agentfield vs trueforge
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. — versus — 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.
agentfield 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.
| agentfield | trueforge | |
|---|---|---|
| Stars | 2.5k | 3.5k |
| Forks | 403 | 241 |
| Language | Go | TypeScript |
| License | Apache-2.0 | MIT |
| Last activity | 4 days ago | yesterday |
| Topics | agents, orchestration | agents, orchestration |
| Curated connections | 7 | 3 |
agentfield — the curator's take
The 'agents as a backend' play: write plain functions (no DSL, no graph wiring), and the Go control plane turns each into a REST endpoint any service can call — with fan-out to thousands of parallel agents, queues, retries, versioned deploys, observability and identity/audit built in. Reach for it when agents must be production infrastructure callable by frontends, cron jobs and other services — not a chat window. NOT for notebook experiments or a single local agent (a control plane + SDK is real operational commitment), and it won't give you reasoning-pattern libraries — you still design the agent logic it hosts. Its prompt-to-backend flow (/agentfield in Claude Code/Cursor) is a nice on-ramp, but evaluate the runtime, not the demo.
trueforge — the 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.