fusionpact-vectordb

Hybrid Vector + Reasoning + Memory for AI Agents

[](LICENSE) [](https://nodejs.org) [](https://www.npmjs.com/package/fusionpact)

> Similarity ≠ Relevance. FusionPact is the first retrieval engine that combines HNSW vector search, reasoning-based tree retrieval, and agent memory in a single platform — purpose-built for AI agents and multi-agent systems.

Quickstart · Hybrid Retrieval · Agent Memory · Multi-Agent · MCP Server · Tree Index · RAG Pipeline · API Reference · Benchmarks · Contributing

---

Traditional vector databases retrieve what's similar. But similar ≠ relevant. Ask a vector DB for "Q3 2024 revenue" and you might get Q2 or Q4 data — semantically similar, but the wrong answer.

FusionPact solves this by combining three retrieval paradigms:

| Strategy | How It Works | Best For | |---|---|---| | Vector Search (HNSW) | Embedding similarity, O(log N) | Broad search across large collections | | Tree Reasoning | LLM navigates document structure | Precise retrieval in structured documents | | Keyword Search (BM25) | Term frequency matching | Exact match requirements |

Plus purpose-built agent memory, multi-agent orchestration, and MCP server — all zero-dependency, local-first, and free.

┌──────────────────────────────────────────────────────────┐
│             FusionPact Retrieval Engine                   │
│                                                          │
│  ┌────────────┐  ┌─────────────┐  ┌────────────────┐   │
│  │ Vector     │  │ Tree        │  │