Knowhere is a document-processing memory layer that turns unstructured PDFs, office files, images, tables, Markdown, and text into structured, navigable information for AI agents. It supports agentic RAG and other LLM workflows by preserving context while parsing documents, extracting hierarchies, and building graphs. The catalogue instruction helps coding agents use Knowhere.
Borrowing it
Nothing to install: this file belongs to Ontos-AI/knowhere. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Ontos-AI/knowhere/main/AGENTS.mdgit clone --depth 1 https://github.com/Ontos-AI/knowhereWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/ontos-ai/knowhere/agents-md)<a href="https://agentmods.dev/instructions/ontos-ai/knowhere/agents-md"><img src="https://agentmods.dev/badge/instructions/ontos-ai/knowhere/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/ontos-ai/knowhere/agents-md"><img src="https://agentmods.dev/badge/instructions/ontos-ai/knowhere/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.07477 | $0.07477 |
| Opus 5.5 | $0.02991 | $0.02991 |
| Sonnet 5.5 | $0.01495 | $0.01495 |
| Haiku 4.5 | $0.00748 | $0.00748 |
Grade A, and why
knowhere AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
Branch Naming
Codex agents and contributors must create branches with this format:
<type>/<user>/<description>
typeshould be lowercase and should normally be one of:feat,fix,refactor,chore,docs,test,perf,ci,build, orrevert.usershould identify the human owner of the work, usually their GitHub username. Do not use a generic tool name such ascodex.descriptionshould be short, lowercase, and kebab-case.
Examples:
feat/alice/add-document-preview
fix/bob/chunk-position-range
refactor/chris/extract-chunk-converter
Project Structure
knowhereapi-main/
├── apps/
│ ├── api/ # FastAPI REST API (port 5005)
│ │ ├── app/
│ │ │ ├── api/v1/routes/ # Endpoint handlers
│ │ │ ├── services/ # Business logic (auth, ingestion, billing)
│ │ │ └── repositories/ # Data access layer
│ │ └── main.py # Entrypoint, runs migrations on start
│ ├── worker/ # Celery worker for async document processing
│ │ ├── app/
│ │ │ ├── services/document_parser/ # All parser modules
│ │ │ └── services/workload/ # Celery task handlers
│ │ └── worker.py # Celery entrypoint
│ ├── web/ # Frontend (separate repo: knowhere-dashboard)
│ └── docs/ # Internal documentation
├── packages/
│ └── shared-python/shared/ # Shared library (pip: knowhere-shared)
│ ├── models/database/ # SQLAlchemy ORM models
│ ├── models/schemas/ # Pydantic request/response schemas
│ ├── services/retrieval/ # Core retrieval engine
│ ├── services/chunks/ # DataFrame → ChunkPayload conversion
│ ├── services/ai/ # LLM prompt service & AI client
│ ├── services/http/ # Public URL validation and outbound HTTP
│ ├── services/redis/ # Redis state, key language, and retry policy
│ ├── services/quota/ # Shared token-pool quota primitives
│ └── utils/ # Generic text, chunk, and API helpers
└── deploy/ # Docker Compose & deployment scripts
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · -1 lines · -31 tokens per session 0c3f2072b819
- 2d ago Changed · -13 tokens per session d7fc167a8e7a
- 10d ago Changed · -13 lines · -26 tokens per session b1126e215557
- 27d ago Changed · -10 tokens per session 75ecdfc87380
- 28d ago Changed · +1 tokens per session 474aefb96208
- 1mo ago Changed · +3 lines · +91 tokens per session 62f1234b6bfb
- 1mo ago Changed · -2 tokens per session c2bfdd145902
- 1mo ago Changed · -3 lines · -117 tokens per session ab00b7126148
- 1mo ago Changed · +9 lines · +169 tokens per session c4c601a4b1d3
- 1mo ago First seen · 696 lines · 7,415 tokens per session scan A cbf6fda628bb
knowhere AGENTS.md is an instructions file published in the GitHub repository Ontos-AI/knowhere (3,791 stars, last pushed yesterday), licensed Apache-2.0. It adds 7,477 tokens to every session, about $0.0299 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.