Server data from the Official MCP Registry
Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector
Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector
Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. ⚠️ Package registry links to a different repository than scanned source. Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.
14 files analyzed · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Set these up before or after installing:
Environment variable: HINDSIGHT_URL
Environment variable: MEMPALACE_BANK
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-holetron-hindsight-mempalace": {
"env": {
"HINDSIGHT_URL": "your-hindsight-url-here",
"MEMPALACE_BANK": "your-mempalace-bank-here"
},
"args": [
"-y",
"hindsight-mempalace-mcp"
],
"command": "npx"
}
}
}From the project's GitHub README.
Hierarchical memory for AI agents. Storage + taxonomy in one system.
A hybrid of two open-source projects:
| Project | What it does | What it lacks |
|---|---|---|
| Hindsight by vectorize-io | Long-term vector memory for AI agents. Stores, embeds, recalls. | No structure — all memories in one flat pile |
| MemPalace by milla-jovovich | Hierarchical taxonomy: rooms, halls, layers — the method of loci for AI | No storage engine — a spec without a database |
This fork connects them. Hindsight's vector store + MemPalace's taxonomy = structured memory with semantic search.
┌──────────────────────────────────────────────────────┐
│ MEMPALACE │
│ │
│ ┌─── Room: auth ──┐ ┌─── Room: pipeline ──┐ │
│ │ Hall: facts │ │ Hall: decisions │ │
│ │ Hall: procedures │ │ Hall: events │ │
│ │ Hall: warnings │ │ Hall: facts │ │
│ │ │ │ │ │
│ │ L0 ████ always │ │ L0 ████ always │ │
│ │ L1 ███░ warm │ │ L1 ███░ warm │ │
│ │ L2 ██░░ cold │ │ L2 ██░░ cold │ │
│ │ L3 █░░░ archive │ │ L3 █░░░ archive │ │
│ └──────────────────┘ └─────────────────────┘ │
│ │ │ │
│ └──── Tunnel ──────────┘ │
│ (cross-bank bridge) │
│ │
│ Closets: compressed summaries + source pointers │
└──────────────────────┬───────────────────────────────┘
│
Hindsight vector store
(embeddings + semantic search)
Rooms — topic isolation. Auth, pipeline, infrastructure, schema — each topic in its own room. An agent searching for auth facts won't wade through 500 deploy memories.
Halls — knowledge typing within a room. Fact, event, decision, procedure, warning. The system knows what it's looking at before reading — like Content-Type for memory.
Layers L0–L3 — four priority tiers. L0 (core) is always loaded. L3 (archive) is deep-search only. Same idea as CPU cache hierarchy: L1 is fast and small, RAM is slow but holds everything.
Closets — AI-compressed summaries with source pointers. Deduplication at the knowledge level: 10 related facts → 1 paragraph + references.
Tunnels — cross-bank bridges between agents. Agent A discovers an insight — Agent B sees it through a tunnel without data duplication.
| Hindsight | MemPalace | This fork | |
|---|---|---|---|
| What it is | Long-term memory store | Hierarchical taxonomy spec | Storage + taxonomy hybrid |
| Storage | Vector store + embeddings | None (spec only) | Vector store + embeddings |
| Memory structure | Flat (all memories equal) | Rooms → Halls → Layers | Rooms → Halls → Layers + embeddings |
| Retrieval | Semantic search | No retrieval engine | Room-scoped semantic search |
| Classification | None | Defined in spec | Keyword-based, <1ms, zero LLM cost |
| Priority tiers | All memories equal | L0–L3 (spec) | L0–L3 (implemented) |
| Compression | None | Closets (spec) | Closets with source pointers |
| Multi-agent | Shared bank | Tunnels (spec) | Tunnels (cross-bank bridges) |
| MCP integration | API only | None | 5 tools via MCP protocol |
| Setup | Docker | Manual config | Docker (drop-in upgrade) |
git clone https://github.com/holetron/hindsight-mempalace.git
cd hindsight-mempalace
cp .env.example .env
# edit .env with your config
docker compose -f docker-compose.mempalace.yml up -d
API available at http://localhost:5100. Drop-in replacement for vanilla Hindsight — same API, same clients, new brain.
Ships with BAAI/bge-small-en-v1.5 (384-dim) — fast, CPU-friendly, baked into the image so first run needs no network download. It's English-optimized; recall quality on other languages degrades.
