# Agent URL: https://docs.hanzo.ai/docs/cli/agent > The `hanzo agent` commands. Also for this capability: [API](https://docs.hanzo.ai/docs/openapi/agent) · **CLI** · [MCP](https://docs.hanzo.ai/docs/mcp-tools/agent) · [SDKs](https://docs.hanzo.ai/docs/sdks) Autonomous agents for your org: define them, run them, keep every run. [API reference →](https://docs.hanzo.ai/docs/openapi/agent) ```bash hanzo agent list ``` Every command takes `--json` for the raw response and `--help` for its own flags. Sign in once with `hanzo auth login`; the commands below use that session, and the org they act in is the one it carries. | Command | What it does | | -------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | | `hanzo agent activity` | Serves the org-wide recent-activity feed. | | `hanzo agent coding` | Start one autonomous coding run against a repo in the caller's org | | `hanzo agent create` | Defines an agent in the caller's org: a model, a system prompt (instructions) and a set of tool names. | | `hanzo agent get ` | Returns one agent with its system prompt and its 20 most recent runs. | | `hanzo agent list` | Returns every agent defined in the caller's org, each with the number of runs recorded against it. | | `hanzo agent metrics` | Serves the invocations-over-time histogram for the org's Agents dashboard. | | `hanzo agent rm ` | Removes an agent and every run recorded against it. | | `hanzo agent run ` | Run one of your org's agents and get the recorded run back. | | `hanzo agent runs ` | Returns one agent's execution history, newest first — each run's input, its output or its error, and how long it took. | | `hanzo agent runs-all` | Returns the org's agent runs across EVERY agent, newest first — what ran here, for whom, on which model, how long it took, and why it failed. | | `hanzo agent spend ` | Answers what one of your org's agents has spent, in integer micro-USD. | | `hanzo agent update ` | Changes an agent in place. | ### Builds | Command | What it does | | -------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `hanzo agent builds list` | Returns the public index of every published build, most recently updated first, so a gallery can link straight to the story behind each product. | | `hanzo agent builds org get ` | Returns the readable build of one product: the agent session that produced it, turn by turn — the prompts, the reasoning, the commits each turn produced — plus the exact `git log` that re-derives every commit binding from git itself, so nothing here has to be taken on trust. | ### Chat | Command | What it does | | ----------------------------------------- | ------------------------------------------------------- | | `hanzo agent chat conversations create` | Record turns in a conversation | | `hanzo agent chat conversations get ` | Read one agent thread in full | | `hanzo agent chat conversations list` | List the agent threads in your org | | `hanzo agent chat create` | Run one tool-calling round against your org's own tools | | `hanzo agent chat presets` | List the agent presets available to a caller | ### Sessions | Command | What it does | | ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | `hanzo agent sessions budget ` | Sets, raises, or removes a session's cap. | | `hanzo agent sessions control ` | Returns the steering commands (pause/resume/stop/message) recorded against the caller's own session that are newer than the cursor, oldest first, with the cursor to poll from next. | | `hanzo agent sessions create` | Opens a live agent session in the caller's org — the row every surface (the CLI's outer agent, hanzo.bot, the console, chat) hangs its activity off. | | `hanzo agent sessions events ` | Records one turn of a session's transcript and answers 201 with it. | | `hanzo agent sessions get ` | Returns one session with its direct child sessions and its 50 most recent events, oldest of those first. | | `hanzo agent sessions list` | Returns the caller org's live sessions, newest first — each with its event count, its direct-child count and a one-line preview of its latest event. | | `hanzo agent sessions message ` | Sends a steering message to a running session — the endpoint a human or another agent interrupts through. | | `hanzo agent sessions pause ` | Asks a running session to pause. | | `hanzo agent sessions progress ` | Returns how far along one run is: the share of its goal that is done, whether it is running, blocked or finished, and a line saying what it is doing right now. | | `hanzo agent sessions resume ` | Asks a paused session to continue, on the same terms as a pause. | | `hanzo agent sessions stop ` | Ends a running session. | | `hanzo agent sessions stream` | Live session and event updates for the caller's org, as Server-Sent Events. | | `hanzo agent sessions tree ` | Returns the subagent-flow graph rooted at this session: the session, its children, their children, each node carrying its own event count. | | `hanzo agent sessions update ` | Updates a session's surface-owned truth: its status, its title, the run-target it is dispatched to, and the product it built plus whether that build's story is public. | ### Targets | Command | What it does | | ---------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `hanzo agent targets claim ` | The machine's long poll for work: it authenticates the daemon, stamps the liveness the dispatch gate reads (the poll IS the proof a runner is listening), and waits up to 25 seconds for the next run addressed to THIS machine. | | `hanzo agent targets create` | Registers a machine as an agent target, or re-links one that is already registered. | | `hanzo agent targets get ` | Returns one registered machine, with its live session load. | | `hanzo agent targets key ` | Mints (or rotates) the claim key a `hanzo code --serve` daemon presents to claim work for this machine, and returns it ONCE: only its SHA-256 hash is stored. | | `hanzo agent targets list` | Returns every machine registered to the caller's org, newest first, each with its live session load. | | `hanzo agent targets rm ` | Deregisters one machine. | | `hanzo agent targets runs report ` | Completes a claimed run: it delivers the terminal result to the run's durable owner, which is what lets that workflow finish. | | `hanzo agent targets update ` | Updates one machine in place. |