktop and mobile. ([#13231](https://github.com/Significant-Gravitas/AutoGPT/pull/13231), [#13245](https://github.com/Significant-Gravitas/AutoGPT/pull/13245))+- **Scheduled filter alignment** — Fixed alignment of the scheduled filter in the agent library. ([#13235](https://github.com/Significant-Gravitas/AutoGPT/pull/13235))++</details>diff --git a/docs/platform/credits-and-billing.md b/docs/platform/credits-and-billing.mdnew file mode 100644index 0000000000..1abc0ecc59--- /dev/null+++ b/docs/platform/credits-and-billing.md@@ -0,0 +1,51 @@+# Credits & Billing++## Overview++The AutoGPT Platform uses automation credits for metered agent execution. This guide explains how usage is priced, how to review costs, and how to manage your balance.++{% hint style="info" %}+Plans and pricing can change. See the [pricing page](https://agpt.co/pricing) for current details.+{% endhint %}++## How Credits Work++Credits are charged when blocks run. Depending on the block, the final charge may be fixed or based on actual usage, such as tokens, provider cost, elapsed time, data size, or number of items. For usage-based blocks, the platform may estimate a charge before execution and reconcile it against actual usage afterward.++### Block Pricing++Block pricing varies by block, configuration, and usage. Review the estimate shown in the platform before running an agent; the final charge for usage-based blocks may differ from the estimate.++Your total cost depends on your plan and automation-credit usage. See the [pricing page](https://agpt.co/pricing) for current subscription and included-credit details.++## Checking Your Balance++Your balance is available from the automation-credits wallet in the platform navigation and from [Billing settings](https://platform.agpt.co/settings/billing?tab=automation-credits).++## Viewing Task Costs++To review the cost of a specific agent run:++1. Go to your [Agent Library](agent-library.md)+2. Open the agent+3. Click on a completed task in the left-hand pane+4. The task detail header displays **Cost** in dollars.++{% hint style="info" %}+Use the **Automation Credits** section in [Billing settings](https://platform.agpt.co/settings/billing?tab=automation-credits) for account-level usage and transaction history. Individual task costs are also available within each agent.+{% endhint %}++## Running Out of Credits++If your automation-credit balance is exhausted, paid blocks cannot start until credits are added. Scheduled tasks may fail for insufficient balance. Final reconciliation for a usage-based block that already ran can leave the balance below zero.++You can add credits manually or configure auto-refill from Billing settings.++## Adding Credits++1. Open **Settings** from your profile menu.+2. Select **Billing**.+3. Open the **Automation Credits** tab.+4. Select **Add credits** and follow the checkout prompts.++You can also go directly to [Billing settings](https://platform.agpt.co/settings/billing?tab=automation-credits).diff --git a/docs/platform/data-flow-and-execution.md b/docs/platform/data-flow-and-execution.mdnew file mode 100644index 0000000000..8c83321456--- /dev/null+++ b/docs/platform/data-flow-and-execution.md@@ -0,0 +1,84 @@+# Data Flow & Execution++## Overview++Understanding how agents execute is key to building effective workflows. This guide explains how data flows through an agent, what determines execution order, and how to work with lists and errors.++## Execution Order++Agent execution follows the graph's starting nodes, data connections, configured values, and input validation.++### How It Works++1. Execution starts from every starting node: an Agent Input block or any executable block with no inbound links.+2. A downstream block is queued when its required inputs validate after upstream outputs and configured values are applied.+3. Execution continues until no more downstream blocks can be queued; conditional branches and skipped nodes mean not every block necessarily runs.+4. Output blocks collect any results that reach them.++### Required Inputs++A block will only execute when:++- All **connected input pins** have received data from their upstream blocks+- All **required input pins** have values — either from a connection or from a hardcoded value set directly on the block++This means you can have blocks that don't depend on each other execute in any order, while blocks that depend on the output of another block will always wait.++## Working with Pins++### Pin Types++Input and output pins are typed. Common types include:++- **Text**: String values+- **Number**: Numeric values+- **File**: File uploads or downloads+- **List**: Arrays of items+- **Boolean**: True/false values+- **Object**: Structured data++Connections can only be made between compatible pin types.