Skip to content

Self-improving AI Employees for everyone

docs(readme): refresh against the v0.1.0 registry and feature set

trohitgadbb83104e74
diff --git a/README.md b/README.md
index 451a7070..7ac23b71 100644
--- a/README.md
+++ b/README.md
@@ -9,7 +9,7 @@
**Your own AI workforce, running on your own machine.**
-OpenCompany is an open-source, self-hosted canvas for AI agent workflows — think n8n, built agent-first. Drag, drop, and connect AI agents to your email, calendar, messages, browser, phone, and 30 other services, with 132 nodes across 27 categories to build from. No code required. No subscription. No usage limits. Bring your own API keys, or run models locally with Ollama / LM Studio for free.
+OpenCompany is an open-source, self-hosted canvas for AI agent workflows — think n8n, built agent-first. Drag, drop, and connect AI agents to your email, calendar, messages, browser, phone, and 30 other services, with 146 nodes across 31 categories to build from. No code required. No subscription. No usage limits. Bring your own API keys, or run models locally with Ollama / LM Studio for free.
**[Read the docs →](https://docs.opencompany.sh)**
@@ -67,14 +67,16 @@ Three example workflows load automatically on first launch. Open them on the can
## What You Can Build
-- **Personal AI assistants that remember.** A chat assistant that knows your calendar, reads your inbox, and follows up on tasks. Conversations are saved as readable markdown you can edit; long-term memory uses vector search so years of context stay accessible.
+- **Personal AI assistants that remember.** A chat assistant that knows your calendar, reads your inbox, and follows up on tasks. Connect a Context node and the conversation durably persists across every trigger firing — inspect the agent's live context in real time from the canvas (formatted transcript or raw JSON). A durable Memory tool holds the facts, preferences, and decisions the agent explicitly remembers, with vector search for long-term recall.
- **Durable agent teams.** Hire an **AI Employee** or Orchestrator as a team lead, connect specialist agents through `input-teammates`, and the lead assigns bounded work through its built-in Task Manager. Tasks are durably queued, run up to three descendants in parallel, require lead acceptance, and remain visible in the read-only Team Monitor.
- **Automations that run themselves.** Recurring jobs ("every weekday at 9 AM, summarize my unread emails"), event-driven replies ("when a customer texts on WhatsApp, draft a response"), and multi-step background pipelines. Any workflow can also expose a live `/webhook/{path}` HTTP endpoint that fires on GET, POST, PUT, DELETE, or PATCH.
-- **Email, calendar, and document workflows.** Send and search Gmail, manage Calendar, Drive, Sheets, Tasks, and Contacts. Read any inbox over IMAP (Gmail, Outlook, Yahoo, iCloud, ProtonMail, Fastmail, or custom servers) — including a polling trigger that fires a workflow on every new message.
-- **Messaging bots.** Send and receive on **WhatsApp** (groups, contacts, newsletter channels), **Telegram** (bots with owner detection), and **Twitter/X** (post, reply, search). A unified social node normalizes incoming messages into one format so the same workflow handles them all.
+- **Email, calendar, and document workflows.** Send and search Gmail, manage Calendar, Drive, Sheets, Tasks, and Contacts; **Microsoft 365** mail and calendar over the Graph API. Read any inbox over IMAP (Gmail, Outlook, Yahoo, iCloud, ProtonMail, Fastmail, or custom servers) — including a polling trigger that fires a workflow on every new message.
+- **Messaging bots.** Send and receive on **WhatsApp** (personal — groups, contacts, newsletter channels), **WhatsApp Business** (official Meta Cloud API: templates, media, interactive messages, signed webhooks), **Telegram** (bots with owner detection), **Discord** (bot with gateway message triggers, slash commands, and OAuth2), and **Twitter/X** (post, reply, search). A unified social node normalizes incoming messages into one format so the same workflow handles them all.
+- **Voice and language.** Provider-abstracted text-to-speech and speech-to-text (OpenAI, ElevenLabs, Deepgram, Groq, Sarvam) with reference-based audio that flows between nodes, plus translate / transliterate / detect-language nodes (DeepL, Sarvam, or any connected LLM).
- **Phone control from a workflow.** Pair your Android phone via QR code and control it from any agent: battery and network status, app launching, WiFi / Bluetooth / airplane toggles, camera, sensors, media playback — 16 device services.
