knowledge-rag

⭐ Star History

🎯 Why knowledge-rag

Most RAG frameworks fall into one of three traps: (1) they require you to ship your data to a cloud API, (2) they hand you 300 building blocks and 0 opinionated defaults, or (3) they bundle RAG as a 5% feature of a much bigger platform you didn't ask for.

knowledge-rag does one thing well: it is the MCP-native local RAG server that Claude Code, Cursor, Windsurf, VS Code, Cline, Gemini CLI and Zed can search out of the box — with enterprise plumbing (bearer auth, Prometheus metrics, rate limiting, health probes, structured JSON logging, zero-downtime reindex) that no other RAG-focused OSS ships built-in.

🔒 100% local, 0% cloud

Your files never leave the machine. No vendor lock-in, no data-residency headache, no forced cloud dependency. LGPD / GDPR / HIPAA compliant by architecture — because there is nothing to comply about when nothing leaves.

🚀 Zero-friction setup

`pip install knowledge-rag` → restart your MCP client → done. No Docker mandatory. No Ollama required. No separate embedding server. Everything runs in-process via FastEmbed ONNX. Works offline after the first model download.

🛡️ Production-grade OSS

7-pillar quality gate on every PR (35+ automated checks), 9-cell OS×Python CI matrix (Linux + Windows + macOS × 3.11/3.12/3.13), nightly chaos + 50K-iteration soak + mutation testing. 700+ tests. 0 known regressions.

💰 Zero ongoing cost

No token bills. No SaaS tier. No paid features hidden behind a wall. MIT license, forever. Runs on the laptop you already have — GPU optional, CPU works fine with FastEmbed ONNX.

📊 How knowledge-rag compares to other RAG frameworks

We audited 16 popular RAG frameworks and platforms (LlamaIndex, LangChain, ChromaDB, Weaviate, Qdrant, RAGFlow, LightRAG, DSPy, GraphRAG, Haystack, RAG-Anything, kotaemon, txtai, llmware, Dify, open-webui, FastGPT) so you can pick honestly.

Legend: ✅ built-in · 🟡 plugin / paid tier / partial · ❌ not available · ⚠️ license or default concern

🚀 Quick Start (3 minutes, from zero to your first query)

Pick your integration path — knowledge-rag ships the same server through every channel.

Path 1 — Claude Code, Cursor, Windsurf, Cline, VS Code, Gemini CLI, Zed (MCP)

pip install knowledge-rag
knowledge-rag init                    # scaffolds config.yaml + documents/

Drop your PDFs, markdown, code files into `documents/`. Restart your MCP client. Ask it:

search_knowledge("your query")

That's it. First query loads the ONNX embedding model (~200MB, one-off download). Subsequent queries are cached and hit sub-second latency.

Path 2 — HTTP / SSE server (multi-user, air-gapped, load-balanced)

# config.yaml
server:
  transport: "sse"                    # or "streamable-http"
  host: "0.0.0.0"
  port: 8179
  auth:
    bearer_token: "your-secret-token"
  rate_limit:
    enabled: true
    requests_per_minute: 60
  metrics:
    enabled: true
    port: 9179
  logging:
    format: "json"                    # ELK / Loki / Datadog / CloudWatch ready

knowledge-rag --transport sse

• Health probe: `curl http://your-host:8179/health` → 200 + JSON payload
• Prometheus scrape: `http://your-host:9179/metrics`
• MCP dispatcher: authenticated via `Authorization: Bearer your-secret-token`

Path 3 — Docker (models pre-downloaded, air-gapped ready)

docker pull ghcr.io/lyonzin/knowledge-rag:latest
docker run -v $(pwd)/documents:/app/documents -p 8179:8179 ghcr.io/lyonzin/knowledge-rag:latest

Full installation guide with all 5 methods, 8 MCP client configurations, and GPU setup: docs/INSTALLATION.md →

🤖 Ready-to-use skills for AI agents

Installing knowledge-rag gives your agent 13 MCP tools. It does not tell the agent when to use them. That is what the `skills/` folder solves — drop-in behavioural skills for Claude Code, Cursor, Windsurf, Cline, Zed, VS Code Copilot that turn "AI with access to RAG" into "AI that actually uses RAG first".

