User Guide
One page per thing humanize does, each answering "how do I use this?" — for the person who runs flows rather than writes them. Where a page here shows Python, it is to say what the weaver on the other side of the feature did; writing a flow yourself is the Weaver Guide.
Never run one before? Start at the quickstart. The tutorials below each take a whole piece of work start to finish; everything under them is for looking up.
Tutorials
| Beat a benchmark | Two agents take turns optimising a kernel |
| Port a project | An agent works, a reviewer reads it back |
| Build a coding agent | Idea, plan, then build under review |
Start here
| Installation | Python, a backend, and what each one needs |
| Concepts | The twelve words the rest of this uses |
| Security | Read this before pointing an agent at a repository you care about |
| Troubleshooting | When it goes wrong |
At the prompt
| Talking to a running turn | A line typed mid-turn goes into it, not after it |
| Side questions | /btw: ask about progress without steering the flow |
| Many conversations at once | One transcript, tab between the agents that are working |
| Showing the working | /details: tool calls and thinking, or only what the agent says |
| The shape of a run | /status: who is working, who handed to whom, what it cost |
| The mission board | Lines you and the flow both write on, and neither waits at |
| Being away | /afk: whether an agent may stop and ask you something |
| Falling back | /fallback: where a turn goes when what was taking it cannot |
| Completion | What a half-typed line could become, under the editor |
| History | Everything typed here before, on ↑ and ↓ |
| Exporting a transcript | /export writes what is on screen, as it was written |
| What a project remembers | Reopening finds it set up the way you left it |
| Stopping | ctrl+c twice ends the flow; what that does to a turn |
Setting an agent up
| Efforts | How hard to think — and moving it while the flow runs |
| Permissions | Four rungs, from read-only to bypass |
| Skills | What an agent carries: its CLI's own, and the ones the flow brings |
| Questions | An agent stopping mid-turn to ask its user something |
| Cost and rate | What has been spent, how fast, and how hard it is thinking |
| Reporting | What humanize sends its developers, and how to say no |
Where the work lands
| Providers | One CLI, two accounts, at the same time |
| Containers | A container of the agent's own, up on the first turn |
| Remote execution | The agent here; its commands on the build box |
Running it, and reading it back
| Unattended | hmz exec from a script, with nobody watching |
| humanize in CI | The same flows on a build machine |
| Tracing | The whole run as one timeline you can open in Perfetto |
| Picking a run up | A loop stopped on Thursday, carried on from where it stopped |
If you write flows too
Three pages live here and matter either way. Concepts is the vocabulary the whole site uses, weaver included; Security is why reading a flow means running it; Skills is what an agent carries into a turn, and what a flow may add. The rest of that job is the Weaver Guide.
Looking for the exhaustive list of flags and keys instead? CLI and TUI.