qmd vs paradedb
Two of the top projects in RAG and search, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
qmd
Local hybrid search over markdown notes and docs, with CLI and MCP server
paradedb
Postgres extension adding BM25 full-text, vector and hybrid search
Verdict
qmd ranks higher, 78 to 76. Of the 4 score parts we measure for both, qmd leads on 2, paradedb on 1 and 1 is even.
- Adoptionqmd leads by 24 points, 91 to 67: a wide gap.
- FreshnessEven at 100.
- Maintenanceparadedb leads by 33 points, 87 to 54: a wide gap.
- Agent-readyqmd leads by 40 points, 40 to 0: a wide gap.
Pick qmd if you are
Developers who want local search over notes and docs for agents
- Hybrid pipeline: query expansion, BM25 plus vector search, RRF fusion, then LLM reranking
- Runs on-device with GGUF models via node-llama-cpp; no hosted API needed
Pick paradedb if you are
Teams adding search and vector retrieval to an existing Postgres
- Search and application data share one Postgres with ACID transactions
- Covers BM25, vector and hybrid search, facets and aggregates in SQL
| What we compare | qmd | paradedb |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 91, widely used | 67, popular |
| Freshness | 100, active | 100, active |
| Maintenance | 54, fair | 87, healthy |
| Agent-ready | 40, minimal | 0, none |
| Facts from GitHub and the README | ||
| Stars | 31.1k | 9.5k |
| License | MIT (permissive) | AGPL-3.0 (copyleft) |
| Last commit | Oct 2026 | Nov 2026 |
| Last release | Aug 2026 | Nov 2026 |
| Language | TypeScript | Rust |
| Docker | No | Yes |
| GPU | Optional | Not needed |
| arm64 or Apple Silicon | Not stated | Mentioned |
qmd
QMD indexes markdown notes, transcripts and docs into a SQLite store and searches them with BM25 (FTS5), vector search and LLM reranking. Models run locally as GGUF through node-llama-cpp. It ships a CLI with JSON and file-list output for agents, an MCP server over stdio or HTTP (default port 8181), and a Node/Bun SDK.
Who it is for: Developers who want local search over notes and docs for agents
Strengths
- Hybrid pipeline: query expansion, BM25 plus vector search, RRF fusion, then LLM reranking
- Runs on-device with GGUF models via node-llama-cpp; no hosted API needed
- CLI, MCP server (stdio or HTTP) and TypeScript SDK available
- HTTP server rejects non-loopback Origin and Host headers to block DNS rebinding
Weaknesses
- HTTP endpoints are unauthenticated; off-host use needs your own auth in front
- Built around markdown and text; other document formats are not mentioned
- Embedding step must run before semantic search works
- TypeScript, GGUF, qwen3-reranker
- Needs Node.js or Bun, node-llama-cpp, SQLite
paradedb
ParadeDB is a Rust Postgres extension that adds a custom index for BM25 full-text search, vector search, filters, facets, aggregations and joins. Search runs inside Postgres with standard SQL and ACID transactions, so no separate search engine is needed. It builds on pgrx, Tantivy and Apache DataFusion, and offers ORM integrations plus agent skills and MCP docs.
Who it is for: Teams adding search and vector retrieval to an existing Postgres
Strengths
- Search and application data share one Postgres with ACID transactions
- Covers BM25, vector and hybrid search, facets and aggregates in SQL
- ORM integrations for Drizzle, Django, SQLAlchemy, Rails and EF Core
- Built on Tantivy and DataFusion rather than a custom engine
Weaknesses
- Community edition is AGPL-3.0; Enterprise needs a commercial license
- Self-hosting Enterprise requires contacting sales
- No embedding or document ingestion pipeline included
- Prisma integration is not yet available
- Rust
- Needs PostgreSQL
- Docker
More in RAG and search
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.