Skip to content

The open-source agent harness - the runtime layer that turns an LLM into a working agent.

docs(readme): make the sandbox optional in the first-agent example + refresh hero (#269)

shubhamagarwal-create49ee1b9d3cf9
diff --git a/README.md b/README.md
index be726d18f..7a54e6299 100644
--- a/README.md
+++ b/README.md
@@ -106,36 +106,36 @@ See the [chart README](charts/trueforge/README.md) (including [`configs.oidc`](c
## Build your first agent
-Full walkthrough: [Quickstart](https://trueforge.dev/quickstart). The example below builds a **web research briefer** — it searches the web, fans out to parallel subagents, and renders an interactive brief.
+Full walkthrough: [Quickstart](https://trueforge.dev/quickstart). The example below builds a **web research briefer** — it searches the web, fans out to parallel subagents, and renders an interactive brief. To get started, you also need a model key.
1. **Add a model provider** - **Settings → Models**, pick a provider, paste your API key.
![Configure a model provider](./docs/images/quickstart-models.png)
-2. **Connect a web-search tool** - **Settings → Connectors**, connect **Exa** (no auth). Then under **Settings → Skills**, enable **web-artifacts-builder** (skills run in a sandbox).
+2. **Connect a web-search tool** - **Settings → Connectors**, connect **Exa** (no auth needed).
- ![Connect Exa in Settings → Connectors](./docs/images/quickstart-connectors.png)
+ ![Connect Exa](./docs/images/quickstart-connectors.png)
-3. **Add a sandbox** - **Settings → Sandbox providers**, configure **Daytona** (the provider supported today).
-
- ![Daytona sandbox connected](./docs/images/quickstart-sandbox-connected.png)
-
-4. **Compose and run** - pick a model, enable Exa and web-artifacts-builder, then send a prompt:
+3. **Compose and run** - pick a model, enable Exa, and send:
> Research the current state of open-source vector databases. Compare Qdrant, Weaviate, and Milvus on performance, features, and licensing, then write a one-page brief with sources.
- The agent searches with Exa, delegates to parallel subagents, and renders an interactive brief.
+ The agent searches with Exa, delegates to parallel subagents, and renders an interactive brief inline. Generative UI is on by default, so no extra setup is needed.
![The agent's interactive research brief](./docs/images/quickstart-chat-result.png)
-5. **Save as an agent** - click **Save Agent** and name it `web-research-brief`.
+4. **Save as an agent** - click **Save Agent** and name it `web-research-brief`.
![Save agent](./docs/images/quickstart-save-agent.png)
-6. **Find it in the Agent Library** - open **Agents Library**, then **Try** or **Edit**. In hosted mode with login enabled, agents created by anyone are visible to everyone - see [Agent Library](https://trueforge.dev/agent-library).
+5. **Find it in the Agent Library** - open **Agents Library**, then **Try** or **Edit**. In hosted mode with login enabled, agents created by anyone are visible to everyone - see [Agent Library](https://trueforge.dev/agent-library).
![Agents Library](./docs/images/quickstart-agents-library.png)
+> **Optional — run code, files, and richer skills.** To let the agent run code or use skills like **web-artifacts-builder** (which packages the brief into a standalone, shareable HTML page), add a **Daytona** sandbox under **Settings → Sandbox providers**. Skills run in the sandbox.
+>
+> ![Daytona sandbox connected](./docs/images/quickstart-sandbox-connected.png)
+
## Architecture
```mermaid
diff --git a/docs/images/hero.png b/docs/images/hero.png
index 365dc508c..b0c7ba7ba 100644
Binary files a/docs/images/hero.png and b/docs/images/hero.png differ