Self-hostable legal OS for drafting, reviewing, and managing contracts, with an AI assistant named Luna for research and document analysis.
- Stars
- 284
- Forks
- 24
- Open issues
- 15
- Last commit
- 3 days ago
What is it?
CaseCite is a self-hosted legal research platform built around retrieval-augmented generation. A firm uploads its documents, which are indexed with hybrid vector and keyword search, and then asks questions in a chat where answers carry inline citations back to the source passages. Deep research breaks a question into sub-questions the user can edit before running, and verifies quotes against the text they came from.
Beyond chat, the app covers contract review (single analysis, clause-by-clause comparison of up to four contracts, redline export), tabular review of many documents with per-cell source quotes, drafting from selected reference documents, and matter-based workspaces with sharing and an audit trail. Case-law tools, judge analytics and a citation check run against CourtListener, which requires a free API token for the citation check.
Documents, the search index and chat history stay on the operator's servers, while AI features send questions and relevant text to the OpenAI, Anthropic, Gemini, Voyage or Cohere endpoints the operator configures. Deployment is via Docker Compose with bundled Postgres, Redis and Caddy.
Key features
- 01Chat over firm documents with hybrid retrieval and inline source citations
- 02Deep research with editable sub-question plans and quote verification
- 03Contract analysis, clause-by-clause comparison and redline export
- 04Tabular review of many documents with source-linked cells and Excel/CSV export
- 05Matter workspaces with sharing, and Word add-in support
- 06Case-law lookup, judge analytics and citation check via CourtListener
Use cases
- A law firm that wants to query its own precedent and matter documents without sending them to a third-party SaaS
- Reviewing hundreds of vendor or lease contracts in one table with cited values
- Drafting agreements grounded in selected reference documents
- Running repeatable review workflows over a set of matter documents
Quick start
- 1
Clone the repository and enter it
git clone https://github.com/thomasunise/casecite.git && cd casecite - 2
Create .env from the template, then generate and fill in the required secrets
cp .env.example .env - 3
Start the full stack with Docker Compose
docker compose -f docker-compose.prod.yml up -d - 4
Open https://$DOMAIN in your browser and register the first admin account using REGISTRATION_BOOTSTRAP_TOKEN
Things to know
- Setup is multi-step and requires generating several secrets and configuring full-disk encryption on the host yourself.
- Most features need an AI provider API key, either server-wide or saved by each user.
- Localhost trials show a browser certificate warning from Caddy's self-signed CA.
- The iManage and NetDocuments connectors are experimental and disabled unless EXPERIMENTAL_CONNECTORS is set to true.
In collections
Topics
FAQ
- What is casecite?
- Self-hosted legal research platform that lets law firms query their own documents with RAG, check citations and review contracts. CaseCite is a self-hosted legal research platform built around retrieval-augmented generation. A firm uploads its documents, which are indexed with hybrid vector and keyword search, and then asks questions in a chat where answers carry inline citations back to the source passages. Deep research breaks a question into sub-questions the user can edit before running, and verifies quotes against the text they came from.
- Is casecite free to use? What license does it have?
- casecite is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is casecite still maintained?
- Actively maintained. The last commit to casecite was on Nov 5, 2026.
- What can I use casecite for?
- A law firm that wants to query its own precedent and matter documents without sending them to a third-party SaaS Reviewing hundreds of vendor or lease contracts in one table with cited values Drafting agreements grounded in selected reference documents Running repeatable review workflows over a set of matter documents
- How do I install casecite?
- Clone the repository and enter it: git clone https://github.com/thomasunise/casecite.git && cd casecite Create .env from the template, then generate and fill in the required secrets: cp .env.example .env Start the full stack with Docker Compose: docker compose -f docker-compose.prod.yml up -d Open https://$DOMAIN in your browser and register the first admin account using REGISTRATION_BOOTSTRAP_TOKEN
- Where can I get casecite?
- The source code and installation instructions are on GitHub: https://github.com/thomasunise/casecite
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source legal AI platform for document review, drafting, and legal research, built on Next.js, Express, and Supabase.
A no-code RAG server that indexes a folder of documents into one of 8 vector databases and keeps answers in sync as files change.
A self-hosted RAG platform that lets you upload documents and chat with them using LLMs, built on Langflow, Docling, and OpenSearch.
A local-first AI office workbench that turns one request into editable PPTX, DOCX, XLSX and HTML files, using your own model keys.
Self-hosted personal AI agent with a built-in WebUI, memory, tools, MCP support, sub-agents and scheduled automations, using local or cloud LLMs.