Open Source Hebbia Alternatives
A curated collection of the 2 best open source alternatives to Hebbia.
The best open source alternative to Hebbia is Mike. If that doesn't suit you, we've compiled a ranked list of other open source Hebbia alternatives to help you find a suitable replacement. Other interesting open source alternative to Hebbia is Corpus.
Hebbia alternatives are mainly Legal but may also be AI Interaction & Interfaces. Browse these if you want a narrower list of alternatives or looking for a specific functionality of Hebbia.
An open source legal AI platform for document review, drafting and case law research, aimed at firms that self-host.
Mike, published as MikeOSS, is a legal AI platform covering document review, drafting and legal research. It brings the assistant to the matter rather than the other way around, letting a firm keep documents, matters and models inside infrastructure it operates.
The application combines a Next.js frontend, an Express backend, Supabase for authentication and Postgres, and Cloudflare R2-compatible object storage. Language models come from Anthropic, Gemini or OpenAI through an API key, or run locally through Ollama for teams that prefer nothing leaves the building.
The feature set follows the shape of legal work.
- Document chat: ask questions across open matters and the document library.
- Review workflows: reusable assistant and tabular-review workflows suggest edits you can apply.
- Citation checking: verify citations and research US case law through CourtListener.
- Word add-in: a beta task pane brings the assistant into Microsoft Word.
- Project structure: projects, folders and a shared library organize what a matter accumulates.
A bundled Docker Compose stack runs Mike, Supabase, RustFS object storage and local email capture without any managed service, so a first look costs one command. Those bundled credentials are for local development only, and a real deployment starts by generating your own signing and encryption secrets.
Document question answering that returns cited answers from uploaded PDFs and web pages, for teams reading across large document sets.
Corpus takes PDFs and web pages, answers questions about them in plain language, and links each answer back to the passage it came from. Documents group into workspaces and document sets, so a research pile stays separated by project instead of merging into one searchable heap.
The backend is FastAPI with PostgreSQL as the primary database, Elasticsearch for full-text search, RabbitMQ as the message queue, Temporal for workflow orchestration, Redis for caching and S3 for document storage. The frontend is React with Vite. A Docker Compose file starts the whole stack, including a LocalStack S3 and the Temporal web interface.
The product sits on a handful of moving parts.
- Citations: every answer carries links back into the source text.
- Cross-correlation: the same question can be compared across several documents at once.
- Workflows: Temporal runs automated workflows whose output can be reviewed and exported.
- Model choice: OpenAI, Anthropic, Google and xAI models are supported for answering.
- Embeddings: OpenAI and Voyage AI both work for the vector side.
Running everything in containers needs only Docker and Docker Compose, while running the services directly needs Python 3.11 or newer with Poetry and Alembic, plus Node.js 20 for the frontend. Video walkthroughs in the repository cover getting started, cross-correlation and workflow creation, and the license is AGPL-3.0.
