vibe-hnindex

Local MCP server — index your repo once, search it in every AI session

Keyword (SQLite FTS5) · Semantic (Qdrant + Ollama embeddings) · Hybrid — your code stays on disk

MCP server (vibe-hnindex) latest: v0.7.0 · hnindex-cli v0.7.0+ (CLI-only patches). Shields badges read npm in real time; GitHub Releases only update when you publish a new tag/release.

What this does

vibe-hnindex is a Model Context Protocol server. After you index a folder once, assistants (Claude, Cursor, Windsurf, Antigravity, …) can search that codebase with paths and line ranges — data is stored locally (SQLite + optional Qdrant). Embeddings use Ollama; vectors use Qdrant (Docker, local, or Qdrant Cloud with QDRANT_API_KEY).

How to read the docs (start here)

Everything else is optional: Configuration, How it works, Troubleshooting.

Full index: docs/README.md

CLI installer (hnindex)

Optional — writes the MCP JSON for you (merge-safe, same npx -y vibe-hnindex block as in the docs):

npm install -g hnindex-cli
hnindex init --mcp antigravity    # or: claude, claude-desktop, cursor, cursor-project, windsurf, vscode
hnindex init --list               # show all targets and paths
hnindex update                    # npm update -g hnindex-cli

See Getting started → CLI and Integrations → hnindex CLI.

Install in 5 steps

1. Node.js — v20+ (nodejs.org). On Windows, Node 20 or 22 LTS is strongly recommended so npm install does not need a C++ compiler. See Troubleshooting → Windows if npm i vibe-hnindex fails.
2. Ollama — install from ollama.com, then: ollama pull bge-m3:567m and keep ollama serve running (or set OLLAMA_URL to a remote server).
3. Qdrant — for semantic/hybrid search: docker run -d --name qdrant -p 6333:6333 qdrant/qdrant (or use Qdrant Cloud). Keyword-only search works without Qdrant.
4. MCP config — add the server to your assistant’s MCP settings. Minimal example (self-hosted Qdrant):

{
  "mcpServers": {
    "vibe-hnindex": {
      "command": "npx",
      "args": ["-y", "vibe-hnindex"],
      "env": {
        "OLLAMA_URL": "http://localhost:11434",
        "OLLAMA_MODEL": "bge-m3:567m",
        "QDRANT_URL": "http://localhost:6333"
      }
    }
  }
}

1. Restart the IDE or assistant, then in chat ask to index a path and search — see First steps.

For Qdrant Cloud, add QDRANT_API_KEY and set QDRANT_URL to your HTTPS cluster URL — details in Getting started.

Optional rerank (RERANK_URL)

Semantic/hybrid search already uses Ollama (OLLAMA_URL, OLLAMA_MODEL e.g. bge-m3:567m) for query vectors and Qdrant for retrieval. After that, the server can reorder the top pool of hits:

• Without RERANK_URL: reorder by Qdrant semantic scores (no extra network service). This is enough for most setups, including when you only run Ollama + Qdrant.
• With RERANK_URL: POST JSON { "query", "documents" } to your URL; response { "scores": number[] } (same length as documents). Use a small HTTP service you host that wraps your reranker; Ollama does not expose this contract on :11434 by default.

Ollama vs rerank: pulling a reranker model in Ollama (e.g. qllama/bge-reranker-v2-m3) does not replace RERANK_URL—you still need an adapter service unless you only rely on the built-in Qdrant reorder. See Configuration → Rerank.

Google Antigravity

Use the same mcpServers block as above, but save it in Antigravity’s MCP file:

Step-by-step: Integrations → Google Antigravity.

Features (short)

Architecture

License

MIT — see LICENSE.

Contributing

Issues and PRs: github.com/AndyAnh174/vibe-hnindex.

Contact

Ho Viet Anh (AndyAnh174) · hovietanh147@gmail.com · GitHub