#3434th of 52 in Agent platforms
trueforge
Agent runtime with chat UI, HTTP API and TypeScript SDK
- Stars
- 6.4k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
0 on 25 Jul 20266,415 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
TrueForge runs the agent loop server-side: model calls, remote MCP tools, git-backed SKILL.md skills, sandboxed code execution, tool approvals, context compaction and session state. It is used through a bundled chat UI, an HTTP API with a TypeScript SDK, or an embeddable UI package. Local mode runs as one Node process with SQLite; hosted mode uses Postgres and Redis.
Who it is for: Teams building and hosting tool-using agents with a ready UI and API
Strengths
- Two run modes: single process with SQLite, or Postgres + Redis via Compose, Helm or Railway
- Works with OpenAI, Anthropic, Gemini or any OpenAI-compatible endpoint
- Remote MCP servers supported with header auth or OAuth, including in-chat authorization
- Includes subagents, deferred tool loading, Code Mode, large-result offloading and compaction
Weaknesses
- Only Daytona is supported as a sandbox provider today; others are planned
- Local mode has no login by default and is not meant for exposure beyond localhost
- Hosted mode needs Postgres and Redis; OIDC login is optional and configured separately
- Benchmark claims against Claude Managed Agents and deepagents are the vendor's own
What it needs
- no GPU
- Docker + Compose
- Needs Node.js >= 22.14, SQLite (local mode), Postgres (hosted mode), Redis (hosted mode), Daytona (sandbox)
- Models: OpenAI, Anthropic, Google Gemini, OpenAI-compatible endpoints
Quick answers
Is trueforge open source?
Yes. Its code is on GitHub under the MIT license.
Can you run trueforge with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does trueforge need a GPU?
No, it runs without one.
Also in Agent platforms
See all 52| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 94 out of 100 |
| 2 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 93 out of 100 |
| 3 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 93 out of 100 |
| #4 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |
| #5 | open-designDesign workspace that drives your coding agent to build prototypes, decks and video | 92 out of 100 |