openhuman vs picobot
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. — versus — A self-hosted personal AI agent in a single ~9MB Go binary — persistent memory, 16 tools + MCP, skills, cron/heartbeat, and Telegram/Discord/Slack/WhatsApp channels. Runs on a $5 VPS.
Both are self-hosted personal agents in one small native binary with memory, skills, cron and messaging channels; picobot is a lean Go single agent, OpenHuman a Rust harness built for fleets.
| openhuman | picobot | |
|---|---|---|
| Stars | 42k | 1.3k |
| Forks | 4.1k | 168 |
| Language | Rust | Go |
| License | GPL-3.0 | MIT |
| Last activity | today | 24 days ago |
| Topics | agents, coding | agents |
| Curated connections | 3 | 6 |
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.
picobot — the curator's take
The anti-bloat statement piece: zero dependencies, ~10MB RAM idle, instant cold start — an always-on agent with ranked memory recall, background subagents, a natural-language HEARTBEAT.md cron, and self-authored skills ('create a skill for checking weather' → it writes the markdown), reachable from your phone via four chat channels. Runs on a Raspberry Pi or Termux on an old Android. Any OpenAI-compatible endpoint, including Ollama. Its own README names the target: OpenClaw's power without the 500MB container. NOT a coding harness and single-user by design — this is your personal daemon, not a team platform; complex multi-agent workflows will outgrow it fast, which is rather the point.