Skip to main content

A configurable embedding system with DuckDB storage and MCP server integration

Project description

Distillery

Distillery

Team Knowledge, Distilled
Capture, classify, connect, and surface team knowledge through conversational commands.

Documentation · Skills · Quick Start · Roadmap · Slides

PyPI version PyPI downloads License Python version


What is Distillery?

Distillery is a team knowledge base accessed through Claude Code skills. It refines raw information from working sessions, meetings, bookmarks, and conversations into concentrated, searchable knowledge — stored as vector embeddings in DuckDB and retrieved through natural language. Runs locally over stdio or as a hosted HTTP service with GitHub OAuth for team access.

Distillery captures the highest-value transformation — from noise to signal — and makes it a tool the whole team can use.

Full documentation: norrietaylor.github.io/distillery

Distillery demo — /distill captures a decision, /pour synthesizes it

Skills

Distillery provides 14 Claude Code slash commands:

Skill Purpose Example
/distill Capture session knowledge with dedup detection /distill "We decided to use DuckDB for local storage"
/recall Semantic search with provenance /recall distributed caching strategies
/pour Multi-entry synthesis with citations /pour how does our auth system work?
/bookmark Store URLs with auto-generated summaries /bookmark https://example.com/article #caching
/minutes Meeting notes with append updates /minutes --update standup-2026-03-22
/classify Classify entries and triage review queue /classify --inbox
/watch Manage monitored feed sources /watch add github:duckdb/duckdb
/radar Ambient feed digest with source suggestions /radar --days 7
/tune Adjust feed relevance thresholds /tune relevance 0.4
/digest Team activity summary from internal entries /digest --days 7 --project myapp
/gh-sync Sync GitHub issues/PRs into the knowledge base /gh-sync owner/repo --issues
/investigate Deep context builder with relationship traversal /investigate distributed caching
/briefing Team knowledge dashboard with metrics /briefing --days 7
/setup Onboarding wizard for MCP connectivity and config /setup

Quick Start

Step 1: Install the Plugin

claude plugin marketplace add norrietaylor/distillery
claude plugin install distillery

This installs all 14 skills. The plugin defaults to a hosted demo server — you can start using Distillery immediately.

Demo Server: distillery-mcp.fly.dev is for evaluation only. Do not store sensitive or confidential data.

Step 2: Switch to Local with uvx (Recommended)

For a private knowledge base, run the MCP server locally with uvx — no persistent install needed:

# Get a free API key from jina.ai, then:
export JINA_API_KEY=jina_...

Add to ~/.claude/settings.json (overrides the plugin's demo server):

{
  "mcpServers": {
    "distillery": {
      "command": "uvx",
      "args": ["distillery-mcp"],
      "env": {
        "JINA_API_KEY": "${JINA_API_KEY}"
      }
    }
  }
}

Restart Claude Code and run the onboarding wizard:

/setup

See the Local Setup Guide for full configuration options, or deploy your own instance for team use.

Development

uv pip install -e ".[dev]"
# or
pip install -e ".[dev]"
pytest                              # run tests
mypy --strict src/distillery/       # type check
ruff check src/ tests/              # lint

See Contributing for the full guide.

License

Apache 2.0 — see LICENSE for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

distillery_mcp-0.3.2.tar.gz (1.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

distillery_mcp-0.3.2-py3-none-any.whl (211.3 kB view details)

Uploaded Python 3

File details

Details for the file distillery_mcp-0.3.2.tar.gz.

File metadata

  • Download URL: distillery_mcp-0.3.2.tar.gz
  • Upload date:
  • Size: 1.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for distillery_mcp-0.3.2.tar.gz
Algorithm Hash digest
SHA256 a77f7acfc5791ee7c3c89af7249e7564545f6eff996550d21200256d05552090
MD5 8aa8c0960f048d5f3fa387b21fbfebbe
BLAKE2b-256 82af580381526108d3a5c01e4d53cf7d8181efbd2bfacfad810af5fbcae564b2

See more details on using hashes here.

Provenance

The following attestation bundles were made for distillery_mcp-0.3.2.tar.gz:

Publisher: pypi-publish.yml on norrietaylor/distillery

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file distillery_mcp-0.3.2-py3-none-any.whl.

File metadata

  • Download URL: distillery_mcp-0.3.2-py3-none-any.whl
  • Upload date:
  • Size: 211.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for distillery_mcp-0.3.2-py3-none-any.whl
Algorithm Hash digest
SHA256 b52737361cbbd74c5eb3b6ac039c03a1a39d21e21d997d6eb8f78b295040f5e0
MD5 2949c60fb2aa5f6e4cfd1062b38ecc73
BLAKE2b-256 9859a98e237ac756afdb4d974ef277d19e546e88f39fb55cf2fc4bf1f11df4b3

See more details on using hashes here.

Provenance

The following attestation bundles were made for distillery_mcp-0.3.2-py3-none-any.whl:

Publisher: pypi-publish.yml on norrietaylor/distillery

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page