++### Data Flow Visualisation++When an agent is running, you can see data moving through the workflow in real time. Data flow is represented by a **coloured bead** that slides along each connection line from the output pin to the input pin, giving you a clear visual of what's happening.++## Working with Lists++Blocks can handle list data in flexible ways:++- **Outputting lists**: Some blocks produce a list of items as their output. You can choose to receive the full list as a single output or receive individual items one at a time.+- **Iterating over lists**: You can send a list into a block that iterates through its contents, yielding each item one by one. This is useful for processing each item in a list independently.++This makes it straightforward to build agents that process batches of data — for example, fetching a list of URLs and then processing each one through an AI block.++## Error Handling++When a block fails during execution, it does **not** automatically stop the entire agent. Instead:++1. The failed block produces data on its **error pin**+2. What happens next depends on how you've wired the agent++### Handling Errors Gracefully++You have full control over error handling through the block connections:++- **Surface the error**: Connect the error pin to an output block to return the error as part of the agent's result. This is useful for debugging or when you want users to see what went wrong.+- **Handle and continue**: Connect the error pin to other blocks that provide fallback behaviour. For example, retry with different settings, use a default value, or route to an alternative workflow path.+- **Ignore the error**: If the error pin is not connected, the error data is simply not propagated. Downstream blocks that depend on the failed block's normal output pins will not execute (since their inputs won't be satisfied).++{% hint style="info" %}+Building robust agents means thinking about what happens when things go wrong. Consider connecting error pins to output blocks during development so you can see any issues, then add proper error handling once your agent is working.+{% endhint %}++## Execution Summary++| Concept | How It Works |+|---------|-------------|+| **Execution order** | Determined by starting nodes, data connections, configured values, and input validation |+| **Starting point** | Agent Input blocks and executable blocks with no inbound links |+| **Ending point** | Output blocks collect final results |+| **Parallel execution** | Blocks with no dependencies on each other can execute in any order |+| **Error handling** | Failed blocks yield data on their error pin — you decide what to do with it |+| **Lists** | Can be processed as a whole or iterated item by item |+| **Visual feedback** | Coloured beads slide along connection lines during execution |diff --git a/docs/platform/getting-started-cloud.md b/docs/platform/getting-started-cloud.mdnew file mode 100644index 0000000000..0b48ad249a--- /dev/null+++ b/docs/platform/getting-started-cloud.md@@ -0,0 +1,79 @@+# Getting Started with AutoGPT (Cloud)++## Introduction++This guide will get you up and running on the hosted AutoGPT Platform at [platform.agpt.co](https://platform.agpt.co). No local installation or Docker setup is required — just sign up and start building.++{% hint style="info" %}+Looking to self-host instead? See the [Self-Hosting Guide](getting-started.md).+{% endhint %}++## Creating Your Account++1. Navigate to [platform.agpt.co](https://platform.agpt.co)+2. Click **Sign Up** and create your account+3. Once signed in, you'll land on the **AutoPilot** home screen++That's it — you're ready to go. Available credits and managed AI providers depend on your plan and account configuration. If a block requires credentials that are not included, the platform will prompt you to connect your own. See the [pricing page](https://agpt.co/pricing) for current plan details.++## Platform Navigation++The AutoGPT Platform has four main areas, accessible from the main navigation:++| Nav Button | URL | Description |+|------------|-----|-------------|+| **Home** | [platform.agpt.co](https://platform.agpt.co) | AutoPilot — your AI assistant for the platform |+| **Build** | [platform.agpt.co/build](https://platform.agpt.co/build) | Agent Builder — visual editor for creating agents |+| **Agents** | [platform.agpt.co/library](https://platform.agpt.co/library) | Your Agent Library — all your saved agents |+| **Marketplace** | [platform.agpt.co/marketplace](https://platform.agpt.co/marketplace) | Community marketplace for discovering agents |++Use the automation-credits wallet or **Billing** settings to review your balance. Account settings and integrations are available from **Settings**.