Skillget

distillery

mcp
Security Audit
Warn
Health Warn
  • License — License: NOASSERTION
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool serves as a team knowledge base and capture system. It ingests meeting notes, URLs, and session context, stores them locally in a DuckDB vector database, and retrieves the information via natural language search and conversational synthesis commands.

Security Assessment
Overall risk: Medium. The application accesses sensitive data by design, specifically reading developer session context, Slack feeds, and URLs to generate vector embeddings. It makes network requests to fetch external bookmarks, monitor external RSS/GitHub feeds, and can operate as an HTTP service utilizing GitHub OAuth. The automated code scan of 12 files found no dangerous patterns, no hardcoded secrets, and the project requests no dangerous system permissions. It does not appear to execute arbitrary shell commands.

Quality Assessment
The project appears to be in active development, with its last push occurring today. However, it currently has very low community visibility, with only 5 GitHub stars, indicating that it has not been broadly tested or reviewed by the public. It claims an Apache 2.0 license in the documentation, though the automated repository metadata flag is unverified (NOASSERTION). While the code is clean and documented, the lack of community adoption means unknown edge cases or vulnerabilities might be present.

Verdict
Use with caution — the code is clean and permissions are safe, but the tool ingests sensitive team data while still being an early-stage, low-visibility project lacking broad community validation.
SUMMARY

Team knowledge evaporates daily — pairing sessions, debugging context, architectural rationale lost to Slack. Distillery captures it at the point of creation, connects it into a living graph, and surfaces it conversationally. It monitors feeds, tracks what matters to your projects, and alerts you before you know to ask. A team brain that learns.

README.md

Distillery

Distillery

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

Documentation · Skills · Quick Start · Roadmap · Slides

PyPI version 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 10 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
/setup Onboarding wizard for MCP connectivity and config /setup

Quick Start

Plugin Install (Recommended)

claude plugin marketplace add norrietaylor/distillery
claude plugin install distillery

Then run the onboarding wizard in Claude Code:

/setup

This verifies MCP connectivity, detects your transport, and configures auto-poll for ambient intelligence.

Demo Server: The plugin defaults to distillery-mcp.fly.dev, which is a demo server for evaluation only. Do not store sensitive or confidential data. For production use, deploy your own instance or run locally.

Local Setup

git clone https://github.com/norrietaylor/distillery.git
cd distillery
pip install -e .

See the Local Setup Guide for configuration and MCP server connection.

Development

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.

Reviews (0)

No results found