CaseCite
Self-hosted legal RAG platform for research, contract review, and document analysis.
Private AI-powered caselaw research, bulk contract review, and matter management on your infrastructure.
CaseCite is an open-source, self-hosted platform designed for legal professionals to research caselaw and analyze documents on infrastructure they control. It suits law firms and legal teams wanting to keep data internal while utilizing bring-your-own-key AI models.
What it is
The platform combines nine legal tools under one login, featuring hybrid search retrieval, deep research plans, OCR-backed document ingestion, and multi-contract tabular reviews. It integrates with CourtListener for case law analytics and citation checks while maintaining isolated matter workspaces.
Who it's for
It suits self-hosted legal tech administrators and tech-forward firms needing private document and contract analysis. It does not suit teams without the technical capability to manage a Dockerized deployment and BYOK AI infrastructure.
Key features
Hybrid Search Retrieval
Combines vector search and full-corpus keyword indexes via rank fusion with inline citation checks.
Tabular Contract Review
Analyze hundreds of contracts at once into a matrix with cell overrides and quote highlights.
Multi-Step Workflows
Automate review, extraction, and drafting processes as ordered background jobs with approval gates.
CourtListener Integration
Access case views, judge intelligence, oral arguments, and citation checks directly within the platform.
Configurable Practice Profile
Define firm practice specifics that automatically ride along as standing context for reviews and drafts.
Up and running in 3 steps
Our honest verdict
What's great
- Complete data sovereignty with all documents, indexes, and chat histories stored on your own infrastructure.
- Brings nine distinct legal tools, from deep research to tabular contract review, into a single login workspace.
- Offers robust contract comparison tools that export structured redlines, drafts, and multi-sheet spreadsheets.
- Provides bring-your-own-key flexibility with support for local OpenAI-compatible endpoints to keep data off third-party servers.
Where it falls short
- Requires technical capability to deploy and manage Docker, Docker Compose, and environment secrets.
- Running proprietary AI models or self-hosted embedding servers incurs ongoing operational and API costs.
- Some document connectors like iManage and NetDocuments are experimental and untested against live tenants.
- Citation checks flag negative-treatment language but do not serve as a complete substitute for traditional citators.
Pricing & license
Free under the Apache-2.0 license, with commercial support and private installs available from the maintainer. The only direct financial costs are for the infrastructure and AI API keys you consume.
Open remote AI-training roles
876 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
Are my firm's documents sent to CaseCite maintainers?
No. Documents, search indexes, and chat histories are stored exclusively on your own servers, and there is no telemetry.
Can I keep document text entirely off third-party AI APIs?
Yes, by configuring both the chat and embedding base URLs to point to OpenAI-compatible servers hosted on your own network.
Does CaseCite replace a traditional citator like KeyCite?
No, the citation check scans citing opinions for negative-treatment language as a research aid, not as a legal substitute.
