Relevant jobs
AI / Algorithm Engineer
Full-stack / Indie Developer
Backend Engineer
Data Analyst / Data Engineer
knowhereOntos-AI/knowhere
Turns messy documents into structured knowledge that AI agents can directly retrieve and reason over,…
No ratings yet
Rate this skill
Stars3.5k
Forks331
Watchers3.5k
Open Issues40
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/Ontos-AI/knowhere.git
OverviewOverview
Key Features
Turns messy documents into structured knowledge that AI agents can directly retrieve and reason over, solving the problems of difficult document parsing, messy chunking, and inaccurate retrieval in RAG pipelines. Key capabilities include: 1. Document intelligence parsing: parses unstructured documents such as PDFs and scans into structured content with hierarchy and semantics, preserving heading, paragraph, and table relationships to reduce semantic breaks during retrieval; 2. RAG pipeline orchestration: provides a complete chain from document ingestion, chunking, and vectorization to retrieval, so agents can answer directly from retrieval results without assembling each stage manually; 3. Multi-agent collaboration framework: supports multiple agents dividing work across document understanding, extraction, and verification, breaking complex document processing into parallel and reviewable steps; 4. Agent integration adapters: offers skill integration for coding agents such as Claude Code, Codex, and Cursor, letting developers invoke document processing capabilities within their existing coding environment. 2. Use Cases: enterprise document parsing and structuring, RAG knowledge base construction, multi-agent document processing pipeline setup, vector retrieval data preparation. 3. Target Roles: AI / Algorithm Engineer, Backend Developer, Data Analyst / Data Engineer, Full-stack / Indie Developer.
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 303 |
|---|---|
| Data source | GitHub |
| Repository | Ontos-AI/knowhere |
| Category | AI & Agent Skills / Document Intelligence & RAG Engineering |
| Primary language | Python |
| License | Apache License 2.0 |
| Default branch | main |
| GitHub repository ID | 1225188401 |
| Node ID | R_kgDOSQbkMQ |
| Rank | #247 (position within the source ranking) |
| Site-wide popularity rank | #351 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
Still collecting
First record taken on 2026-09-23. Two days of data are needed before a trend line can be drawn.
TimelineTimeline
Repository created2026-04-30 03:13:106 months ago
Data last updated2026-10-26 11:55:5321 days ago
Last commit2026-09-23 13:18:261 months ago
CommitLatest commit
Committed by suguanYang. Update Category: Bug Fixes & Stability Improvements. Commit details: Merge pull request #459 from Ontos-AI/fix/wangbinqi/source-content-deduplication. This update resolves known runtime errors and enhances system reliability.