Metadata-Version: 2.4
Name: mackin
Version: 0.1.0
Summary: Shared reasoning memory for parallel multi-agent systems
Project-URL: Homepage, https://github.com/Mackin-labs/Mackin
Project-URL: Repository, https://github.com/Mackin-labs/Mackin
Project-URL: Issues, https://github.com/Mackin-labs/Mackin/issues
Author: Mackin Contributors
License-Expression: MIT
Keywords: agents,ai,embeddings,llm,memory,multi-agent,reasoning
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Requires-Dist: aiosqlite>=0.20.0
Requires-Dist: pydantic>=2.0.0
Provides-Extra: anthropic
Requires-Dist: anthropic>=0.39.0; extra == 'anthropic'
Provides-Extra: dev
Requires-Dist: anthropic>=0.39.0; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Description-Content-Type: text/markdown

# Mackin (Python)

Shared reasoning memory for parallel multi-agent systems.

## Install

```bash
pip install mackin
```

For enhanced embeddings with Anthropic API:

```bash
pip install mackin[anthropic]
```

## Quick start

```python
from mackin import MackinStore

memory = MackinStore(session_id="my-task")

# Agent A writes reasoning
await memory.write(
    agent="researcher",
    decision="use Q4 2024 earnings report",
    reasoning="Most recent and authoritative source",
    confidence=0.9,
    tags=["source-selection"]
)

# Agent B reads structured context
context = await memory.read(
    agent="writer",
    filter={"tags": ["source-selection"], "confidence_min": 0.8}
)

# Detect conflicts
conflicts = await memory.conflicts(topic="revenue")

# Full trace
trace = await memory.trace()
```

## No API key required

Mackin works out of the box with local hash-based embeddings. Set `ANTHROPIC_API_KEY` for higher-quality semantic search via Claude embeddings.

## Full documentation

See the [main repository README](https://github.com/Mackin-labs/Mackin).
