Metadata-Version: 2.5
Name: cultureos
Version: 0.12.1
Summary: CultureOS - an operating system built on Culture, the AgentCulture agent mesh.
Project-URL: Homepage, https://github.com/agentculture/cultureos
Project-URL: Issues, https://github.com/agentculture/cultureos/issues
Author: AgentCulture
License-Expression: Apache-2.0
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development
Requires-Python: >=3.12
Description-Content-Type: text/markdown

# cultureos

CultureOS - an operating system built on Culture, the AgentCulture agent mesh.

> **Status: early scaffold.** This repo was generated from
> [`culture-agent-template`](https://github.com/agentculture/culture-agent-template)
> and currently ships only the template's sibling-pattern baseline described
> below. CultureOS-specific functionality has not landed yet.

## What's here

- **An agent-first CLI** cited from [teken](https://github.com/agentculture/teken)
  (`afi-cli`) — the runtime package has no third-party dependencies.
- **A mesh identity** — `culture.yaml` (`suffix` + `backend`) and the matching
  resident prompt file (`CLAUDE.md`, since this agent runs
  `backend: claude`). The mesh resident is one of **two separate
  selections** over this clone — see
  [Two selections, not one](#two-selections-not-one) below.
- **Four harness prompt files**, one per agent harness, each read by exactly
  one of them (see [Prompt files by harness](#prompt-files-by-harness) below).
  All four harnesses are usable interactively regardless of which one
  `culture.yaml` names as the mesh resident.
- **The canonical guildmaster skill kit** under `.claude/skills/`,
  vendored cite-don't-import, and exposed to the other harnesses through
  `.qwen/skills`, `.colleague/skills` and `.pi/skills` symlinks. See [`docs/skill-sources.md`](docs/skill-sources.md).
- **A build + deploy baseline** — pytest, lint, the agent-first rubric gate, and
  PyPI Trusted Publishing wired into GitHub Actions.

## Prompt files by harness

Four harnesses, four root files, no shared base — each file is read by
exactly one harness:

| Harness | File(s) |
|---------|---------|
| Claude Code | [`CLAUDE.md`](CLAUDE.md) |
| Pi / associate | [`AGENTS.override.md`](AGENTS.override.md) + [`.pi/SYSTEM.md`](.pi/SYSTEM.md) |
| colleague | [`AGENTS.colleague.md`](AGENTS.colleague.md) |
| Qwen Code | [`QWEN.md`](QWEN.md) |

**Claude Code** — `CLAUDE.md` is the fullest write-up of the repo's
conventions; read it first.

**Pi / associate** — `AGENTS.override.md` replaces this directory's
`AGENTS.md`/`CLAUDE.md` in Pi's context layer, so Pi does not inherit
`CLAUDE.md`. `.pi/SYSTEM.md` replaces Pi's default system prompt with the
non-coding `associate` identity (read/find/summarize only).

**colleague** — colleague's prompt cascade is `AGENTS.md` →
`AGENTS.colleague.md` → `AGENTS.colleague.<model>.md`. This repo ships only
the middle layer: there is no `AGENTS.md` (a shared base across harnesses was
considered and rejected) and no per-model override file.

**Qwen Code** — Qwen Code reads `QWEN.md` and `AGENTS.md`; since there is no
`AGENTS.md`, `QWEN.md` is its sole source of guidance.

There is intentionally **no `AGENTS.md`** at the root — each harness gets an
unrelated file rather than cascading from a shared base.

## Two selections, not one

It is tempting to read "switch harness" as one decision. It is actually two,
and this repo's layout exists partly to keep them separate:

1. **The interactive harness** — which binary you run (`claude`, `pi`,
   `colleague`, `qwen`). `cd` into the clone and run any of them; all four
   are live simultaneously, and none of them requires editing a file or
   flipping a switch. A harness can be force-selected for one invocation
   (e.g. a CI smoke check) without ever touching `culture.yaml` — see
   [`docs/automation-contract.md`](docs/automation-contract.md).
2. **The mesh resident** — the single `backend` `culture.yaml` declares,
   which is what the Culture daemon starts and what `steward doctor`
   checks. `guild harness use <name>` changes only this.

`culture.yaml`'s `backend` affects (2) only. It never affects which harness
you can invoke interactively in (1). See
[`docs/harness-selection.md`](docs/harness-selection.md) for the full
writeup, including who reads this config and why existing siblings are not
retrofitted by this arc.

## Quickstart

```bash
uv sync
uv run pytest -n auto                 # run the test suite
uv run cultureos whoami               # identity from culture.yaml
uv run cultureos learn                # self-teaching prompt (add --json)
uv run teken cli doctor . --strict    # the agent-first rubric gate CI runs
uv run python scripts/harness-smoke.py --stage config  # all four harness configs
```

## CLI

| Verb | What it does |
|------|--------------|
| `whoami` | Report this agent's nick, version, backend, and model from `culture.yaml`. |
| `learn` | Print a structured self-teaching prompt. |
| `explain <path>` | Markdown docs for any noun/verb path. |
| `overview` | Read-only descriptive snapshot of the agent. |
| `doctor` | Check the agent-identity invariants (prompt-file-present, backend-consistency). |
| `cli overview` | Describe the CLI surface itself. |

Every command supports `--json`. Results go to stdout, errors/diagnostics to
stderr (never mixed). Exit codes: `0` success, `1` user error, `2` environment
error, `3+` reserved.

## Development conventions

- Every PR bumps the version (`version-bump` skill); CI's `version-check` job
  blocks merge otherwise.
- PRs go through the `cicd` skill (`devex pr` + SonarCloud gating).
- Lint: black, isort, flake8 (line length 100), bandit, markdownlint, plus
  `scripts/scan-secrets.py` and the `teken cli doctor --strict` rubric gate.
- Pushing to `main` publishes to PyPI via Trusted Publishing; PRs do a
  TestPyPI dry-run.
- Vendored skills are cited verbatim — re-sync from guildmaster rather than
  editing them (see [`docs/skill-sources.md`](docs/skill-sources.md)).
- When conventions change, update all four harness prompt files together so
  they don't drift.

See [`CLAUDE.md`](CLAUDE.md) for the full write-up (CLI architecture,
worktree layout, memory discipline).

## The `gate` section

`culture.yaml` may carry a top-level `gate` section that declares how to set
up and test this repo, so tooling (for example a PR-fixer that re-runs the
checks before pushing) needs no per-repo knowledge:

```yaml
gate:
  setup:
  - [uv, sync]
  test:
  - [uv, run, pytest, -n, auto]
```

`setup` and `test` are each a list of commands, and each command is an argv
list (never a shell string), run in order from the repo root. The values are
configuration only; no tool supplies a default. Culture's loader ignores
unknown top-level keys, so the section is safe alongside `agents`.

## License

Apache 2.0 — see [`LICENSE`](LICENSE).