- **Web automation and research.** An interactive browser with accessibility-tree navigation (click, type, screenshot); an alpha harness that drives your *real* Chrome over CDP; scraping with Crawlee and Apify actors (Instagram, TikTok, LinkedIn, Facebook, YouTube, Google Search); search via DuckDuckGo (free), Brave, Serper, and Perplexity; residential proxies with geo-targeting and rotation.
-- **Code, deploys, and pull requests.** Run Python / JavaScript / TypeScript in per-workflow sandboxed workspaces, keep dev servers alive with the Process Manager node (output streams to the Terminal tab), open and merge PRs with the **GitHub** node, and ship with the **Vercel** node — both can authenticate through their own CLIs, no token pasting required.
+- **Code, deploys, and pull requests.** Run Python / JavaScript / TypeScript in per-workflow sandboxed workspaces, keep dev servers alive with the Process Manager node (output streams to the Terminal tab), open and merge PRs with the **GitHub** node, ship with the **Vercel** node, manage DNS and analytics with **Cloudflare**, and drive Compute Engine / Cloud Run / Storage with the **Google Cloud** node — all four authenticate through their own CLIs, no token pasting required. A **Gallery** node gives every workflow a visual file explorer with previews and drag-to-parameter assignment.
+- **Local data and vision.** Give agents typed, bounded access to workspace files and operator-approved external folders through the dataSource tool, and vision for every host model via the visionAnalyze delegate — images travel as native content blocks, never pasted base64.
- **Payments.** **Stripe** action node (charges, subscriptions) plus a signed-webhook receiver for reacting to payment events in real time.
- **Your own knowledge base.** RAG out of the box: parse PDFs and HTML, chunk, embed locally or via OpenAI, store in ChromaDB / Qdrant / Pinecone, query from any agent.
@@ -128,11 +130,11 @@ The Claude Code agent keeps warm interactive sessions in a pool (same session ac
### Skills you can edit yourself
-Skills are short markdown files that teach an agent how to do something well — when to use which tool, what arguments to pass, common mistakes to avoid. Edit them in the UI; changes apply immediately. 73 ship built in across 18 folders, covering Android control, Google Workspace, social messaging, web research, coding, terminal use (Bash, PowerShell, WSL, Nushell), payments, deployment, and more — and you can drop your own into `.opencompany/skills/`, where they override the built-ins of the same name.
+Skills are short markdown files that teach an agent how to do something well — when to use which tool, what arguments to pass, common mistakes to avoid. Edit them in the UI; changes apply immediately. 77 ship built in across 19 folders, covering Android control, Google Workspace, social messaging, web research, local data and vision, coding, terminal use (Bash, PowerShell, WSL, Nushell), payments, deployment, and more — and you can drop your own into `.opencompany/skills/`, where they override the built-ins of the same name.
-### Memory that scales with your context window
+### Conversations that survive, memory that scales
-Agents connected to a memory node can track normalized token usage and compact long conversations as they approach the model's context limit (80% by default). Compaction is a context-pressure control, not an agent termination rule: the shared native LLM layer asks the selected model for a five-section summary — Task Overview, Current State, Important Discoveries, Next Steps, Context to Preserve — and continues from that summary. Provider-reported usage is aggregated across an agent loop; session token and cost metrics are persisted on the memory-connected in-process path, while durable Temporal runs return their aggregate usage in the execution result.
+Connect a **Context** node and an agent's conversation is durably stored per workflow generation — every trigger firing (a chat message, a completed delegated task) continues the same conversation, and the panel shows the live transcript in real time. When token usage approaches the model's context limit (80% by default), the agent compacts: the shared native LLM layer asks the selected model for a five-section summary — Task Overview, Current State, Important Discoveries, Next Steps, Context to Preserve — and continues from it, with the system prompt untouched and the summary carried across firings. Provider-reported usage is aggregated across the loop; session token and cost metrics are persisted on the memory-connected in-process path, while durable Temporal runs return their aggregate usage in the execution result.
### Cost tracking, built in