広告掲載
MCP.so
ログイン

Hindsight Mempalace MCP Server

@holetron

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

holetron

投稿者

HOLETRON

Hindsight Mempalace MCP Server について

Self-hosted long-term memory for AI agents. An MCP server that gives agents persistent, hierarchical recall (L0–L3) over pgvector — retain preferences, decisions and observations, then recall them by topic across sessions. MIT, clone-and-run, requires Postgres + pgvector.

#memory#long-term-memory#pgvector#self-hosted#knowledge#rag#agents

Hindsight Mempalace MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "hindsight-mempalace": {
      "command": "npx",
      "args": [
        "-y",
        "hindsight-mempalace-mcp"
      ],
      "env": {
        "HINDSIGHT_URL": "http://127.0.0.1:5100",
        "MEMPALACE_BANK": "mempalace-main"
      }
    }
  }
}

Hindsight Mempalace MCP Server のツール

5

Save a fact, observation, or document to long-term memory with automatic room/hall classification. Rooms: auth, pipeline, schema, infrastructure, ui, api, deployment, monitoring, agent, general. Halls: fact, event, decision, preference, discovery, procedure, warning. Layers: L0=Identity (always loaded), L1=Critical, L2=Session (default), L3=Deep.

Search long-term memory for relevant facts. Uses semantic search with optional room/hall scoping for significantly improved retrieval accuracy. Supports layer cascade (L0 results always prioritized).

Deep reasoning over memory — synthesizes facts, finds patterns, answers complex questions with citations. Use for analysis: "What patterns emerge from recent events?" or "Summarize everything about X."

Create compressed memory summaries (closets) from stored facts. Groups memories by room+hall and creates AI-generated summaries with source pointers. Use when a topic has accumulated many facts.

Create a cross-bank memory bridge (tunnel) between two related memories in different banks. Relations: same_concept, depends_on, contradicts, extends. Use when concepts in separate banks are related.

概要

What is Hindsight Mempalace?

Hindsight Mempalace is a hierarchical memory system for AI agents, merging Hindsight's long-term vector store with MemPalace's taxonomy architecture. It provides structured memory with semantic search, rooms, halls, layers, closets, and tunnels, plus an MCP server for client integration.

How to use Hindsight Mempalace?

Clone the repository, copy .env.example to .env, edit configuration, then run docker compose -f docker-compose.mempalace.yml up -d. API available at http://localhost:5100. For the MCP server, install npm dependencies in mcp-server/ and run with environment variables.

Key features of Hindsight Mempalace

  • Vector store with hierarchical taxonomy (rooms, halls, layers)
  • Keyword-based auto-classification (<1ms, zero LLM cost)
  • L0–L3 priority tiers (always loaded to archive)
  • Cross-bank tunnels for multi-agent memory sharing
  • Closet compression: summaries with source pointers
  • 5 MCP tools: retain, recall, reflect, compress, bridge

Use cases of Hindsight Mempalace

  • AI agents needing structured long-term memory with topic isolation
  • Multi-agent systems sharing insights across banks via tunnels
  • Development teams storing deployment procedures, warnings, and decisions
  • Knowledge management with automatic classification and compression

よくある質問

1

What does Hindsight Mempalace add over vanilla Hindsight?

It adds a taxonomy layer (rooms, halls, layers), auto-classification, closets, tunnels, cross-bank bridges, and a standalone MCP server with 5 tools.

2

What are the runtime requirements?

Docker for the API server; Node.js for the MCP server. Ships with `BAAI/bge-small-en-v1.5` embeddings (English-optimized). Optional multilingual model `BAAI/bge-m3` for other languages.

3

How does data classification work?

A keyword-based classifier (`room_hall_classifier.py`) assigns room and hall automatically in under 1ms without LLM calls. Users can also specify these manually.

4

Can I use this as a drop-in replacement for Hindsight?

Yes. The base `/retain` and `/recall` endpoints are fully backward-compatible. All new parameters are optional.

5

How do tunnels and bridges work?

Tunnels are cross-bank bridges between agents. Agent A discovers a memory; Agent B accesses it through a tunnel without duplicating data. Created via the `/bridge` endpoint or `memory_bridge` MCP tool.

6

What models are supported for embeddings?

Default English model `BAAI/bge-small-en-v1.5` (384-dim). For multilingual use, set `HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL=BAAI/bge-m3` (1024-dim) on an empty store.

コメント

「その他」の他のコンテンツ

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K
広告掲載