# FusionPact

> Use this tool when you need to efficiently retrieve and manage complex information across multiple agents and documents. FusionPact solves problems of information overload and knowledge fragmentation by combining advanced search and retrieval methods with purpose-built agent memory types. It takes in documents and agent interactions as inputs and outputs relevant, context-rich information, making it ideal for use in multi-agent systems and knowledge-intensive applications.

Canonical page: https://skillsregistry.net/skills/fusionpact-vectordb  
JSON: https://api.skillsregistry.net/v1/skills/fusionpact-vectordb

## Description

Combines HNSW vector search, reasoning-based tree retrieval, and BM25 keyword matching into a single retrieval platform using reciprocal rank fusion. Provides purpose-built agent memory with episodic, semantic, procedural, and shared memory types for multi-agent systems. Includes a RAG pipeline for document ingestion, chunking, and LLM-ready context building, all local-first with zero external dependencies.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/fusionpact-vectordb)
- **Repository:** <https://github.com/fusionpacttech/fusionpact-vectordb>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "fusionpact-vectordb"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/fusionpact-vectordb` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/fusionpact-vectordb/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt