Weasley DeepMind

io.github.potatohoney-pPublished by GitHub account potatohoney-pv1.0.0Updated Oct 24, 2026

Secure, fragment-based long-term memory for MCP-compatible AI agents.

VerifiedSTDIODesktop onlyDatabasesKnowledge & Memory

Overview

AI-generated overview

Self-hosted long-term memory server that lets an AI assistant store, link and recall small typed memory fragments through MCP.

What you can do
  • Store memory fragments, individually or in batches, with type, provenance, importance and lifecycle state
  • Recall ranked context within a token budget using keyword, PostgreSQL GIN, graph-neighbor and optional vector search
  • Amend, forget and link fragments, and explore the memory graph
  • Reflect on and consolidate stored memory, and read memory statistics
  • Inspect fragment history, reconstruct history and search traces
When to use it
Useful when an assistant should carry context across sessions without replaying whole conversations, and you are willing to run your own PostgreSQL database. Suited to teams that want memory data kept on their own infrastructure.
Requirements
Node.js 20.19 or newer and PostgreSQL 15 or newer with the pgvector extension; Redis 7 is optional. Requires the DATABASE_URL connection string, and optionally EMBEDDING_API_KEY for semantic recall. Runs as a local stdio process via npx, or as an HTTP server on loopback with a bearer access key.
Before you install
DATABASE_URL holds database credentials and EMBEDDING_API_KEY an embedding provider secret; keep them out of version control. Stdio mode trusts the local host process, so protect the host account and database access. Memory tools write, amend and delete stored data. HTTP mode fails closed without WEASLEY_DEEPMIND_ACCESS_KEY, and disabling authentication is meant only for loopback development.

Installation

In SourceWeft

  1. Open Weasley DeepMind in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[Weasley DeepMind]

Weasley DeepMind

Weasley DeepMind is a self-hosted memory server for AI agents. It stores small, typed memory fragments, links related evidence, and recalls the right context through MCP without forcing an entire conversation history back into every prompt.

It is part of the Weasley Open Source family and is released under Apache-2.0.

Why DeepMind

  • Useful recall, not a transcript dump. Keyword, PostgreSQL GIN, graph-neighbor, and optional pgvector search are merged and ranked within a token budget.
  • Memory with structure. Facts, decisions, procedures, preferences, episodes, and errors keep provenance, importance, links, and lifecycle state.
  • MCP-native. Use a local stdio process or the Streamable HTTP endpoint at /mcp.
  • Fail-closed HTTP security. The HTTP server rejects requests when no access key is configured. Authentication can only be disabled explicitly for local development.
  • Self-hosted data. PostgreSQL is the system of record. Redis and external embedding or LLM providers are optional.
  • Operationally ready. Migrations are serialized with a PostgreSQL advisory lock, secrets are redacted from logs, and updates refuse dirty Git checkouts.

Requirements

  • Node.js 20.19 or newer
  • PostgreSQL 15 or newer with the pgvector extension
  • Redis 7 (optional, for cache and low-latency keyword lookup)

For a reproducible offline check of correction/retraction recall and content-token budgets, run npm run --silent eval:recall with Node.js 24. This uses production recall code and synthetic storage, with no database or model required. See the offline recall evaluation for the negative control, report definitions and limits.

Install from npm

bash
npm install --global weasley-deepmind

Create a PostgreSQL database with pgvector, then configure the connection:

bash
export DATABASE_URL='postgresql://postgres:password@localhost:5432/weasley_deepmind'export WEASLEY_DEEPMIND_ACCESS_KEY='replace-with-a-long-random-secret'
weasley-deepmind migrateweasley-deepmind serve

The HTTP server listens on http://127.0.0.1:57332 by default. Its MCP endpoint is http://127.0.0.1:57332/mcp.