++## What to Do First++Here are three great ways to get started:++### Option 1: Chat with AutoPilot++Click **Home** in the nav bar to open AutoPilot. You can ask it to perform supported actions such as browsing the marketplace, running agents, building agents, generating images, and conducting research. It's the fastest way to experience the platform.++### Option 2: Add an Agent from the Marketplace++1. Click **Marketplace** in the nav bar+2. Browse or search for an agent that interests you+3. Click on an agent to view its details+4. Click **Add to Library**+5. Navigate to **Agents** to find it in your library+6. Click on the agent and press **New agent task** to run it++### Option 3: Build Your Own Agent++1. Click **Build** in the nav bar to open the Agent Builder+2. Open the Blocks menu on the left-hand side+3. Add an **Input Block**, an **AI Text Generator Block**, and an **Output Block**+4. Connect them together by dragging between their pins+5. Press **Ctrl+S** (Windows/Linux) or **Cmd+S** (macOS), or click the save button to save your agent+6. Navigate to **Agents** to find and run it++For a detailed walkthrough, see [Creating a Basic Agent](create-basic-agent.md).++## Key Concepts++Before diving deeper, here are the core concepts you'll encounter:++- **Agent**: An automated workflow you design to perform specific tasks. Agents are made up of connected blocks.+- **Block**: A single action within an agent — such as generating text with AI, sending an email, or looking up data. The available block catalog depends on the platform deployment.+- **Task**: A single execution of an agent. When you run an agent with a set of inputs, that creates a task. You can view the task's inputs, outputs, and reported cost.+- **AutoPilot**: Your AI assistant that can perform supported platform actions through natural conversation.+- **Marketplace**: A public library of community-built agents you can add to your own library.+- **Credits**: The currency used for metered block execution. Pricing varies by block and usage; review your balance from the automation-credits wallet or Billing settings.++## Next Steps++| Guide | Description |+|-------|-------------|+| [AutoPilot](autopilot.md) | Learn what AutoPilot can do for you |+| [Agent Builder Guide](agent-builder-guide.md) | Master the visual agent builder |+| [Agent Library](agent-library.md) | Manage your agents, tasks, and schedules |+| [Marketplace](marketplace.md) | Discover and share agents |+| [Credits & Billing](credits-and-billing.md) | Understand the credit system |diff --git a/docs/platform/integrations-and-credentials.md b/docs/platform/integrations-and-credentials.mdnew file mode 100644index 0000000000..5011047b53--- /dev/null+++ b/docs/platform/integrations-and-credentials.md@@ -0,0 +1,59 @@+# Integrations & Credentials++## Overview++Many blocks on the AutoGPT Platform integrate with external services like Google, GitHub, Linear, Twitter, and more. These integrations require credentials — such as OAuth connections, API keys, or username/password pairs — to access your accounts on those services.++This guide explains how credentials work on the platform, how to add them, and how to manage them.++## How Credentials Work++### Platform-Provided Credentials++On the cloud-hosted platform at [platform.agpt.co](https://platform.agpt.co), some plans and account configurations include managed AI providers. If a block requires credentials that are not included, the platform will prompt you to connect your own. See the [pricing page](https://agpt.co/pricing) for current plan details.++### User-Provided Credentials++For services tied to your personal accounts, connect your own credentials. Credentials can be reused across agents, but you choose which compatible credential an agent or task uses. Managed credentials may be selected automatically when available.++## Adding Credentials++You can connect credentials centrally from **Settings → Integrations → Connect Service**, or in context when a builder block or task asks for one.++### When Building an Agent++If a block needs credentials, select an existing compatible credential or connect a new one from the block.++### When Running an Agent++Credential fields show the credentials that task will use. Select an existing compatible credential or connect a new one.