trueforge

TrueFoundry's open agent harness: the runtime loop — model calls, MCP tools, SKILL.md packs, sandboxing, approvals, compaction — behind a chat UI, HTTP API, TypeScript SDK and embeddable UI.

3,506 241 TypeScript MITupdated yesterday

agents orchestration

View on GitHubDispute this mapping →

Curator's take

Take it when the agent logic is the easy part and you don't want to hand-build streaming, session persistence, tool auth, sandboxing and an approval UI: YAML catalogs configure models, MCP servers, skills and a sandbox once, then agents pick from what you connected. Context engineering is first-class — subagents, deferred tool loading, Code Mode, large-result offloading, compaction — and it scales from `npx` on SQLite to Postgres+Redis via Docker Compose or Helm. Caveats: local mode has no login and is explicitly not for anything internet-facing, sandboxing means Daytona today, and it's a harness rather than a graph framework — if you need bespoke control flow per step, a lower-level runtime fits better.

Mapped by ShipWithAI editors · links verified

README.md

The open-source agent harness - the runtime layer that turns an LLM into a working agent

TrueForge

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.

TrueForge Chat UI

Why TrueForge?

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, MCP servers, skills, and a 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.
**Hum

Continue your stack

What teams reach for next — and why each earns a place beside trueforge. Ranked by curator confidence.

Alternative to See all + compare →

deepagents

LangChain's batteries-included agent harness on LangGraph — planning, sub-agents with isolated context, filesystem, shell, skills, human-in-the-loop and persistent memory out of the box.

Why it fitsBoth ship the batteries — planning, subagents, filesystem, skills, human-in-the-loop. deepagents is a Python library on LangGraph you compose in code; TrueForge is a TypeScript server with a chat UI, HTTP API and catalogs you configure once.

scale-agentex

Scale AI's open agent platform: scaffold agents with a CLI, run them behind the ACP protocol with a dev UI, and graduate from sync chat to durable Temporal-backed long-running workflows.

Why it fitsTwo open agent platforms with a server, dev UI and SDK. AgentEx graduates you to the ACP protocol and Temporal-backed durable workflows; TrueForge stays a batteries-included harness with sandboxing, approvals and context compaction built in.

agentfield

Open-source control plane that runs AI agents as microservices: write plain Python/Go/TS functions, get REST endpoints with routing, queues, retries, memory and tracing — one laptop to 10k agents.

Why it fitsagentfield runs agents as microservices — REST endpoints, queues, retries, fleet scale; TrueForge runs one well-instrumented agent loop with a UI in front of it. Pick by whether your problem is scaling deployments or getting a single agent production-ready.