Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file removed docs/images/agent-harness-definition.png
Binary file not shown.
Binary file added docs/images/trueforge-overview.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
6 changes: 3 additions & 3 deletions docs/introduction.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,10 @@ description: 'TrueForge is an open-source agent harness — the runtime layer th

An agent harness is the runtime layer around an LLM that turns it into a reliable, long-running agent. Instead of only generating text, the harness runs the full execution loop — planning, tool routing and execution, context management for long tasks, security boundaries like sandboxing and human-in-the-loop approvals, and session state that survives reconnects and restarts.

<Frame caption="The harness orchestrates the agent run, connecting the model, tools, sandbox, and approvals to deliver a safe, reliable result">
<Frame caption="TrueForge is the open-source agent harness: plug in any model, skills, and MCP tools, and it handles context engineering, the agent runtime, and how agents run and interact, ready to drop into your app.">
<img
src="/images/agent-harness-definition.png"
alt="Diagram of the agent harness sitting between a user goal and the final response: the harness orchestrates the run, routes between model, tools and MCP servers, sandbox, and approval gates, and records every step"
src="/images/trueforge-overview.png"
alt="TrueForge architecture: model providers (OpenAI, Anthropic, Gemini, and more), skills, and tools (Slack, Jira, Notion, Postgres, GitHub, any MCP server) feed into the TrueForge open-source agent harness, which provides context engineering, agent runtime, and run-and-interact capabilities, connected to your AI application"
/>
</Frame>

Expand Down
Loading