OpenAGIA self-improving,
proactive agent.
It learns. It reaches out. It earns its keep.
Most local agents just sit there waiting for a prompt. OpenAGI runs as a daemon on your machine, learns from your conversations, optionally watches what you do on screen, and pings you with what it can take off your plate. Bring your own LLM. Your data never leaves.
curl -fsSL openagi.sh | shLocal agents are good.
An agent with a decision layer is better.
Hermes Agent, OpenClaw, and SwarmClaw set the bar for self-hosted agent runtimes — memory, MCP, BYO LLM, all there. OpenAGI takes that shape and adds the four things they don’t: it watches you work, scores every signal before acting, spawns persistent specialists for repeated work, and locks in your correctionsso you never have to make the same one twice. The cloud agents (Operator, Claude.ai) don’t start the same race.
OpenAGI local | Hermes Agent local | OpenClaw local | SwarmClaw local | Operator cloud | Claude.ai cloud | |
|---|---|---|---|---|---|---|
| Runs on your machine | ✓ | ✓ | ✓ | ✓ | — | — |
| Your data never leaves | ✓ | ✓ | ✓ | ✓ | — | — |
| Bring your own LLM | ✓ any | ✓ 200+ | ✓ | ✓ 23+ | — | — |
| Watches you, learns patterns | ✓ | — | — | — | — | — |
| Adaptive Scrutiny decision layer | ✓ | — | — | — | — | — |
| Persistent specialists (propagation) | ✓ auto-spawn | parallel only | — | manual org chart | — | — |
| Corrections lock in, never repeat | ✓ | — | — | — | — | — |
| Persistent memory across sessions | ✓ tiered | ✓ FTS5 | ✓ markdown | ✓ durable | limited | limited |
| Multi-channel (SMS / Telegram / HTTP) | ✓ | ✓ | ✓ | dashboard only | — | — |
| Skills system | ✓ auto + manual | ✓ agentskills.io | ✓ | ✓ reviewed | — | — |
| Cron / scheduled tasks | ✓ | ✓ | ✓ | ✓ | — | — |
| Source-available | ✓ | ✓ | ✓ | ✓ | — | — |
| No telemetry, no accounts | ✓ | ✓ | ✓ | ✓ | — | — |
OpenAGI builds on the foundation that Hermes Agent, OpenClaw, and SwarmClaw shipped first — durable memory, MCP, daemon shape, BYO LLM. The four highlighted rows are the differentiators: watching you work, Scrutiny scoring, persistent specialization, and corrections that lock in. Hermes spawns parallel subagents per turn. SwarmClaw uses manually-configured org charts. OpenAGI auto-spawns persistent specialists when Scrutiny decides the task warrants one.
Talks like someone
who knows you.
Every conversation, every correction, every decision lives in OpenAGI’s tiered memory — short-term for working context, medium for repeated patterns, long-term “Lava” for durable truths. The agent doesn’t reset between sessions. It picks up where you left off, remembers what you ruled out, and stops asking the same questions twice.
The seven-axis Scrutiny layer scores every signal before acting. Corrections lock in. Mistakes don’t repeat. Risky or repeated tasks spawn bounded specialists with their own scope. Specialization without sprawl.
- → Tiered memory: short / medium / long-term, with intelligent decay
- → Directional Adaptive Scrutiny — act, ask, watch, ignore, propagate
- → Corrections you make once never have to be made twice
Plus — it can
watch you work.
Turn on local screen capture and OpenAGI starts noticing the things you do over and over. The file you keep moving, the report you build every Friday, the script you run after every deploy. Once it sees the pattern enough times, it builds a skill for it and offers to do it for you next time.
You don’t teach it. You don’t configure it. You just work, and it’s paying attention. (And the screen capture stays on your machine like everything else.)
- → Local screen capture, processed on-device
- → Pattern detection across days, not just sessions
- → Auto-generated skills you can review, edit, or reject
- → Off by default — opt in per workspace
Personal. Private.
Yours.
Everything OpenAGI sees, learns, and remembers lives in ~/.openagi/ on your machine. No accounts. No telemetry. No remote dependencies beyond the model API key you choose to provide.
Use any LLM — OpenAI, Claude, Gemini, local Ollama, anything that speaks the OpenAI Responses API. Swap models any time. The agent you raise belongs to you, not to the lab that trained the weights.
- → Bring your own keys for any provider
- → Falls back to deterministic mode if no key is set
- → File-backed JSONL stores you can read, back up, or delete
- → MCP servers add tools without giving up control
Inputs in. Outputs out.
Everything in between is yours.
One command. Three flavors.
All three end with a daemon listening on 127.0.0.1:43210 and a setup wizard at /setup for your model keys.
curl -fsSL openagi.sh | shOne-line shell installer. macOS & Linux. Drops the binary, sets up launchd or systemd, you’re done.
Multi-arch (amd64 + arm64). Mount a data volume and the daemon survives restarts. Works on Raspberry Pi.
Clone, run npm run serve, hit the setup wizard at localhost:43210/setup.
Raise your own agent.
Today, day one.
OpenAGI starts knowing nothing. By week two, it knows your patterns. By month three, it’s doing the boring half of your work without being asked. Bring your own keys. Bring your own machine. Bring whatever LLM you trust.