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. That is what the hindsight mempalace mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
API available at http://localhost:5100. Drop-in replacement for vanilla Hindsight — same API, same clients, new brain.
The server publishes 9 tools. What each one is for:
memory_retain — Save a memory with automatic room/hall classificationmemory_recall — Scoped semantic search with room/hall/layer filtersmemory_reflect — Deep reasoning — synthesize facts, find patterns, answer with citationsmemory_compress — Create closet summaries from accumulated factsmemory_bridge — Cross-bank tunnels between related memoriesEmbeddings — 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'sTools — The Tools tool exposed by this serverSetup — The Setup tool exposed by this serverLayers — The Layers tool exposed by this serverConfiguration is passed through the environment: HINDSIGHT_URL, MEMPALACE_BANK. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
The server ships on npm as HINDSIGHT_URL, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Hindsight MemPalace's toolset — memory_retain, memory_recall, memory_reflect and 6 more — is a fair guide to whether it matches your workflow. It is maintained by holetron; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Hindsight MemPalace's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| 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 |
| Embeddings | 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. |
| Tools | The Tools tool exposed by this server. |
| Setup | The Setup tool exposed by this server. |
| Layers | The Layers tool exposed by this server. |
{
"mcpServers": {
"hindsight-mempalace": {
"command": "npx",
"args": ["-y", "HINDSIGHT_URL"],
"env": {
"HINDSIGHT_URL": "your-value",
"MEMPALACE_BANK": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| HINDSIGHT_URL | Endpoint or connection string the server talks to. | Yes |
| MEMPALACE_BANK | Configuration value read at startup. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.