{ "markdown": "

\n \n \n \n \"Distillery\"\n \n

\n\n

Distillery

\n\n\n\n

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

\n\n

\n Documentation ·\n Skills ·\n Quick Start ·\n Roadmap ·\n Slides\n

\n\n

\n \"PyPI\n \"PyPI\n \"License\"\n \"Python\n

\n\n---\n## What is Distillery?\n\nDistillery 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.\n\nDistillery captures the highest-value transformation — from noise to signal — and makes it a tool the whole team can use.\n\n> **Full documentation:** [norrietaylor.github.io/distillery](https://norrietaylor.github.io/distillery/)\n\n

\n \"Distillery\n

\n\n## Skills\n\nDistillery provides 15 Claude Code slash commands:\n\n| Skill | Purpose | Example |\n|-------|---------|---------|\n| `/distill` | Capture session knowledge with dedup detection | `/distill \"We decided to use DuckDB for local storage\"` |\n| `/recall` | Semantic search with provenance | `/recall distributed caching strategies` |\n| `/pour` | Multi-entry synthesis with citations | `/pour how does our auth system work?` |\n| `/compass` | Contrast internal knowledge vs. ambient intelligence for a directional assessment | `/compass our caching strategy` |\n| `/bookmark` | Store URLs with auto-generated summaries | `/bookmark https://example.com/article #caching` |\n| `/minutes` | Meeting notes with append updates | `/minutes --update standup-2026-03-22` |\n| `/classify` | Classify entries and triage review queue | `/classify --inbox` |\n| `/watch` | Manage monitored feed sources | `/watch add github:duckdb/duckdb` |\n| `/radar` | Ambient feed digest with source suggestions | `/radar --days 7` |\n| `/tune` | Adjust feed relevance thresholds | `/tune relevance 0.4` |\n| `/digest` | Team activity summary from internal entries | `/digest --days 7 --project myapp` |\n| `/gh-sync` | Sync GitHub issues/PRs into the knowledge base | `/gh-sync owner/repo --issues` |\n| `/investigate` | Deep context builder with relationship traversal | `/investigate distributed caching` |\n| `/briefing` | Team knowledge dashboard with metrics | `/briefing --days 7` |\n| `/setup` | Onboarding wizard for MCP connectivity and config | `/setup` |\n\n## Quick Start\n\n### Step 1: Install the Plugin\n\n```bash\nclaude plugin marketplace add norrietaylor/distillery\nclaude plugin install distillery\n```\n\nThis installs all 15 skills. The plugin **does not configure an MCP server automatically** — run `/setup` (below) to add one. The recommended setup runs **locally** via `uvx --from 'distillery-mcp[fastembed]>=0.6.0' distillery-mcp` — a private, self-contained knowledge base on your machine, with on-device `fastembed` embeddings (no API key required). Requires Python 3.11+ and [`uv`](https://docs.astral.sh/uv/) (install: `curl -LsSf https://astral.sh/uv/install.sh | sh`).\n\n### Step 2 (Optional): Use Jina or OpenAI Instead\n\nThe default `fastembed` provider runs offline with no API key. If you'd rather use a hosted embedding service, set `DISTILLERY_EMBEDDING_PROVIDER` and provide the matching API key:\n\n```bash\n# Jina (free tier at jina.ai)\nexport DISTILLERY_EMBEDDING_PROVIDER=jina\nexport JINA_API_KEY=jina_...\n\n# Or OpenAI\nexport DISTILLERY_EMBEDDING_PROVIDER=openai\nexport OPENAI_API_KEY=sk-...\n```\n\n`uvx` inherits these from your shell environment. See [`distillery.yaml.example`](distillery.yaml.example) for the full provider configuration block (including Option C for fastembed model selection).\n\nRestart Claude Code and run the onboarding wizard:\n\n```text\n/setup\n```\n\n### Try the Hosted Demo (Opt-In)\n\nWant to evaluate without installing anything locally? Configure the hosted demo at `distillery-mcp.fly.dev` instead of a local server:\n\n```bash\nclaude mcp add distillery --scope user --transport http --url https://distillery-mcp.fly.dev/mcp\n```\n\n> **Demo Server:** `distillery-mcp.fly.dev` is for evaluation only. Do not store sensitive or confidential data.\n\nSee the [Local Setup Guide](https://norrietaylor.github.io/distillery/getting-started/local-setup/) for full configuration options, or [deploy your own instance](https://norrietaylor.github.io/distillery/team/deployment/) for team use.\n\n## Development\n\n```bash\nuv pip install -e \".[dev]\"\n# or\npip install -e \".[dev]\"\npytest # run tests\nmypy --strict src/distillery/ # type check\nruff check src/ tests/ # lint\n```\n\nSee [Contributing](https://norrietaylor.github.io/distillery/contributing/) for the full guide.\n\n## License\n\nApache 2.0 — see [LICENSE](LICENSE) for details.\n", "bytes": 6423, "sha": "8749851af5d5f7930bab9bfbccd57a238202a8050ab3f14a1814f09a9d5d437a", "repo_slug": "norrietaylor/distillery", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_norrietaylor_distillery_mcp_ad7ef653/readme" }