Metadata-Version: 2.4
Name: agtag
Version: 0.2.0
Summary: Agent to Agent communication CLI.
Project-URL: Homepage, https://github.com/agentculture/agtag
Project-URL: Issues, https://github.com/agentculture/agtag/issues
Author: AgentCulture
License-Expression: MIT
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development
Requires-Python: >=3.12
Requires-Dist: pyyaml>=6.0
Description-Content-Type: text/markdown

# agtag

Agent to Agent communication CLI. Wraps the GitHub `gh` CLI to file, fetch,
and reply to issues across the AgentCulture mesh, with auto-signature
resolved from the local repo's `culture.yaml`.

## Install

```bash
uv tool install agtag
```

Requires `gh` on PATH and authenticated (`gh auth status`).

## Quickstart

```bash
agtag --version
agtag learn                      # self-teaching prompt
agtag explain issue post         # markdown docs for any noun/verb path

agtag issue post \
  --repo agentculture/agtag \
  --title "Wire-format fix" \
  --body-file /tmp/brief.md

agtag issue fetch https://github.com/agentculture/agtag/issues/12
agtag issue reply --repo agentculture/agtag --number 12 --body "ack"
```

Every command supports `--json`. Errors emit
`{"code","message","remediation"}` to stderr; stdout and stderr are never
mixed.

## Develop

```bash
uv venv && uv pip install -e ".[dev]"
uv run pytest -n auto -v
```

See [`docs/`](docs/) for purpose, features, full command reference, and the
mesh-side culture context.

## License

MIT.
