{"adoption": {"forks": 709, "observed_at": "2026-08-28T04:09:56.392979+00:00", "stars": 7172}, "canonical_url": "https://ross.abutalabs.com/products/unstract", "card": {"archived": false, "artifact_type": "application", "description": "LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows", "domain": ["artificial-intelligence", "large-language-models", "pdf", "developer-tools"], "enriched": true, "function": ["ocr", "etl", "rag", "prompt-engineering", "mcp", "llm-inference", "data-science", "api-framework", "self-hosted"], "health_score": 100, "homepage": "https://unstract.com", "language": "Python", "license": "AGPL-3.0", "license_family": "copyleft", "maturity": "active", "member_repos": ["Zipstack/unstract"], "name": "Zipstack/unstract", "platform": ["python", "self-hosted", "cloud"], "pushed_at": "2026-08-26T16:41:01+00:00", "repo": "Zipstack/unstract", "stars": 7172, "tags": ["intelligent-document-processing", "idp", "document-ai", "structured-output", "json-extraction", "llm-challenge", "prompt-studio", "etl-pipelines", "agentic-ai", "pdf-extraction", "data-engineering", "automation", "docker", "web-server"], "topics": ["ai-agents", "data-engineering", "document-ai", "generative-ai", "idp", "json-extraction", "llm", "mcp-server", "ocr", "pdf-extraction", "prompt-engineering", "structured-output"], "urls": [], "use_cases": ["extract structured data from pdfs with llm", "parse invoices into json automatically", "build an etl pipeline for unstructured documents", "deploy document extraction as an api", "process bank statements without templates", "add document extraction to ai agents via mcp", "reduce llm token costs for document parsing", "automate accounts payable document processing"], "what_it_is": "Unstract is an open-source, LLM-driven platform that extracts structured JSON data from unstructured documents such as PDFs, images, and scans using natural-language prompts. It supports deployment as APIs, ETL pipelines, and an MCP server, with features like dual-LLM validation (LLMChallenge) and token-saving extraction modes.", "when_to_avoid": ["you only need simple OCR text extraction without structured output", "you want a lightweight library to embed in code rather than a platform to deploy", "AGPL-3.0 licensing is incompatible with your usage", "your documents are already structured (CSV, JSON) and need no LLM parsing"], "when_to_choose": ["you need production-grade extraction from varied document formats without training or templates", "you want API or ETL deployment of document extraction workflows", "hallucination control matters - dual-LLM consensus validation is valuable", "you need connectors to file systems and databases for bulk document processing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/unstract", "repo": "Zipstack/unstract", "role": "main", "score": 88}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:56.392979+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:39:56.574411+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "502c7b6ca6c8eaebfc38c0d1300936935673a70646d903ba97ba3733a425522b", "fetched_at": "2026-08-28T04:09:56.392979+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zipstack/unstract"}, {"content_hash": "7523b9e8d5cba363122399934808d13906c0cf80567477446e9027bdfef2000d", "fetched_at": "2026-08-29T08:35:20.746887+00:00", "kind": "homepage", "missing": false, "url": "https://unstract.com"}, {"content_hash": "3b8e138d44cc8952b6c6dc5474babd95ac9d8587955b19e246a449b0521b5acc", "fetched_at": "2026-08-29T08:35:20.758098+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstract.com/"}, {"content_hash": "19b4c6be2d27cd28af823dd7fd533eb3ac2154f647c5893c071d8a55de7c2232", "fetched_at": "2026-08-29T08:35:20.756023+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/pricing"}, {"content_hash": "c4a68faa5aefa6656c76d86c99cfc7fcb0da377d0627eafded9bcea0d9af8a33", "fetched_at": "2026-08-29T08:35:20.759777+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/unstract-editions"}, {"content_hash": "27cacae9dbce21f637ce76acd3be51e658c7e5309f58e5ff03b667b2c3178fdb", "fetched_at": "2026-08-29T08:35:20.761948+00:00", "kind": "site_page", "missing": false, "url": "https://unstract.com/ai-accounts-payable-procurement-document-processing/contract-pricing-proposal-data-extraction"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 66, "rhythm": 86}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 924, "days_push": 7, "days_rel": 13, "gap_med": 0.0, "n_releases_24m": 415}, "score": 88, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}