{"adoption": {"forks": 292, "observed_at": "2026-08-28T04:07:09.279664+00:00", "stars": 2673}, "canonical_url": "https://ross.abutalabs.com/products/knowhere", "card": {"archived": false, "artifact_type": "service", "description": "Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.", "domain": ["artificial-intelligence", "pdf", "developer-tools", "apis"], "enriched": true, "function": ["parser", "rag", "etl", "pdf", "ocr", "mcp", "sdk", "search-engine"], "health_score": 100, "homepage": "https://knowhereto.ai", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["Ontos-AI/knowhere"], "name": "Ontos-AI/knowhere", "platform": ["python", "self-hosted", "cli"], "pushed_at": "2026-08-26T02:54:17+00:00", "repo": "Ontos-AI/knowhere", "stars": 2673, "tags": ["chunking-as-a-service", "document-parsing", "agentic-rag", "document-intelligence", "vectorless-rag", "hierarchical-chunking", "mcp-server", "rest-api", "retrieval-augmented-generation", "ai-agents", "natural-language-processing", "nodejs", "docker", "web-server"], "topics": ["ai-agents", "claude-code", "cursor", "langchain", "rag-pipeline", "skills", "agent-harness", "codex", "document-intelligence", "mutli-agent", "vector-database"], "urls": [], "use_cases": ["parse resumes from pdfs into structured chunks", "prepare messy PDFs for RAG pipelines", "extract tables and layouts from documents for LLMs", "chunk long technical documents with hierarchy preserved", "give AI agents document parsing via MCP", "build agentic RAG over unstructured documents", "convert docx and pptx files into clean JSON chunks"], "what_it_is": "Knowhere is a document ingestion and parsing platform that transforms unstructured documents (PDF, DOCX, XLSX, PPTX, images) into structured, RAG-ready chunks with preserved hierarchy, tables, and metadata. It is offered as a managed REST API (Chunking-as-a-Service), an open-source self-hosted stack, and an MCP server for AI agents like Cursor, Claude Code, and Codex.", "when_to_avoid": ["you only need simple plain-text extraction from clean documents", "you need fully offline processing and cannot use a cloud API or self-host", "your documents are already well-structured markdown or JSON", "you need formats not yet supported like epub or html"], "when_to_choose": ["you need high-quality, structure-preserving chunking for RAG or agents", "you want an MCP server so coding agents can parse and search documents", "you deal with complex PDFs with tables, merged cells, or hundreds of pages", "you want a managed API instead of maintaining your own parsing pipeline"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/knowhere", "repo": "Ontos-AI/knowhere", "role": "main", "score": 81}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.279664+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:18:04.932457+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f2196b9750ce9048a07de2378af41d3268b609fffac16a79abaed727cfce22a", "fetched_at": "2026-08-28T04:07:09.279664+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Ontos-AI/knowhere"}, {"content_hash": "ad2ad83070db9804799b2c39929c69ae83e74288887c3706efb6175fddaff5c5", "fetched_at": "2026-08-29T10:00:38.734124+00:00", "kind": "homepage", "missing": false, "url": "https://knowhereto.ai"}, {"content_hash": "2a2d730299c8aa5ac7fea8366115803fbad41d95cb03cf2a711d0501d018e82d", "fetched_at": "2026-08-29T10:00:38.736635+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/"}, {"content_hash": "b9b54943b8121f47db677b40a48520f35e1378f7766d64095dd5c2d95fb5021c", "fetched_at": "2026-08-29T10:00:38.738292+00:00", "kind": "site_page", "missing": false, "url": "https://docs.knowhereto.ai/mcp"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 8, "rhythm": 99}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 125, "days_push": 7, "days_rel": 8, "gap_med": 0, "n_releases_24m": 38}, "score": 81, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}