# Open-Source-Legal/OpenContracts

The open document intelligence platform for builders and hackers - DMS for the agentic world

Repository: https://github.com/Open-Source-Legal/OpenContracts
Canonical: https://ross.abutalabs.com/products/opencontracts
Homepage: https://open-source-legal.github.io/OpenContracts/
Language: Python
License: MIT
License Family: permissive
Topics: agent, agentic-ai, etl, etl-pipeline, llm, unstructured-data, vector-database, prompt-engineering, ai, ai-agents
Last push: 2026-08-26T14:11:30+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 84, longevity 100
- inputs: {"age_days": 1409, "days_push": 7, "days_rel": 24, "gap_med": 51, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1451, forks 183 (observed 2026-08-28T04:04:45.824522+00:00)

## What it is
OpenContracts is a self-hosted, MIT-licensed document intelligence platform that turns document repositories into a programmable citation graph with human annotation, structured extraction, and AI agents. It exposes the same corpus through a GraphQL/REST API, an MCP server for AI tools like Claude and Cursor, and a React UI.

## Use cases
- build a searchable knowledge base from PDFs and DOCX files
- extract structured data fields across hundreds of documents with LLMs
- annotate documents by hand and with AI agents
- expose a document corpus to Claude or Cursor via MCP
- run agents that search and answer questions over a document corpus
- self-host a document management system with fine-grained permissions
- fork and version-control shared document corpuses

## When to choose
- you need self-hosted document ingestion, annotation, and LLM-powered extraction in one platform
- you want to give AI agents structured access to a document corpus via MCP or API
- your team needs human-in-the-loop annotation alongside automated extraction
- you need multi-format (PDF/DOCX/text) parsing with a pluggable pipeline

## When to avoid
- you only need simple full-text search without annotation or extraction
- you want a lightweight library to embed in your own app rather than a full platform
- you need a fully managed SaaS with no self-hosting overhead
- your documents are mostly spreadsheets or images rather than text documents

## Facets
- artifact type: application
- maturity: active
- function: rag, vector-database, etl, search-engine, mcp, agent-framework, prompt-engineering, pdf, nlp, api-framework, graphql, web-framework
- domain: artificial-intelligence, large-language-models, pdf, self-hosted, legal, developer-tools
- platform: python, self-hosted, cross-platform
- tags: document-intelligence, document-management, annotation, corpus-management, data-extraction, mcp-server, pydantic-ai, docling, knowledge-base, citation-graph, ai-agents, retrieval-augmented-generation, natural-language-processing, documents, web-server, docker

## Member repositories
- Open-Source-Legal/OpenContracts (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:45.824522+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:35:50.466070+00:00, confidence not recorded.
  - readme: https://github.com/Open-Source-Legal/OpenContracts (fetched 2026-08-28T04:04:45.824522+00:00, sha 61660ef518b3)
  - homepage: https://open-source-legal.github.io/OpenContracts/ (fetched 2026-08-29T11:45:13.304855+00:00, sha bd08a2e3f433)
- Data as of 2026-08-30T08:39:29.467469+00:00.