GitHub radar
Open Source Agent Runtime by TrueFoundry
TrueForge is an open source agent wrapper created by TrueFoundry that makes any LLM an agent with isolated code execution, MCP integration, and human approval.
TrueForge is an open source agent wrapper created by TrueFoundry that turns any LLM into an agent. It was launched roughly a month ago and currently has 3,400 stars. TrueForge offers model invocation, tool invocation, isolated code execution (via Daytona), session management, and human approval (the ability for agents to ask for human approval prior to taking significant actions while maintaining an audit log of their actions). The framework can be used with OpenAI, Anthropic, Google Gemini, and other OpenAI compatible APIs. TrueForge also offers support for skills (sets of instructions hosted on git) which can be plugged into your agent without changing the runtime and updated dynamically. You can interact with TrueForge via a chat interface, an HTTP API (to integrate it into your projects), or embeddable UIs (to create custom UIs).
Why a vibe-coder should care
Instead of building an agent stack yourself, you can have a production grade agent runtime set up in a matter of minutes. Human approval ensures that your agent won’t take significant actions without your permission. Skills enable you to modify your agent’s behavior dynamically without needing to redeploy.
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Deploy TrueForge from here: https://github.com/truefoundry/trueforge — follow the README, run via `npx @truefoundry/trueforge`, open the local interface and show it to me. Ask me if you need a model API key.
Runs on a regular laptop — Node.js 22.14 and a language model key required (OpenAI, Anthropic, or Google).
Open on GitHub▌ More finds