Memlord
Memlord is a self-hosted, multi-user MCP memory server with hybrid search, typed memory management, and workspace support via an MCP API and web UI (backed by PostgreSQL + pgvector).
Store memories (
store_memory): Save typed memories (fact,preference,instruction,feedback,decision) with tags, metadata, and workspace assignment. Includes automatic near-duplicate detection.Hybrid search (
retrieve_memory): Semantic (vector KNN) + full-text (BM25) search fused via Reciprocal Rank Fusion, with filtering by memory type, workspace, and similarity threshold. Returns compact snippets by default.Time-based search (
recall_memory): Find memories using natural-language time expressions (e.g., "last week", "about Python last month") combined with semantic search.Fetch a memory (
get_memory): Retrieve full content of a specific memory by numeric ID.List memories (
list_memories): Paginated listing ordered by creation date, filterable by type or tag.Tag search (
search_by_tag): Find memories by exact tag match with AND/OR logic.Update memory (
update_memory): Modify content, type, tags, or metadata of an existing memory by ID.Delete memory (
delete_memory): Permanently remove a memory by ID, including from vector and full-text indexes.Move memory (
move_memory): Transfer a memory between workspaces (requires write access).List workspaces (
list_workspaces): View all personal and shared workspaces you belong to, with roles and member counts.Web UI: Browse, search, edit, delete, import, and export memories in a browser interface.
Local embeddings: Zero-config local ONNX models โ no external API dependencies.
Utilizes PostgreSQL with the pgvector extension as the primary storage backend to provide persistent memory storage, full-text search, and vector-based semantic retrieval.
โจ Features
๐ Hybrid search โ BM25 (full-text) + vector KNN (pgvector) fused via Reciprocal Rank Fusion
๐ Multi-user โ each user sees only their own memories; workspaces for shared team knowledge
๐ ๏ธ 11 MCP tools โ store, retrieve, recall, list, search by tag, get, update, delete, move, list workspaces, dream report
๐ค Dreaming โ a guided consolidation pass (
dreamMCP prompt +dream_reporttool): finds near-duplicate and conflicting memories, merges them into insights non-destructively, driven by the client LLM๐ Web UI โ browse, search, edit and delete memories in the browser; export/import JSON
๐ OAuth 2.1 โ full in-process authorization server, always enabled
๐ PostgreSQL โ pgvector for embeddings, tsvector for full-text search
๐ Progressive disclosure โ search returns compact snippets by default; call
get_memory(name)only for what you need, reducing token usage๐ Deduplication โ automatically detects near-identical memories before saving, preventing noise accumulation
Related MCP server: Memory MCP Server
๐ How Memlord compares
Memlord | ||||
Search | BM25 + vector + RRF | Vector only (Qdrant) | BM25 + vector + RRF | BM25 + vector |
Embeddings | Local ONNX, zero config | OpenAI default; Ollama optional | Local ONNX, zero config | Local FastEmbed |
Storage | PostgreSQL + pgvector | PostgreSQL + Qdrant | SQLite-vec / Cloudflare Vectorize | SQLite + Markdown files |
Multi-user | โ | โ single-user in practice | โ ๏ธ agent-ID scoping, no isolation | โ |
Workspaces | โ shared + personal, invite links | โ ๏ธ "Apps" namespace | โ ๏ธ tags + conversation_id | โ per-project flag |
Authentication | โ OAuth 2.1 | โ none (self-hosted) | โ OAuth 2.0 + PKCE | โ |
Web UI | โ browse, edit, export | โ Next.js dashboard | โ rich UI, graph viz, quality scores | โ local; cloud only |
MCP tools | 11 | 5 | 15+ | ~20 |
Self-hosted | โ single process | โ Docker (3 containers) | โ | โ |
Memory input | Manual (explicit store) | Auto-extracted by LLM | Manual | Manual (Markdown notes) |
Memory types | fact / preference / instruction / feedback / decision / insight | auto-extracted facts | โ | observations + wiki links |
Time-aware search | โ natural language dates | โ ๏ธ REST only, not in MCP tools | โ | โ recent_activity |
Token efficiency | โ progressive disclosure | โ | โ | โ build_context traversal |
Import / Export | โ JSON | โ ZIP (JSON + JSONL) | โ | โ Markdown (human-readable) |
License | AGPL-3.0 / Commercial | Apache 2.0 | Apache 2.0 | AGPL-3.0 |
Where competitors have a real edge:
OpenMemory โ auto-extracts memories from raw conversation text; no need to decide what to store manually; good import/export
mcp-memory-service โ richer web UI (graph visualization, quality scoring, 8 tabs); more permissive license (Apache 2.0); multiple transport options (stdio, SSE, HTTP)
basic-memory โ 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
When to pick Memlord:
You want zero-config local embeddings โ ONNX model ships with the server, no Ollama or external API needed
You run a multi-user team server with proper OAuth 2.1 auth and invite-based workspaces
You want a production-grade database (PostgreSQL) that scales beyond a single machine's SQLite
You manage memories explicitly โ store exactly what matters, typed and tagged, not everything the LLM decides to extract
You want a self-hosted Web UI with full CRUD and JSON export, without a cloud subscription
๐ Quickstart
๐ณ Docker
cp .env.example .env
docker compose upHTTP server (multi-user, Web UI, OAuth)
# 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
memlordOpen http://localhost:8000 for the Web UI. The MCP endpoint is at /mcp.