++### Credential Types++Depending on the service, you'll be prompted to authenticate in one of three ways:++| Type | Description | Example Services |+|------|-------------|------------------|+| **OAuth** | Click to authorise via the service's login page | Google, GitHub, Twitter |+| **API Key** | Paste your API key from the service's dashboard | Linear, OpenAI |+| **Username & Password** | Enter your account credentials | Varies by service |++{% hint style="info" %}+Credentials are reusable, but each block or task retains its selected credential reference.+{% endhint %}++## Managing Credentials++1. Open **Settings**.+2. Select **Integrations**.+3. Use **Connect Service** to add a credential, or manage/remove credentials already listed.++**URL:** [platform.agpt.co/settings/integrations](https://platform.agpt.co/settings/integrations)++{% hint style="warning" %}+Removing a credential can break agents, workflows, or active webhooks that reference it. Review the dependency warning before confirming removal.+{% endhint %}++## Self-Hosted Credentials++When self-hosting, configure deployment-level provider keys and OAuth application credentials in `autogpt_platform/backend/.env`, then connect end-user accounts from **Settings → Integrations** as needed. See the [Self-Hosting Guide](getting-started.md) for details.diff --git a/docs/platform/marketplace.md b/docs/platform/marketplace.mdnew file mode 100644index 0000000000..c9b64e9edc--- /dev/null+++ b/docs/platform/marketplace.md@@ -0,0 +1,77 @@+# Marketplace++## Overview++The AutoGPT Marketplace is a public library of agents created by the community and by the AutoGPT team. You can discover agents for a wide range of use cases, add them to your library with one click, and even publish your own agents for others to use.++**URL:** [platform.agpt.co/marketplace](https://platform.agpt.co/marketplace)++**Access:** Click **Marketplace** in the navigation bar.++## Browsing the Marketplace++The marketplace allows you to:++- **Search** for agents by name or keyword+- **Browse by category** to explore different use cases+- **View agent details** by clicking on any agent++### Agent Detail Page++Each agent in the marketplace has a dedicated page that includes:++- **Title and description** of what the agent does+- **Creator information** — who built the agent and a link to their other agents+- **Video** (when available) — a demonstration of the agent in action+- **Output showcase** (when available) — examples of the agent's results+- **Instructions** — guidance on how to run the agent and what to expect++## Adding an Agent to Your Library++When you find an agent you want to use:++1. Click on the agent to open its marketplace page+2. Click the **Add to Library** button++The agent appears in your [Agent Library](agent-library.md), where you can run or schedule it. Marketplace agents open read-only; duplicate one before editing.++{% hint style="info" %}+If you already have the agent in your library, the button changes to **See Runs**, which takes you directly to that agent in your library.+{% endhint %}++### Download for Self-Hosting++Marketplace detail pages also provide **Download here** under “Want to use this agent locally?” Download the agent JSON and import it into your local instance. See [Download & Import an Agent](download-agent-from-marketplace-local.md) for details.++## Publishing an Agent++You can publish your own agents to the marketplace for the community to discover and use.++### How to Publish++1. Open the agent in the Builder and select **Publish to Marketplace**, or open **Settings → Creator Dashboard** and select **Publish Agent**+2. Choose the agent and version you want to publish if prompted+3. Fill out the publishing form:++| Field | Description |+|-------|-------------|+| **Title** | The name of your agent as it will appear in the marketplace |+| **Subheader** | A short tagline for your agent |+| **Slug** | A URL-friendly identifier (e.g., `resume-rewriter`) |+| **Thumbnail Images** | Upload images — the first image becomes the marketplace thumbnail |+| **YouTube Video Link** | Optional — a video demonstrating your agent |+| **Output demo** | Optional — a URL showing example output the agent produces |+| **Category** | Select the most relevant category for your agent |+| **Description** | A detailed explanation of what your agent does |+| **Instructions** | Explain to users how to run this agent and what to expect |+| **Recommended Schedule** | Suggest when users should run this agent for best results |++4. Click **Submit for review**++### Review Process++After submission, a member of the AutoGPT team will review your agent against curation standards. If approved, your agent will be published to the marketplace and visible to all users.++## Editing Marketplace Agents++An agent added from the marketplace is read-only. Open it in the builder and click **Duplicate** to create an editable fork in your library. Changes to that fork do not modify the original marketplace listing.diff --git a/docs/platform/scheduling-and-triggers.md b/docs/platform/scheduling-and-triggers.mdnew file mode 100644index 0000000000..59b6a71570--- /dev/null+++ b/docs/platform/scheduling-and-triggers.md@@ -0,0 +1,97 @@+# Scheduling & Triggers++## Overview++AutoGPT agents can be run on demand, on a recurring schedule, or automatically in response to external events via webhooks. This guide covers both scheduling and trigger-based execution.++## Scheduling an Agent++Scheduling lets you run an agent automatically on a recurring basis with pre-configured inputs.++### Setting Up a Schedule++1. Go to your [Agent Library](agent-library.md) and open the agent you want to schedule+2. Click **New agent task** (the same button used for manual runs)+3. Fill in all the input fields with the values you want the agent to use+4. At the bottom of the input form, you'll see two buttons: **Start Task** and **Schedule Task**+5. Click **Schedule Task**++### Configuring the Schedule++The schedule configuration screen allows you to set:++| Setting | Description |+|---------|-------------|+| **Schedule Name** | A descriptive name for this schedule |+| **Repeats** | Frequency — e.g., Weekly |+| **Repeats On** | Select specific days (individual days, weekdays, weekends, or select all) |+| **At** | The time of day to run (hour and minute) |+| **Timezone** | Schedule runs in your local timezone, displayed on screen |++**Example:** Run "Keyword SEO Expert" every weekday at 9:00 AM in the timezone shown in the schedule form.++### Managing Schedules++After creating a schedule, you can view and manage it on your agent's detail page:++- Open the agent from your library+- Select the **Scheduled** tab on the left-hand side+- The tab shows the count of active schedules (e.g., `Scheduled 1`)++## Triggers (Webhook-Based Execution)++Triggers allow external services or your own code to start an agent automatically by sending data to a webhook URL.++### How Triggers Work++Unlike standard input blocks, **trigger blocks** are a special type of input block. When you add a trigger block to your agent in the builder, the agent's execution model changes — instead of being started manually, it waits for incoming webhook events.++### Setting Up a Trigger++#### Step 1: Add a Trigger Block in the Builder++1. Open the [Agent Builder](agent-builder-guide.md)+2. From the blocks menu, add a **trigger block** to your agent+3. Connect it to the rest of your workflow like any other input block+4. Save your agent++#### Step 2: Configure the Trigger in Your Library++1. Go to your [Agent Library](agent-library.md) and open the agent+2. Click **New agent task**+3. Enter the trigger name and description and complete any required inputs or credentials+4. Click **Set up Trigger**++#### Step 3: Copy the Webhook URL++Once the trigger is created, you'll see a status panel:++> **Trigger Status**+>+> Status: **Active**+>+> This trigger is ready to be used. Use the Webhook URL below to set up the trigger connection with the service of your choosing.+>+> **Webhook URL:** `https://backend.agpt.co/api/integrations/generic_webhook/webhooks/<webhook-id>/ingress`++Copy this webhook URL and provide it to the external platform or code that will be sending events to trigger your agent.++{% hint style="info" %}+Trigger-based agents cannot be started manually. Configure them through **New agent task** and **Set up Trigger**, then send data to the webhook URL to execute them.+{% endhint %}++### Example Use Cases++- **GitHub webhook**: Trigger an agent whenever a pull request is opened+- **Payment processor**: Run an agent when a new payment is received+- **Form submission**: Process data when a user submits a form on your website+- **Custom integration**: Send data from any service that supports webhooks++## Schedule vs. Trigger++| | Schedule | Trigger |+|---|----------|---------|+| **How it starts** | Automatically at configured times | When an external event sends data to the webhook URL |+| **Input source** | Pre-configured when the schedule is created | Provided by the incoming webhook payload |+| **Use case** | Recurring tasks with fixed inputs (daily reports, weekly summaries) | Event-driven tasks (new PR opened, form submitted, payment received) |+| **Setup** | Through the **New agent task** → **Schedule Task** flow | Through trigger blocks in the builder, then **New agent task** → **Set up Trigger** in the library |diff --git a/docs/platform/sharing-and-exporting.md b/docs/platform/sharing-and-exporting.mdnew file mode 100644index 0000000000..311f7ae676--- /dev/null+++ b/docs/platform/sharing-and-exporting.md@@ -0,0 +1,53 @@+# Sharing & Exporting Agents++## Overview++There are several ways to share agents and their outputs with others on the AutoGPT Platform. This guide covers all the available options.