Picard.law
picard.law
What it is
Picard.law offers open-source legal AI that runs locally and a managed cloud product for production teams. It analyzes legal documents and answers questions with citations tied to the documents, refusing when supporting evidence is missing. Matter workspaces keep uploaded agreements and diligence packs in shared context. Tabular review extracts information across documents and cites each cell to a page and quote; the open-source version also supports Excel export. Picard OSS runs on one machine with documents stored locally, using BM25 full-text search and CARP retrieval on SQLite FTS5. Picard.law Cloud is managed on Azure and uses Neo4j GraphRAG. The maker describes OSS as suited to legal engineers and air-gap use, while Cloud is aimed at production legal AI teams. OSS is single-user and has no built-in authentication. Its plan costs nothing under AGPL for local development and proof of concept, but users pay model API costs with their own keys. The products are available on the web and self-hosted.
Spec sheet
- Product
- Picard.law offers locally run open-source legal AI and a managed cloud product for production teams.Read 8 Oct 2026 · picard.law
- Intended users
- The homepage describes OSS as suited to legal engineers and air-gap use, and Cloud as suited to production legal AI teams.Read 8 Oct 2026 · picard.law
- Deployment
- Picard OSS runs on a single machine with documents stored locally, while Picard.law Cloud is managed on Azure.Read 8 Oct 2026 · picard.law
- Security
- The privacy policy states that cloud data is encrypted at rest with AES-256 and in transit with TLS 1.3, and documents are not used to train AI models.Read 8 Oct 2026 · picard.law
- Support
- The homepage lists [email protected] as the Help Center contact.Read 8 Oct 2026 · picard.law
- Headquarters
- The homepage says the company is based in Dubai and India and serves global LegalOps teams.Read 8 Oct 2026 · picard.law
- Data control
- The privacy policy says users can export or delete their data, and that AI providers do not retain document content after processing.Read 8 Oct 2026 · picard.law
- Document analysis
- The product analyzes legal documents and provides chat answers grounded in citations, with a refusal when evidence is missing.Read 8 Oct 2026 · picard.law
- Founder
- The About page identifies Saurabh as founder and CEO and says Picard.Law was built in 2024.Read 8 Oct 2026 · picard.law
- Integration
- The maker says users can integrate their DMS, but does not name a specific DMS integration on the page.Read 8 Oct 2026 · picard.law
- Local use limit
- Picard OSS is single-user and has no built-in authentication, according to the product comparison on the homepage.Read 8 Oct 2026 · picard.law
- Matter workspaces
- Matter-scoped workspaces let teams upload agreements and diligence packs and keep context across documents.Read 8 Oct 2026 · picard.law
- Search
- Picard OSS uses BM25 full-text search and CARP retrieval on SQLite FTS5, while the cloud version uses Neo4j GraphRAG.Read 8 Oct 2026 · picard.law
- Tabular review
- Tabular review extracts information across documents and cites each cell to a page and quote; the OSS version includes Excel export.Read 8 Oct 2026 · picard.law
Plans and prices
Strong points and limits
Strong points
- Answers legal questions with document citations
- Refuses answers when evidence is missing
- Tabular review cites each cell to page and quote
- OSS stores documents locally
- Cloud data encrypted at rest and in transit
Limits
- OSS is single-user
- OSS has no built-in authentication
- Users pay model API costs with their own keys
Who it suits
Picard OSS suits legal engineers and air-gap use, while the cloud option is presented for production legal AI teams. Teams should account for the OSS single-user limit and lack of built-in authentication.
Verdict
Picard.law offers local open-source and managed cloud deployment, with document-grounded answers and review tools.
Where Specifiction places it
- Legal Knowledge Management Software#17 of 237.2
- AI Legal Research Software#28 of 327.2