๐ How It Works
Each search request runs BM25 and vector KNN in parallel, then merges results via Reciprocal Rank Fusion:
flowchart TD
Q([query]) --> BM25["BM25\nsearch_vector @@ websearch_to_tsquery"]
Q --> EMB["ONNX embed\nparaphrase-multilingual-MiniLM-L12-v2 ยท 384d ยท local"]
EMB --> KNN["KNN\nembedding <=> query_vector\ncosine distance"]
BM25 --> RRF["RRF fusion\nscore = 1/(k+rank_bm25) + 1/(k+rank_vec)\nk=60"]
KNN --> RRF
RRF --> R([top-N results])โ๏ธ Configuration
All settings use the MEMLORD_ prefix. See .env.example for the full list.
Variable | Default | Description |
|
| PostgreSQL connection URL |
|
| Server port |
|
| Public URL for OAuth (HTTP mode) |
|
| JWT signing secret (HTTP mode) |
Set MEMLORD_BASE_URL to your public URL and change MEMLORD_OAUTH_JWT_SECRET before deploying.
๐ ๏ธ MCP Tools
Tool | Description |
| Save a memory (idempotent by content); raises on near-duplicates; optional |
| Hybrid semantic + full-text search; returns snippets by default |
| Search by natural-language time expression; returns snippets by default |
| Paginated list with type/tag filters |
| AND/OR tag search |
| Fetch a single memory by name with full content (expired included) |
| Update content, type, tags, metadata, or expiry by name (and optionally rename) |
| Delete by name |
| Move a memory to a different workspace |
| List workspaces you are a member of (including personal) |
| Read-only consolidation candidates: similar memory pairs, expired and expiring-soon memories |
The dream MCP prompt walks the client LLM through a full consolidation pass over the
dream_report output: classify similar pairs (duplicate / complementary / conflict), merge
into insight memories, retire superseded ones via expires_at โ never destructively.
Workspace management (create, invite, join, leave) is handled via the Web UI.
๐ป System Requirements
Python 3.12
PostgreSQL โฅ 15 with pgvector extension
uv โ Python package manager
๐จโ๐ป Development
pyright src/ # type check
ruff format . # format
pytest # run tests
alembic-autogen-check # verify migrations are up to date๐ License
Memlord is dual-licensed:
AGPL-3.0 โ free for open-source use. If you run a modified version as a network service, you must publish your source code.
Commercial License โ for proprietary or closed-source deployments. Contact sergey@memlord.com or dmitry@memlord.com to purchase.
Available Tools
11 toolsdelete_memoryADestructive
Delete a memory by name. Pass workspace to disambiguate if the name exists in multiple workspaces.
Inputs: name (required), workspace. Returns: name, success
dream_reportARead-only
Candidates for memory consolidation: similar pairs, expired and expiring memories.
Read-only. The report only proposes candidates โ reviewing and acting on them
(merge, supersede, extend, delete) is done via the regular memory tools.
Similar pairs are always within a single workspace, ordered by similarity.
Use the dream prompt for the full guided consolidation procedure.
Inputs: max_pairs, workspace, similarity_threshold. