TrueForge – The open-source agent harness

TrueFoundry has released TrueForge, an open-source agent harness that provides the runtime layer for turning an LLM into a working agent, including model calls, MCP tools, skills, sandboxing, approvals, context management, and session state. The harness offers a chat UI, an HTTP API with a TypeScript SDK, and an embeddable UI SDK, supporting any model provider such as OpenAI, Anthropic, and Google Gemini, and can run in local mode (SQLite) or hosted mode (Postgres + Redis). TrueForge claims to match the accuracy of Claude Managed Agents and deepagents at lower cost, based on benchmarks reproduced in the repository.

The open-source agent harness - the runtime layer that turns an LLM into a working agent TrueForge runs the agent execution loop for you - model calls, MCP tools, skills, sandboxing, approvals, context management, and session state - and exposes it three ways: a chat UI , an HTTP API with a TypeScript SDK , and an embeddable UI SDK . Building an agent is easy. Running one well is not - you need streaming, session persistence, tool servers, sandboxing, approvals, and a UI. TrueForge gives you that out of the box: Initial setup from catalogs - configure models https://trueforge.dev/models , MCP servers https://trueforge.dev/mcp-servers , skills https://trueforge.dev/skills , and a sandbox https://trueforge.dev/sandbox once; agents pick from what you connected. Presets come from shipped YAML catalogs you can customize. Any model provider - OpenAI, Anthropic, Google Gemini, and other catalog providers, or any OpenAI-compatible endpoint. MCP tools - remote MCP servers with header auth or OAuth, including in-chat authorization. Skills - git-backed SKILL.md instruction packs, loaded on demand in the sandbox. Sandbox as a tool - isolated code/file execution Daytona today; more providers planned , provisioned only when needed. Secrets stay in the harness. Human checkpoints - tool approval, ask-user-questions, and Generative UI in chat. Context engineering - subagents, deferred tool loading, Code Mode, large-result offloading, and compaction. Chat UI + SDK - use the bundled UI, automate with @truefoundry/trueforge-sdk , or embed @truefoundry/trueforge-ui . It scales down and up: local mode one process, SQLite or hosted mode Postgres + Redis, Docker Compose or Helm . Run TrueForge local, Docker Compose, or Kubernetes , connect a model and tools, and build your first reusable agent in the Quickstart https://trueforge.dev/quickstart . To work on TrueForge from this repository, see CONTRIBUTING.md /truefoundry/trueforge/blob/main/CONTRIBUTING.md . | Mode | Best for | Storage | Extra infra | How to run | |---|---|---|---|---| | Local | Personal use, trying it out | SQLite | None | npx @truefoundry/trueforge | | Hosted | Teams, multi-replica | Postgres | Postgres + Redis | Docker Compose or Helm | Local mode is for your machine only.It is a convenient way to try TrueForge — not a production or internet-facing setup. There is no login by default, and 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 shared or production deployment, use hosted mode. | Section | What you'll find | |---|---| | Quickstart https://trueforge.dev/quickstart Initial Setup https://trueforge.dev/harness/initial-setup Create an Agent https://trueforge.dev/create-agent/overview Harness Capabilities https://trueforge.dev/key-features/overview Setup Login https://trueforge.dev/authentication/overview Benchmarking https://trueforge.dev/benchmarking SDK https://trueforge.dev/api/overview Chat UI https://trueforge.dev/chat-ui @truefoundry/trueforge-ui API Reference https://trueforge.dev/api-reference We compare TrueForge against Claude Managed Agents and deepagents on the same tasks, tools, and model - same accuracy, lower cost. Reproduce it from benchmark/ /truefoundry/trueforge/blob/main/benchmark . Write-up: Benchmarking https://trueforge.dev/benchmarking . We love contributions - bug reports, features, and docs fixes. See CONTRIBUTING.md /truefoundry/trueforge/blob/main/CONTRIBUTING.md and our Code of Conduct /truefoundry/trueforge/blob/main/CODE OF CONDUCT.md . Fork PRs should change source only; maintainers regenerate the SDK after merge. To report a security vulnerability, follow SECURITY.md /truefoundry/trueforge/blob/main/SECURITY.md instead of opening a public issue. Community Discord https://discord.com/invite/fHeGRvakb - Founder emails: abhishek@truefoundry.com mailto:abhishek@truefoundry.com / anuraag@truefoundry.com mailto:anuraag@truefoundry.com TrueForge is released under the MIT License /truefoundry/trueforge/blob/main/LICENSE .