This guide gets AgentOS installed, configured, and running locally. It assumes you want the standard product experience: terminal commands, local Web UI, Pilot Router, memory/search support, and safe local defaults.
- Python 3.12 or newer for terminal installs.
uvfor the recommended terminal install.- Git, Git LFS, and Node.js 22 or newer only when installing from source.
- A provider API key unless you use a local provider such as Ollama.
Install the current release (recommended extras included) by following the Installation section of the README. The newest release assets are always on the Releases page.
The recommended extra includes Pilot Router dependencies and memory/search
support used by the default product experience.
If agentos is not found after install, open a new shell or run:
uv tool update-shellInteractive setup:
agentos onboardScript-friendly setup:
export OPENROUTER_API_KEY="sk-..."
agentos onboard --provider openrouter --api-key-env OPENROUTER_API_KEYUseful variants:
agentos onboard --if-needed
agentos onboard --minimal
agentos onboard --provider openai --api-key-env OPENAI_API_KEY
agentos onboard --provider ollama --model llama3.1--if-needed is safe for install scripts because it avoids rewriting an
already-ready setup. --minimal configures the provider path and skips optional
channels/search/image-generation sections.
Check onboarding state:
agentos onboard statusForeground gateway:
agentos gateway runBackground gateway with readiness wait:
agentos gateway start --json
agentos gateway statusDefault address:
http://127.0.0.1:18791/control/
The gateway defaults to loopback for safety. To bind elsewhere, opt in:
agentos gateway run --listen 0.0.0.0 --port 18791Only expose a non-loopback gateway behind appropriate auth and network controls.
Open the Web UI:
http://127.0.0.1:18791/control/
Start terminal chat:
agentos chatRun one automation turn:
agentos agent -m "Inspect this workspace and suggest a test plan"Run a one-shot task in a specific workspace:
agentos agent \
--workspace /path/to/project \
--workspace-strict \
-m "Review the current diff and list the highest-risk changes"Use the Web UI for browser-based chat, approvals, setup, channels, usage, and
logs. Use agentos chat when you want a terminal conversation. Use
agentos agent for one-shot automation.
Resume a terminal chat session:
agentos chat --session <session-key>Inspect sessions:
agentos sessions list
agentos sessions show <session-key>
agentos sessions export <session-key>Export a session when exact history matters for debugging or handoff.
Run these after setup:
agentos doctor
agentos providers list
agentos search list
agentos channels types --jsonIf the gateway is running, inspect runtime status:
agentos gateway status
agentos providers status
agentos channels status
agentos memory statusFor provider/model selection details, see
providers-and-models.md. For search setup, see
search.md.
For gateway lifecycle, host/port, and exposure guidance, see
gateway.md.
Foreground gateway:
Ctrl+C
Managed background gateway:
agentos gateway stop
agentos gateway restartUpgrade to the latest release. agentos upgrade also restarts the
gateway and verifies it reports the new version, so it is preferred
over calling uv tool yourself:
agentos upgradeIt installs the published release of use-agent-os[recommended] — the
same extras profile install_source.sh uses — pinned to the Python
version already running AgentOS. Your configuration and data in
~/.agentos/ are not touched. To check the installed version, run
uv tool list.
agentos upgrade never installs from a local checkout: only
bash scripts/install_source.sh rebuilds the React control UI before
installing. If you installed from source, re-run that script. See the
README upgrade section.
After the first run:
- Configure search if you want web research:
search.md. - Enable channels if you want Slack, Telegram, Discord, or another
messaging surface:
channels.md. - Review memory behavior if you want durable recall:
features/memory.md. - Review tool permissions before unattended automation:
tools-and-sandbox.md. - Learn Pilot Router if you want cost-aware model routing:
features/agentos-router.md. - Use the glossary if product terms are unfamiliar:
glossary.md.
Use source install when you want a checkout-backed install:
git lfs install
git clone https://github.com/use-agent-os/agent-os.git
cd agent-os
git lfs pull --include="src/agentos/memory/models/**"
git lfs pull --include="src/agentos/agentos_router/models/**"
bash scripts/install_source.shFor development, use the repository virtual environment:
uv sync --extra recommended --extra dev
uv run agentos --help
uv run agentos gateway runWhen developing from source, prefix commands with uv run so they use the
checkout you are editing.
Docs index · Product guide · Improve this page · Report a docs issue