Add it to an MCP client

The npm package includes a newline-delimited stdio transport. A generic MCP client configuration looks like this:

json
{  "mcpServers": {    "weasley-deepmind": {      "command": "npx",      "args": ["-y", "weasley-deepmind", "stdio"],      "env": {        "DATABASE_URL": "postgresql://postgres:password@localhost:5432/weasley_deepmind",        "WEASLEY_DEEPMIND_AUTO_MIGRATE": "true"      }    }  }}

For an already-running HTTP deployment, point the client at /mcp and send Authorization: Bearer <WEASLEY_DEEPMIND_ACCESS_KEY>.

Run the repository locally

bash
git clone https://github.com/potatohoney-p/weasley-deepmind.gitcd weasley-deepmindnpm cidocker compose -f docker-compose.dev.yml up -dcp .env.example.minimal .envnpm run migratenpm start

The development Compose file exposes PostgreSQL at localhost:35432 and Redis at localhost:36379. Update .env to match those ports before starting the server.

Core flow

mermaid
flowchart LR    Agent["AI agent"] --> MCP["stdio or Streamable HTTP"]    MCP --> Tools["remember · recall · reflect · context"]    Tools --> Rank["keyword + graph + vector ranking"]    Rank --> Postgres["PostgreSQL + pgvector"]    Rank -. optional cache .-> Redis["Redis"]

The main tool set includes remember, batch_remember, recall, forget, amend, link, reflect, context, memory_stats, memory_consolidate, graph_explore, fragment_history, reconstruct_history, and search_traces. Tool availability can be limited by API-key permissions and operating mode.

Configuration

VariablePurposeDefault
DATABASE_URLPostgreSQL connection URLderived from POSTGRES_*
WEASLEY_DEEPMIND_ACCESS_KEYRequired bearer secret for HTTP modenone; HTTP fails closed
WEASLEY_DEEPMIND_AUTH_DISABLEDExplicit loopback-only authentication opt-out; startup rejects non-loopback listenersfalse
WEASLEY_DEEPMIND_AUTO_MIGRATERun migrations before stdio startupfalse (server.json suggests true)
WEASLEY_DEEPMIND_HOMECLI cache and local state directory~/.weasley/deepmind
WEASLEY_DEEPMIND_HOSTHTTP listen address127.0.0.1
PORTHTTP port57332
REDIS_ENABLEDEnable Redis-backed featuresfalse
EMBEDDING_PROVIDERopenai, gemini, ollama, localai, cloudflare, transformers (optional install), or customopenai
EMBEDDING_API_KEYOptional embedding provider secretnone

See .env.example, configuration, and the installation guide for the complete matrix.

Local transformer embeddings are intentionally excluded from the default install so the core MCP server does not inherit an optional native-image dependency. Follow the pinned setup in docs/embedding-local.md before selecting EMBEDDING_PROVIDER=transformers.

CLI

text
weasley-deepmind serve       Start the HTTP MCP serverweasley-deepmind stdio       Start the local stdio MCP serverweasley-deepmind migrate     Apply pending database migrationsweasley-deepmind health      Check database, Redis, and embeddingsweasley-deepmind recall      Search memory from the terminalweasley-deepmind remember    Store a memory fragmentweasley-deepmind update      Preview or apply an update

Run weasley-deepmind --help or see the CLI reference for every command.

Security defaults

  • Keep the HTTP listener on loopback unless you have a trusted reverse proxy and an explicit origin allowlist.
  • Use a unique, high-entropy WEASLEY_DEEPMIND_ACCESS_KEY and never commit .env.
  • Stdio mode trusts the local MCP host process; protect the host account and database credentials accordingly.
  • Report vulnerabilities privately using the instructions in SECURITY.md.

Development

bash
npm cinpm testnpm run lintnpm run lint:migrationsnpm pack --dry-run

Architecture and operations details live in docs/architecture.en.md and docs/operations. Contributions are welcome through CONTRIBUTING.md.

License

Copyright 2026 Weasley Open Source.

Licensed under the Apache License 2.0. See NOTICE for attribution information.

Source: README.md at commit 762f5c7

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts