goose vs openhuman
General-purpose local AI agent in Rust — native desktop app, full CLI and embeddable API — over 15+ providers and 70+ MCP extensions. Block's goose, now an Agentic AI Foundation project. — versus — Rust agent harness built for fleets: desktop app, terminal or embeddable library, with built-in memory, browser/desktop control, 119 OAuth apps and 14 channels — 500 agents on a $10 VPS.
Both are general-purpose Rust agents shipped as desktop app, CLI and embeddable API with MCP extensions; goose is Apache-2.0 and foundation-governed, OpenHuman GPL-3.0 and tuned for fleet density.
| goose | openhuman | |
|---|---|---|
| Stars | 55k | 42k |
| Forks | 6.4k | 4.1k |
| Language | Rust | Rust |
| License | Apache-2.0 | GPL-3.0 |
| Last activity | 3 days ago | today |
| Topics | agents, coding | agents, coding |
| Curated connections | 10 | 3 |
goose — the curator's take
The default answer when someone wants a real agent on their own machine and does not want to assemble one. Rust, three surfaces (desktop app, CLI, API), 15+ providers including Ollama and your existing Claude/ChatGPT/Gemini subscriptions over ACP, 70+ MCP extensions, and custom distributions if you want to ship your own branded build. Now governed under the Linux Foundation's AAIF rather than one vendor, which matters if you are betting a product on it. It is deliberately general — code, research, writing, data — so it has no opinion about your SDLC: no verification gates, no worktree isolation, no PR pipeline. If you want an agent that must prove its work, or a spec-to-PR factory, layer that on or pick a purpose-built harness. Note the repo moved from block/goose; old links and forks still point at the old org.
openhuman — the curator's take
Interesting if you want one agent per customer or per task at fleet scale, or a typed Rust API instead of shelling out to a CLI — its own 10-task SWE-bench run shows far less memory, tokens and time than Claude Code, Codex or Hermes. Caveats: early beta, benchmarks are self-run, GPL-3.0 constrains embedding it in closed products, and tool search and on-screen clicks lean on the hosted Jev model.