Samuraizer
Local MCP server for meeting transcripts, summaries, action items & decisions — no cloud.
Open source Open in the app JSON README (API)
About
Local MCP server for meeting transcripts, summaries, action items & decisions — no cloud.
Details
- Kind
- MCP servers
- Topic
- Productivity
- Publisher
- uladzkha
- Origin
- official
- Category
- ferramentas
- Transport
- local
- Version
- 0.1.7
- Last push
- 2026-08-28T18:38:55Z
- Repository state
- ativo
- Language
- TypeScript
- License
- MIT
- Added
- 2026-08-29 03:02:18
- Updated
- 2026-09-07 16:04:09
- Origin id
io.github.UladzKha/samuraizer
README
# Samuraizer Turn meeting recordings into transcripts, summaries, action items, and decisions — entirely on your machine. No cloud, no subscriptions, no data leaving your network. > **Reference implementation.** Samuraizer is the reference implementation of the [memnex specification](https://github.com/UladzKha/memnex) — an open standard for portable meeting outputs (transcripts, summaries, action items, decisions). All outputs conform to memnex v0.2, including a full provenance chain. ## Why Samuraizer - **Fully local.** Your recordings never leave your machine. - **CLI-first.** Scriptable, automatable, integrates with cron, Git hooks, Obsidian workflows. - **Resumable.** Crashed mid-pipeline? Re-run picks up where it left off. - **Fast.** LLM stages (summary, action items, decisions) run in parallel, cutting total time by ~2.3×. - **Model-agnostic.** Works with any Ollama-compatible LLM — pick what fits your hardware. - **Free.** No subscriptions, no per-minute pricing. ## Portable output with memnex Samuraizer writes meeting results in the portable [memnex v0.2](https://github.com/UladzKha/memnex) format. This lets another meeting app, local AI agent, or MCP server consume the same transcript, summary, action items, decisions, and provenance without learning a Samuraizer-specific JSON shape. To verify a memnex document in under a minute, follow the [memnex quickstart](https://github.com/UladzKha/memnex#try-it-in-60-seconds). It installs the validator and checks a real v0.2 example end to end. ## 📦 Packages This is a monorepo. Samuraizer is published as two npm packages, each with its own README and changelog: | Package | What it does | Docs | |---|---|---| | [`@samuraizer/cli`](https://www.npmjs.com/package/@samuraizer/cli) | The meeting-processing CLI — install, configure, and run the local pipeline. **Start here.** | [packages/cli/README.md](./packages/cli/README.md) | | [`@samuraizer/mcp-server`](https://www.npmjs.com/package/@samuraizer/mcp-server) | Companion [Model Context Protocol](https://modelcontextprotocol.io/) server. Lets AI agents (Claude Desktop, Claude Code, MCP Inspector) query your processed meetings and trigger the pipeline. | [packages/mcp-server/README.md](./packages/mcp-server/README.md) | ## 🏛 Project status - **memnex specification: v0.2** — see [the memnex repo](https://github.com/UladzKha/memnex) for the schema, conformance suite, and governance documents. - **Schemastore registered.** memnex is in the [universal JSON Schema catalog](https://github.com/SchemaStore/schemastore) (PR [#5676](https://github.com/SchemaStore/schemastore/pull/5676)). `*.memnex.json` and `meeting-output.json` files get IDE autocomplete and validation by default in VS Code, JetBrains IDEs, Neovim, Sublime, and other editors with language-server support. - **Roadmap:** local diarization, cryptographic signing UX, accessibility (WebVTT subtitles), and the path to memnex v1.0 are funded milestones. ## 🤝 Contributing Samuraizer follows a BDFL bootstrap model — see the memnex [GOVERNANCE.md](https://github.com/UladzKha/memnex/blob/main/GOVERNANCE.md) for the broader project's governance model, which Samuraizer mirrors. Bug reports and feature discussions are welcome in [GitHub Issues](https://github.com/UladzKha/samuraizer-cli/issues). ## 📝 Changelogs - [`packages/cli/CHANGELOG.md`](./packages/cli/CHANGELOG.md) - [`packages/mcp-server/CHANGELOG.md`](./packages/mcp-server/CHANGELOG.md) ## 📄 License MIT — see [LICENSE](./LICENSE).