{"slug": "trueforge-the-open-source-agent-harness", "title": "TrueForge – The open-source agent harness", "summary": "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.", "body_md": "The open-source agent harness - the runtime layer that turns an LLM into a working agent\n\nTrueForge 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**.\n\nBuilding 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:\n\n**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`\n\ninstruction 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`\n\n, or embed`@truefoundry/trueforge-ui`\n\n.\n\nIt scales down and up: **local mode** (one process, SQLite) or **hosted mode** (Postgres + Redis, Docker Compose or Helm).\n\nRun TrueForge (local, Docker Compose, or Kubernetes), connect a model and tools, and build your first reusable agent in the [Quickstart](https://trueforge.dev/quickstart).\n\nTo work on TrueForge from this repository, see [CONTRIBUTING.md](/truefoundry/trueforge/blob/main/CONTRIBUTING.md).\n\n| Mode | Best for | Storage | Extra infra | How to run |\n|---|---|---|---|---|\n| Local | Personal use, trying it out | SQLite | None | `npx @truefoundry/trueforge` |\n| Hosted | Teams, multi-replica | Postgres | Postgres + Redis | Docker Compose or Helm |\n\nLocal 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.\n\n| Section | What you'll find |\n|---|---|\n|\n\n[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`\n\n[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:\n\n[Benchmarking](https://trueforge.dev/benchmarking).\n\nWe 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.\n\nTo report a security vulnerability, follow [SECURITY.md](/truefoundry/trueforge/blob/main/SECURITY.md) instead of opening a public issue.\n\n[Community Discord](https://discord.com/invite/fHeGRvakb)- Founder emails:\n[abhishek@truefoundry.com](mailto:abhishek@truefoundry.com)/[anuraag@truefoundry.com](mailto:anuraag@truefoundry.com)\n\nTrueForge is released under the [MIT License](/truefoundry/trueforge/blob/main/LICENSE).", "url": "https://wpnews.pro/news/trueforge-the-open-source-agent-harness", "canonical_source": "https://github.com/truefoundry/trueforge", "published_at": "2026-08-20 18:36:07+00:00", "updated_at": "2026-08-20 18:45:23.784657+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools"], "entities": ["TrueFoundry", "TrueForge", "OpenAI", "Anthropic", "Google Gemini", "Daytona", "Claude Managed Agents", "deepagents"], "alternates": {"html": "https://wpnews.pro/news/trueforge-the-open-source-agent-harness", "markdown": "https://wpnews.pro/news/trueforge-the-open-source-agent-harness.md", "text": "https://wpnews.pro/news/trueforge-the-open-source-agent-harness.txt", "jsonld": "https://wpnews.pro/news/trueforge-the-open-source-agent-harness.jsonld"}}