Skip to main content
Glama
README.md
# Athena

**A project-aware, capability-driven advisory framework for AI coding assistants.**

Athena is an AI Consultation Runtime. Cursor Composer owns execution; Athena owns consultation.

## Features

- Single MCP tool: `consult(advisor_type, question, session_context, mode)`
- Capability-driven routing across Anthropic, OpenAI, and Ollama providers
- Project memory with SQLite storage and git-based incremental indexing
- Structured advisory responses for Composer to apply

## Quickstart

```bash
pip install -e ".[dev,providers]"
export ANTHROPIC_API_KEY=your-key
python -m athena.mcp_server.server
```

Add the plugin MCP config from [`plugin/.mcp.json`](plugin/.mcp.json) to your project's `.cursor/mcp.json`.

## Documentation

Engineering specifications live in [`docs/specs/README.md`](docs/specs/README.md).

## Development

```bash
pip install -e ".[dev,providers]"
python3 -m pytest -q
python3 -m ruff check athena tests benchmarks
python3 benchmarks/run_baseline.py
```

See [`docs/extension-guide.md`](docs/extension-guide.md) for adding providers, advisor profiles, capabilities, and strategy modes.

## License

MIT — see [LICENSE](LICENSE).

TDQS

B3/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a distinct purpose: indexing, remembering decisions, checking status, consulting, and viewing history. No overlap in functionality.

Naming Consistency3/5

Three tools follow the 'athena_verb' pattern, but 'consult' and 'get_consultation_history' break the pattern with different prefixes, introducing inconsistency.

Tool Count5/5

Five tools is a well-scoped set for a project memory and expert advisor server, covering core operations without being excessive.

Completeness4/5

The surface covers essential memory and consulting operations, but could include update/delete for memories or clearing consultation history for full lifecycle coverage.

Maintenance

ActivityInactive
ResponsivenessNo issues