Harvey raised 500M for legal AI, I built the same and open sourced it
Repository · https://github.com/thomasunise/casecite
First seen by Oriel on .
AI summary
CaseCite is a source-available, self-hosted legal RAG platform combining private document research, contract analysis, drafting, and CourtListener-powered case-law tools on user-controlled infrastructure.
- Its RAG pipeline uses semantic retrieval with BM25 rescoring and returns inline citations to source documents.
- AI requests send questions and relevant text to configured providers, but self-hosted OpenAI-compatible chat and embedding endpoints can keep document text on-network.
- The Docker stack bundles Postgres, Redis, and Caddy; originals and credentials use AES-256-GCM, while derived text requires host-level disk encryption.
- CourtListener is the sole case-law source; citation checking requires a token, and anonymous access makes other research features impractical under real load.
- Elastic License 2.0 permits internal self-hosting and modification, but prohibits offering CaseCite to third parties as a hosted or managed service.
#legal rag #self-hosting #document analysis #courtlistener
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Points
Score reported by the source.
- Hacker News: 47, latest observation
Comments
Comment count reported by the source.
- Hacker News: 8, latest observation
Aliases
| Source | External ID | URL |
|---|---|---|
| Hacker News | 50273623 | https://github.com/thomasunise/casecite Read discussion |