++## Sharing Options++### Share Task Output via URL++A completed task remains private until you explicitly enable sharing:++1. Open the agent and select the completed task.+2. Click **Share results**.+3. Review the public-access warning and click **Enable Sharing**.+4. Copy the generated **Share URL**.++Anyone with that URL can view the run's outputs. Use **Stop Sharing** in the same dialog to revoke the link.++{% hint style="warning" %}+A share URL is publicly accessible to anyone who has it. It does not publish the task inputs, but outputs may contain sensitive data.+{% endhint %}++### Publish to the Marketplace++The most visible way to share an agent is to publish it to the [Marketplace](marketplace.md). Published agents are discoverable by all platform users and go through a review process by the AutoGPT team.++See [Publishing an Agent](marketplace.md#publishing-an-agent) for the full guide.++### Export as a File++For sharing agents privately — without publishing to the marketplace — you can export an agent as a file:++1. Go to your [Agent Library](agent-library.md) and open the agent+2. Click the **three dots** (⋯) on the far right+3. Select **Export Agent to File**+4. The agent file will download to your computer++You can then send this file to anyone via email, messaging, or any other method.++### Import a Shared File++To import an agent file someone has shared with you:++1. Go to your [Agent Library](agent-library.md)+2. Click **Import**+3. Select the **AutoGPT agent** tab+4. Upload the exported `.json` file+5. The agent will be added to your library++## Teams & Collaboration++Organization and team workspaces are available only when enabled for your account or deployment. Use their built-in access controls where available. Export/import remains the portable way to transfer an agent file between separate accounts or deployments.diff --git a/docs/platform/templates.md b/docs/platform/templates.mdnew file mode 100644index 0000000000..220d02f10c--- /dev/null+++ b/docs/platform/templates.md@@ -0,0 +1,44 @@+# Templates++## Overview++Templates save a completed task's inputs and selected credential references so you can start another task with the same configuration.++## Creating a Template++Templates are created from previously completed tasks:++1. Go to your [Agent Library](agent-library.md) and open the agent+2. Find a completed task in the left-hand pane whose inputs you want to reuse+3. Click the **three dots** (⋯) on the task+4. Select **Save as Template**+5. Give the template a **name** and **description**+6. Click **Save**++The template stores the task's input values, selected credential references, graph ID, and graph version. It does not copy credential secrets.++## Using a Template++To run an agent using a saved template:++1. Open the agent from your library+2. Switch to the **Templates** tab on the left-hand side+3. Click the template you want to use+4. Review or edit its saved inputs and credential selections+5. Select **Start task from template**++## Managing Templates++Templates are listed under the **Templates** tab on your agent's detail page. The tab shows the count of available templates (e.g., `Templates 3`).++## When to Use Templates++Templates are particularly useful for:++- **Recurring tasks**: When you run an agent regularly with the same inputs (e.g., a daily SEO report for the same keyword)+- **Standard configurations**: When you've found input settings that work well and want to reuse them+- **Quick re-runs**: When you want to repeat a successful task without re-entering all the inputs++{% hint style="info" %}+A template is pinned to the agent graph version from which it was created. Later agent edits do not automatically update the template to a newer graph version.+{% endhint %}diff --git a/docs/platform/what-is-autogpt-platform.md b/docs/platform/what-is-autogpt-platform.mdindex 2daed2d9c2..cf32e12d8e 100644--- a/docs/platform/what-is-autogpt-platform.md+++ b/docs/platform/what-is-autogpt-platform.md@@ -78,5 +78,5 @@ This strategy allows us to share previously closed-source components, fostering## Ready to Get Started?-* Read the [Getting Started docs](getting-started.md) to self-host.-* [Join the waitlist](https://agpt.co/waitlist) for the cloud-hosted beta.+* **Cloud:** Read the [Getting Started (Cloud)](getting-started-cloud.md) guide to start using the hosted platform immediately.+* **Self-Host:** Read the [Self-Hosting Guide](getting-started.md) to run the platform on your own infrastructure.