For multilingual memory (e.g. RU, multi-script), point it at a multilingual model:
HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL=BAAI/bge-m3 # 1024-dim, multilingual
Dimension is detected automatically. ⚠️ Switching models changes the vector dimension — do it on an empty memory store, or wipe + re-embed, since existing vectors can't be mixed across dimensions.
The mcp-server/ directory contains a standalone MCP server. Any MCP-compatible client (Claude Code, OpenClaw, Cursor, etc.) connects and gets structured long-term memory.
| Tool | Description |
|---|---|
memory_retain | Save a memory with automatic room/hall classification |
memory_recall | Scoped semantic search with room/hall/layer filters |
memory_reflect | Deep reasoning — synthesize facts, find patterns, answer with citations |
memory_compress | Create closet summaries from accumulated facts |
memory_bridge | Cross-bank tunnels between related memories |
cd mcp-server
npm install
HINDSIGHT_URL=http://localhost:5100 node server.js
Add to ~/.claude/mcp.json:
{
"mcpServers": {
"mempalace": {
"command": "node",
"args": ["/path/to/mcp-server/server.js"],
"env": {
"HINDSIGHT_URL": "http://localhost:5100",
"MEMPALACE_BANK": "my-agent-bank"
}
}
}
}
See mcp-server/README.md for full docs and environment variables.
The base /retain and /recall endpoints are fully backward-compatible. New parameters are optional.
| Endpoint | Parameter | Type | Description |
|---|---|---|---|
/retain | room | string | Topic room (auto-classified if omitted) |
/retain | hall | string | Knowledge type (auto-classified if omitted) |
/retain | layer | int | Priority 0-3 (default: 2) |
/recall | room | string | Filter recall to a specific room |
/recall | hall | string | Filter recall to a specific hall |
/recall | max_layer | int | Maximum layer depth to search |
| Method | Endpoint | Description |
|---|---|---|
| POST | /bridge | Create a cross-bank memory bridge |
| GET | /tunnels | List existing tunnels |
| POST | /tunnels | Create a tunnel between banks |
| GET | /closets | List compressed memory summaries |
| POST | /closets | Compress L3 memories into a closet |
auth · pipeline · infrastructure · deployment · schema · api · ui · tax · hr · legal · compliance · monitoring · agent · general
warning · decision · procedure · event · preference · discovery · fact
| Layer | Name | Behavior |
|---|---|---|
| L0 | Critical | Always recalled |
| L1 | Important | Recalled by default |
| L2 | Normal | Standard (default for new memories) |
| L3 | Archive | Deep search only, compressed into closets |
MemPalace includes a keyword-based classifier (room_hall_classifier.py) that assigns room and hall automatically when not provided. No LLM call — classification is instant and free.
Extensible: add keywords to ROOM_KEYWORDS / HALL_KEYWORDS dictionaries.
curl -X POST http://localhost:5100/retain \
-H "Content-Type: application/json" \
-d '{
"bank": "project-alpha",
"text": "Never restart PROD PM2 without confirming DEV works first.",
"room": "deployment",
"hall": "warning",
"layer": 0
}'
curl -X POST http://localhost:5100/recall \
-H "Content-Type: application/json" \
-d '{
"bank": "project-alpha",
"query": "deployment safety rules",
"room": "deployment",
"hall": "warning",
"max_layer": 1
}'
curl -X POST http://localhost:5100/bridge \
-H "Content-Type: application/json" \
-d '{
"source_bank": "project-alpha",
"target_bank": "project-beta",
"room": "infrastructure",
"hall": "procedure"
}'
A taxonomy layer over Hindsight's vector store, plus a standalone MCP server.
Key additions:
room_hall_classifier.py — keyword-based taxonomy engine (new)aa1_add_room_hall_to_memory_units.py — DB migration: flat → hierarchical, adds room/hall + layer column (new)mcp-server/ — standalone MCP server with 5 tools (new)Full architectural spec: MEMPALACE.md
This fork tracks vectorize-io/hindsight as upstream. To pull updates:
git remote add upstream https://github.com/vectorize-io/hindsight.git
git fetch upstream
git merge upstream/main
All changes are additive — existing Hindsight behavior is preserved.
MIT — same as upstream Hindsight. See LICENSE.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
by mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.