10 skills, MIT licensed, organized by kind:

Install — pick the shortest path for your machine:

# Option 1 — Via skills.sh (needs Node — one command, zero clone)
npx skills add lyonzin/knowledge-rag

# Option 2 — Via our install.sh (no Node needed; works on Linux/macOS/WSL/Git Bash)
curl -fsSL https://raw.githubusercontent.com/lyonzin/knowledge-rag/master/skills/install.sh | bash

Both restart-Claude-Code and you are done. Option 2 supports `--project`, `--only rag-check-first,rag-cite-sources`, `--dry-run`, `--help`.

For Cursor, Windsurf, Cline and full manual instructions → skills/README.md · Full catalog with skill chains → skills/CATALOG.md

🛠️ The 13 MCP tools your agent gets

Once installed, your AI agent gets these 13 tools automatically:

Full API reference with parameter details, return schemas, examples: docs/API.md →

🏢 Enterprise Features (built-in, zero configuration)

Every RAG framework claims "production-ready." Here is what knowledge-rag ships in the OSS core, verified by regression tests, that competitors either paywall, plugin-ify, or simply don't have.

Security

• Bearer token auth on SSE / HTTP transports — constant-time comparison (`hmac.compare_digest`), RFC 6750 challenge, 401 fenced with `WWW-Authenticate` header
• Path traversal + symlink escape defenses — `validate_path_within` guarding 6 CRUD tools (CWE-22, CWE-59)
• Prompt injection 3-layer defense — sentinel neutralization + provenance fence + `external_source` flag (OWASP LLM01:2025)
• OpenSSF Best Practices badge verified · CodeQL weekly scan · Bandit + Semgrep + Gitleaks + pip-audit on every PR
• PyPI Trusted Publishing via OIDC (zero long-lived tokens in CI)

Observability

• Prometheus `/metrics` endpoint — custom histogram buckets tuned for RAG (p95 ≤ 10ms fast-path targets), 7 canonical metrics via `@instrument` decorator on all 13 tools
• Rate limiting — thread-safe sliding-window counter, per-client RPM + burst, zero overhead when disabled
• Health probes — `GET /health` and `/healthz` returning `{status, version, uptime_seconds, cache}` in front of the auth middleware (probes always succeed)
• Structured JSON logging — opt-in via `server.logging.format: "json"`, one JSON object per record ready for ELK / Loki / Datadog / CloudWatch
• Public benchmark dashboard on GitHub Pages

Scale & performance

• SSE / streamable-http transport — 1 server serves N MCP clients, ChromaDB WAL mode enabled automatically, shared embedding model + query cache
• BM25 inverted-index — 128× faster than linear scan (custom implementation, replaces `rank-bm25`)
• FTS5 SQLite fast-path (opt-in, ADR-002/003/006/008) —

Reliability

• Nightly chaos injection — HuggingFace Hub offline · ONNX zero-byte replay · watchdog crash recovery (3 scenarios in `tests/chaos/`)
• 50 000-iteration soak test — proves no memory leak after 1h of continuous queries (`KNOWLEDGE_RAG_SOAK_ITERATIONS=50000`)
• Mutation testing (mutmut) on `instance_lock` + `preflight` — catches tests that are too weak
• Determinism check — full test suite × 3, catches flakes
• Backwards-compat frozen — 13 MCP tool parameter names guarded by `tests/test_backwards_compat.py` + legacy YAML fixtures (v3.6.0 / v3.7.0) still parse
• API surface AST diff — `check_api_surface.py` blocks any breaking change at PR time
• 9-cell CI matrix — Linux + Windows + macOS × 3.11 + 3.12 + 3.13

💼 Use Cases (real corpora, real teams)

Security Teams — Red / Blue / CTF

Preset: `cybersecurity.yaml` · 8 categories · 200+ routing keywords · 69 query expansions

Ingest MITRE ATT&CK, threat reports, exploit writeups, incident reports. Search from Claude Code with `search_knowledge("privilege escalation windows")` and get instant recall across your entire corpus. Air-gapped — nothing leaves the laptop.

