Memlord

- 🔍Hybrid search— BM25 (full-text) + vector KNN (pgvector) fused via Reciprocal Rank Fusion
- 📂Multi-user— each user sees only their own memories; workspaces for shared team knowledge
- 🛠️11 MCP tools— store, retrieve, recall, list, search by tag, get, update, delete, move, list workspaces, dream report
- 💤Dreaming— a guided consolidation pass (dreamMCP prompt +dream_reporttool): finds near-duplicate and conflicting memories, merges them into insights non-destructively, driven by the client LLM
- 🌐Web UI— browse, search, edit and delete memories in the browser; export/import JSON
- 🔒OAuth 2.1— full in-process authorization server, always enabled
- 🐘PostgreSQL— pgvector for embeddings, tsvector for full-text search
- 📊Progressive disclosure— search returns compact snippets by default; callget_memory(name)only for what you need, reducing token usage
- 🔁Deduplication— automatically detects near-identical memories before saving, preventing noise accumulation

- OpenMemory— auto-extracts memories from raw conversation text; no need to decide what to store manually; good import/export
- mcp-memory-service— richer web UI (graph visualization, quality scoring, 8 tabs); more permissive license (Apache 2.0); multiple transport options (stdio, SSE, HTTP)
- basic-memory— memories are human-readable Markdown files you can edit, version-control, and read without any server; wiki-style entity links form a local knowledge graph; ~20 MCP tools

- You wantzero-config local embeddings— ONNX model ships with the server, no Ollama or external API needed
- You run amulti-user team serverwith proper OAuth 2.1 auth and invite-based workspaces
- You want aproduction-grade database(PostgreSQL) that scales beyond a single machine's SQLite
- You manage memoriesexplicitly— store exactly what matters, typed and tagged, not everything the LLM decides to extract
- You want aself-hosted Web UIwith full CRUD and JSON export, without a cloud subscription

# Install dependencies uv sync --dev # Download ONNX model (~23 MB) uv run python scripts/download_model.py # Run migrations alembic upgrade head # Start the server memlord

Each search request runs BM25 and vector KNNin parallel, then merges results viaReciprocal Rank Fusion:

SetMEMLORD_BASE_URLto your public URL and changeMEMLORD_OAUTH_JWT_SECRETbefore deploying.

ThedreamMCP prompt walks the client LLM through a full consolidation pass over thedream_reportoutput: classify similar pairs (duplicate / complementary / conflict), merge intoinsightmemories, retire superseded ones viaexpires_at— never destructively.

Workspace management (create, invite, join, leave) is handled via the Web UI.

pyright src/ # type check ruff format . # format pytest # run tests alembic-autogen-check # verify migrations are up to date

Engram is a hosted MCP server that provides reliable memory for AI agents:

Persistent memory, teams, and projects for AI agents. 76 MCP tools for storing, recalling, and sharing knowledge across sessions.

Provides searchable local storage for Claude conversation history, enabling context retrieval during sessions.

Deterministic O(1) memory for AI agents — local-first, MCP-native, with multi-agent speaker attribution and millisecond recall.

Integrates with Mem0.ai to provide persistent memory capabilities for LLMs, supporting cloud, Supabase, and local storage.

Enables Large Language Models to store and retrieve persistent memories with intelligent search capabilities.

Extends the Memory server with PouchDB for robust document-based storage, custom memory file paths, and interaction timestamping.

A memory management system for AI assistants to store, retrieve, and manage user information using a local database.

Open-source shared AI memory and team knowledge layer with 44 MCP tools for notes, memories, URLs, emails, projects, graph search, semantic search, and Git sync.