Fusionpact Vectordb
by atul-fusionpactcommunityv2.1.1
FusionPact is a retrieval engine that combines HNSW vector search, reasoning-based tree retrieval, and agent memory for AI agents and multi-agent systems.
From the registry: Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.
Install & configure
Prerequisites
- requiredNode.js 18+Requires Node.js 18 or higher
- optionalEmbedding provider (recommended)Install Ollama locally for free embeddings, or set OPENAI_API_KEY
https://ollama.com$ ollama pull nomic-embed-text
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `fusionpact-vectordb` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 18+** — Requires Node.js 18 or higher
Optional prerequisites:
- Embedding provider (recommended) — Install Ollama locally for free embeddings, or set OPENAI_API_KEY Run: `ollama pull nomic-embed-text` (https://ollama.com)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["fusionpact","mcp"]
- optional environment variables:
- `EMBEDDING_PROVIDER`: Embedder: 'ollama' (recommended), 'openai', or 'mock' (example: `ollama`)
- `OPENAI_API_KEY`: Required if using openai embedder (example: `<your-openai-api-key>`)
Note: Hybrid retrieval engine (vector + tree reasoning + keyword) with agent memory. Local-first, zero dependencies.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: Hybrid retrieval engine (vector + tree reasoning + keyword) with agent memory. Local-first, zero dependencies.
Tools (11)
fusionpact_create_collection
Create HNSW-indexed vector collection
fusionpact_search
Semantic vector search
fusionpact_hybrid_search
Hybrid retrieval (vector + tree + keyword)
fusionpact_rag_ingest
One-click RAG ingestion
fusionpact_rag_query
Build LLM-ready context
fusionpact_memory_remember
Store episodic memory
fusionpact_memory_recall
Recall relevant memories
fusionpact_memory_learn
Add semantic knowledge
fusionpact_memory_share
Share cross-agent knowledge
fusionpact_memory_forget
GDPR-style memory erasure
fusionpact_memory_conversation
Manage conversation threads
Environment variables
EMBEDDING_PROVIDERrequiredSpecifies the embedding provider to usePackages
fusionpact
npmv2.1.1transport: stdio
Details
- Language
- JavaScript
- License
- Apache-2.0
- Released
- Mar 10, 2026
- Last commit
- Mar 10, 2026
- Registry name
- io.github.atul-fusionpact/fusionpact-vectordb