open-legal-products/mike

OSS Legal AI Platform

Mike – Open‑Source Legal AI Platform

What it is — Mike (MikeOSS) is a full‑stack, open‑source application that lets lawyers and other professionals interact with AI‑powered tools for legal work. It bundles a web UI, an API server, document storage, and a Microsoft Word add‑in, all wired together so you can chat with documents, get draft suggestions, and run structured review workflows.

Key components

  • Frontend – a Next.js web app that provides the chat UI, project/folder navigation, and settings.
  • Backend – an Express server handling authentication (via Supabase), document processing, and calls to LLM providers (Anthropic, Gemini, OpenAI) or a local Ollama model.
  • Data layer – Supabase Postgres for user and metadata storage; Cloudflare‑compatible R2 (RustFS) for binary document blobs.
  • Word add‑in – a beta task‑pane extension that brings the same assistant experience inside Microsoft Word.
  • Workflows – reusable “assistant” and “tabular‑review” pipelines defined in a companion repo (mike‑workflows).

How it works

  1. Users sign up (or SSO via Google) and upload legal documents.
  2. The UI lets you chat with a document, ask for case‑law citations (via CourtListener), or request draft edits.
  3. The backend sends the request to a chosen LLM (or a local Ollama model) and returns the AI‑generated response.
  4. Results can be applied as edits, saved, or exported. Tabular‑review workflows let you run the same checks across many documents.
  5. Optional connectors let Mike read/write Gmail/Calendar events, with explicit user consent for every action.

Getting started

  • Clone the repo and copy the .env.example files.
  • Generate two random 32‑byte secrets (DOWNLOAD_SIGNING_SECRET and USER_API_KEYS_ENCRYPTION_SECRET).
  • Add an Anthropic, Gemini, OpenAI, or Ollama key.
  • Run docker compose up --build – this starts the web app, API, Supabase, and object storage locally.
  • Open http://localhost:3000 to create an account and explore.

Privacy & telemetry Mike reports only anonymised error data to Sentry; document content and user IDs are never sent. You can disable it with SENTRY_DISABLED=true or point it at your own Sentry DSN.

Who it’s for

  • Law firms or solo practitioners who want a self‑hosted AI assistant without sending confidential documents to third‑party SaaS.
  • Developers building custom legal‑AI workflows, since the platform is open‑source and extensible via the mike‑workflows repo.

License

  • AGPL‑3.0 for the code; bundled contract templates keep their original licenses.

All details are taken directly from the repository’s README.

Related

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.

  • Project
    FuturixAI-and-Quantum-Works/Prism-Legal-OS

    An open-source legal operating system for drafting, reviewing, and managing contracts with an integrated AI assistant for document intelligence.

  • Project
    router-for-me/CLIProxyAPI

    CLI Proxy API is an open‑source proxy server that presents a unified OpenAI‑compatible API for many LLM providers (OpenAI, Gemini, Claude, Grok, Kimi, Meta, etc.). It handles OAuth logins, multi‑account load‑balancing, streaming, function calls, and multimodal inputs, and offers optional dashboards for usage and cost tracking. Ideal for developers with multiple AI subscriptions who want a single local endpoint for their CLI tools.

  • Project
    Narcooo/inkos

    InkOS is a Node‑based AI authoring platform for novels, short stories, scripts, interactive worlds, and translation. It provides a unified Studio web UI, terminal UI, and CLI that share a pi‑agent harness: a language model proposes actions and InkOS executes them deterministically, managing story‑wide memory, chapter snapshots, and structured state. Built‑in Skills cover writing, reviewing, cover‑image generation, and play‑world creation. It works with many LLM providers (Moonshot Kimi, Claude, Gemini, DeepSeek, etc.) via the kkaiapi aggregation layer, supports multi‑model routing, and can be called as an OpenClaw skill. Installation is a single `npm i -g @actalk/inkos` and the workflow follows create → write → review → revise → export, with robust configuration via Studio UI or environment variables.

  • Project
    onyx-dot-app/onyx-foss

    Onyx is a self-hosted knowledge and context layer that connects to over 50 applications to provide AI agents with secure, relevant access to your organization's internal data.