Skip to main content

​
What is an agent harness?

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.
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

The harness orchestrates the agent run, connecting the model, tools, sandbox, and approvals to deliver a safe, reliable result

​
What is TrueForge?

TrueForge is an open-source agent harness with three parts: a core server that runs the agent loop, an HTTP API (with a TypeScript SDK) to drive it from code, and a chat UI (with a React UI SDK) to drive it from the browser.
truefoundry/trueforge
Loading repository data...
The TrueForge chat UI showing an agent response with the agent-steps panel expanded — reasoning, Exa tool calls, and a subagent

The bundled chat UI — a streaming response with the agent-steps panel expanded to show reasoning, tool calls, and a subagent.

​
Key Components

TrueForge architecture: Chat UI and SDK connect to the TrueForge server HTTP API and agent loop, which talks to SQLite or Postgres and bring-your-own models, MCP servers, and sandbox

Chat UI and SDK connect to the TrueForge server HTTP API and agent loop, which talks to SQLite or Postgres and bring-your-own models, MCP servers, and sandbox

​
TrueForge server

Runs the agent loop. When a user sends a message, the server:
  • Plans the turn, calls the model, and executes tools — streaming every step back
  • Pauses for human approval on sensitive actions
  • Keeps context lean on long tasks with harness capabilities like subagents and compaction
  • Persists sessions, so conversations survive reconnects and restarts
The services the loop talks to — model providers, MCP servers, the sandbox provider — are bring your own: you configure them, TrueForge orchestrates them.
Many harnesses run the agent inside a sandbox. TrueForge treats the sandbox as a tool: one is provisioned only when the agent actually needs to execute code. That’s why one server can run many agents concurrently, and why turns that don’t need code execution are cheaper and faster.

​
HTTP API + TypeScript SDK

Everything the server does is exposed as an API, so anything you see in the UI you can automate:
  • REST + Server-Sent Events, with an OpenAPI spec and interactive docs at /api/v1/docs
  • A TypeScript SDK (@truefoundry/trueforge-core) to create and call agents from your own code
See the SDK Quickstart.

​
Chat UI + UI SDK

A ready-made interface for the agents you create:
  • Browse your agents, chat with them, and manage models, MCP servers, skills, and sandbox settings
  • Bundled with the server and served on the same port — nothing extra to deploy
  • Also published as a customizable UI SDK (@truefoundry/trueforge-ui): theme it to your organization and launch your own Claude Desktop-like interface, backed by your TrueForge server

​
Two ways to run it

The agent features are identical in both modes — only the backend around the server changes. The Quickstart has run instructions for each.
Local (standalone) mode is meant for personal use on your own machine. It is not hardened for production or shared internet access — there is no login by default, and your data lives in a local SQLite file. Please keep it on localhost. We cannot take responsibility for data loss or unauthorized access if local mode is used beyond that. For a team or production deployment, use hosted mode with Postgres, Redis, and login enabled.

​
Start building

Quickstart

Run TrueForge with one command, configure a model provider, and start chatting.

Initial Setup

Configure models, MCP servers, skills, and sandbox — and customize the shipped catalogs.

Create an Agent

Select a model, attach connectors and skills, then save to the Agents Library.

Harness Capabilities

Sandbox-as-tool, subagents, deferred tools, code mode, compaction, and human checkpoints.

Setup Login

Optional OIDC for shared deployments — admin vs user, with a local no-auth default.

SDK

HTTP API and TypeScript SDK to create sessions, stream turns, and automate agents.

Chat UI

Bundled chat experience, or embed @truefoundry/trueforge-ui in your React app.