Development Teams — Design Docs, Runbooks, Code

Preset: `developer.yaml` · 9 categories · 150+ routing keywords · 50+ expansions

Replace Confluence hunting. Ingest architecture docs, ADRs, runbooks, code, API specs. Devs ask their AI agent "how do we authenticate the payment service" and get the exact ADR + implementation file citation.

Research Labs — Papers, Notebooks, Datasets

Preset: `research.yaml` · 9 categories · 100+ routing keywords · 40+ expansions

Index arXiv papers, lab notebooks, dataset documentation. Semantic search finds papers by intent, not just keywords — cross-encoder reranking surfaces the actually-relevant one instead of five that share a term.

Enterprise Knowledge Base — Air-gapped, Auditable

Preset: `general.yaml` · blank slate, pure semantic search

Deploy via SSE on a single VM. 40+ users authenticated via bearer token, rate-limited, Prometheus-monitored, `/health` probes wired to your load balancer, JSON logs shipped to Datadog. No cloud calls. Meets LGPD, GDPR, HIPAA data-locality requirements by design.

Verified at scale: production reproduction on a 5 889-doc / 75 016-chunk corpus with concurrent queries during a nuclear rebuild — zero downtime, zero errors (see CHANGELOG v4.8.3).

🏗️ Architecture at a glance

End-to-end view of how MCP clients, the retrieval pipeline, storage, and enterprise plumbing connect. Every arrow is a real code path — nothing pictured here is aspirational.

flowchart TB
    subgraph CLIENTS["MCP Clients (any of these)"]
        C1[Claude Code]
        C2[Claude Desktop]
        C3[Cursor]
        C4[Windsurf]
        C5[VS Code · Cline · Gemini CLI · Zed]
    end

    subgraph TRANSPORT["Transport Layer"]
        T1[stdio1 process per client]
        T2[SSE / streamable-http1 server serves N clients]
    end

    subgraph MIDDLEWARE["ASGI Middleware Chain (HTTP mode)"]
        M1[HealthMiddleware/health · /healthz]
        M2[BearerAuthMiddlewareconstant-time compare]
        M3[Rate Limitersliding window]
    end

    subgraph MCP["13 MCP Tools (frozen contract)"]
        MT1[search_knowledge]
        MT2[get_document · search_similar]
        MT3[add_document · add_from_url · update · remove]
        MT4[reindex_documents · get_reindex_status]
        MT5[list_documents · list_categories · get_index_stats · evaluate_retrieval]
    end

    subgraph SEARCH["Retrieval Pipeline"]
        R[Query Routerlexical vs semantic]
        F[FTS5 Fast-Pathopt-in · lt 10ms]
        BM[BM25 Inverted Index128x faster than baseline]
        SE[Semantic SearchFastEmbed ONNX lazy-loaded]
        RRF[Reciprocal Rank Fusion]
        CE[Cross-Encoder RerankMiniLM-L-6-v2]
        QC[Query CacheLRU + 5-min TTL]
    end

    subgraph STORAGE["Storage (100% local)"]
        CH[ChromaDBvectors + metadataWAL mode]
        FT[SQLite FTS5lexical indexWAL + busy-timeout]
        MD[index_metadata.jsondurable state]
    end

    subgraph INGEST["Document Ingestion"]
        FS[documents/ folder]
        WD[Watchdog10s debounce]
        PA[35 ParsersMD · PDF · DOCX · code · IaC · IPYNB]
        CK[Chunkermarkdown-aware · code-aware]
        EM[FastEmbed ONNX384D bge-small-en-v1.5]
        DD[SHA256 Dedup]
        SW[Zero-downtime Staging Swaprollback on validation fail]
    end

    subgraph OBS["Enterprise Observability (opt-in)"]
        PM[Prometheus /metrics7 canonical + histograms]
        LG[Structured JSON logsELK · Loki · Datadog · CloudWatch]
        HC[Health payloadversion · uptime · cache stats]
    end

    subgraph CFG["Configuration"]
        YM[config.yaml+ 5 domain presets]
    end

    C1 & C2 & C3 & C4 & C5 -->|MCP protocol| T1
    C1 & C2 & C3 & C4 & C5 -.->|remote deploy| T2
    T1 --> MCP
    T2 --> M1 --> M2 --> M3 --> MCP

    MT1 --> QC
    QC -->|cache miss| R
    R -->|lexical| F
    R -->|semantic| SE
    R -->|hybrid| BM
    F --> CH
    F --> FT
    BM --> CH
    SE --> CH
    BM --> RRF
    SE --> RRF
    RRF --> CE
    CE --> QC

    MT2 --> CH
    MT3 --> INGEST
    MT4 --> SW
    MT5 --> CH

    FS --> WD --> PA
    PA --> CK --> EM --> DD --> CH
    SW -.->|atomic swap| CH
    SW -.-> FT
    CH -.-> MD

    MCP -.->|instrumented| PM
    MCP -.->|logs| LG
    M1 --> HC

    YM -.-> SEARCH
    YM -.-> STORAGE
    YM -.-> OBS
    YM -.-> MIDDLEWARE

    classDef client fill:#3776AB,stroke:#1e5a8a,color:#fff
    classDef transport fill:#00A67E,stroke:#006e54,color:#fff
    classDef middleware fill:#6b46c1,stroke:#4c1d95,color:#fff
    classDef storage fill:#4b5563,stroke:#1f2937,color:#fff
    classDef obs fill:#dc2626,stroke:#7f1d1d,color:#fff
    classDef ingest fill:#f59e0b,stroke:#78350f,color:#fff

    class C1,C2,C3,C4,C5 client
    class T1,T2 transport
    class M1,M2,M3 middleware
    class CH,FT,MD storage
    class PM,LG,HC obs
    class FS,WD,PA,CK,EM,DD,SW ingest

Reading the diagram (top → bottom):

1. Any MCP client — Claude Code, Cursor, Windsurf, and 5 others — connects via the transport of your choice (stdio for personal use, SSE/streamable-http for teams).

2. HTTP mode chains 3 ASGI middlewares in order: health probes first (always answered), then bearer auth (fenced with `WWW-Authenticate`), then rate limiter (sliding window).

3. All 13 MCP tools are decorated with `@rate_limited` + `@instrument` — Prometheus counts every call, rate limiter enforces RPM+burst, both zero-cost when disabled.

4. `search_knowledge` checks the query cache first; cache miss routes through the Query Router (regex classifier) to either the FTS5 fast-path (lexical) or the hybrid pipeline (BM25 + semantic + RRF + cross-encoder rerank).

5. Storage is 100% local: ChromaDB (WAL mode) for vectors + metadata, SQLite FTS5 (WAL + busy-timeout) for lexical fast-path, `index_metadata.json` for durable state.

6. Document ingestion runs continuously: watchdog observes `documents/`, 35 parsers handle each format, chunker respects language boundaries, FastEmbed ONNX generates embeddings, SHA256 deduplicates, and a staging swap performs zero-downtime rebuilds with rollback-on-failure.

7. Enterprise observability (opt-in) — Prometheus `/metrics`, structured JSON logs, `/health` payload — attaches to the same instrumentation points, no code changes required.

8. `config.yaml` (with 5 domain presets) controls every subsystem — no environment variable spaghetti, no hardcoded paths.

Complete architecture — 4 detailed Mermaid diagrams (System Overview · Query Flow · Document Ingestion · hybrid_alpha effect): docs/ARCHITECTURE.md

📄 35 File Formats — parsed natively, no plugins needed

Every parser is chunk-aware — Markdown splits at `##` headers, code splits at function/class boundaries, notebooks skip base64 outputs, PDFs use PyMuPDF, spreadsheets extract sheet-by-sheet. 33 formats are enabled by default; the 2 MetaTrader formats are opt-in (add to `documents.supported_formats` in `config.yaml`).

> Enable an opt-in format — add the extension to `documents.supported_formats` in your `config.yaml`:

> ```yaml

> documents:

> supported_formats: [".md", ".pdf", ".mq4", ".mqh"]

> ```

Full parser reference with per-format notes: docs/CONFIGURATION.md

🔌 Choose your MCP integration

Claude Code

`~/.claude.json`

Claude Desktop

`claude_desktop_config.json`

Cursor

`~/.cursor/mcp.json`

Windsurf

`~/.codeium/windsurf/mcp_config.json`

VS Code

Copilot Chat `mcp.json`

Cline · Gemini CLI · Zed

Native MCP

Complete client configuration guide with JSON schemas per client: docs/INSTALLATION.md#use-with-other-mcp-clients →

⚙️ Configuration in 30 seconds

# config.yaml — everything is optional; defaults just work

paths:
  documents_dir: "./documents"
  data_dir: "./data"

models:
  embedding:
    profile: "compact"                  # "compact" | "quality" | "multilingual" | "custom"
    gpu: "auto"                         # "auto" | "true" | "false"
  reranker:
    enabled: true                       # cross-encoder rerank

search:
  default_results: 5
  max_results: 100

server:                                 # optional — SSE / HTTP mode
  transport: "stdio"                    # or "sse" / "streamable-http"
  auth:
    bearer_token: ""                    # set a secret to enable auth
  rate_limit:
    enabled: false
  metrics:
    enabled: false
  logging:
    format: "text"                      # or "json"

Pre-built presets: `cybersecurity.yaml` · `developer.yaml` · `research.yaml` · `general.yaml` · `multilingual.yaml`

Complete configuration reference — every field, every default, tuning guide: docs/CONFIGURATION.md →

🔒 Security & Compliance

knowledge-rag is designed for teams that cannot let their documents leave the perimeter.

OpenSSF Best Practices badge: passing · project ID #13864

📈 Numbers that matter

• 26 000+ total downloads on PyPI · 250+ GitHub stars · 70+ enterprise teams (private + community)
• 700+ tests collected · 1.33:1 test-to-code ratio · codecov trend gate ±0.5pp
• 35+ status checks on every PR (9-cell OS×Python matrix · 7 quality pillars)
• 35 file formats parsed natively · 13 MCP tools frozen · 5 domain presets (cyber · dev · research · multilingual · general)
• BM25 128× faster than baseline · cross-encoder +1.88pp Recall@10 (p<0.001) · cache −40% p95 latency
• 1 800+ files / 39 K chunks indexed in < 3 min on a modern laptop (typical developer corpus)
• Verified in production on 5 889-doc / 75 016-chunk corpora

Public benchmark dashboard: https://lyonzin.github.io/knowledge-rag/

📚 Documentation

🤝 Community & Support

• Report a bug → Open an issue
• Ask a question → GitHub Discussions
• Report a vulnerability → Security advisory (private)
• Contribute → CONTRIBUTING.md

Response SLA (best-effort, community project):

• Security reports: within 48 h
• Bug reports with reproduction: within 5 business days
• Feature requests: triaged on next release cycle

🗺️ Recent releases

• v4.8.5 (2026-08-13) — Enterprise observability: `/health` endpoint + opt-in JSON structured logging
• v4.8.4 (2026-08-13) — Patch: security + durability + defensive fixes
• v4.8.3 (2026-08-10) — Critical hotfix: nuclear-rebuild + smart-reindex hardening on 50k+ chunk corpora
• v4.8.2 (2026-08-10) — FTS5 lexical fast-path opt-in release
• v4.8.0 (2026-08-06) — Multilingual foundation + zero-downtime reindex

Full history: CHANGELOG.md →

📜 License

MIT License — LICENSE. Forever. No cloud upsell, no dual-licensing, no restrictive clauses. Fork it, sell derivatives, embed it in commercial products — the license does not care.

🙏 Acknowledgments

Built on the shoulders of amazing open-source projects:

• **Anthropic MCP** — Model Context Protocol spec + Python SDK
• **ChromaDB** — vector database that just works
• **FastEmbed** — ONNX embeddings, no PyTorch bloat
• **HuggingFace** — model hosting + `Xenova/ms-marco-MiniLM-L-6-v2` cross-encoder
• **BAAI** — the `bge-small-en-v1.5` embedding model

Community contributors: @Hohlas · @eeshsaxena · Sergey Khokhlov · and everyone who filed issues or PRs.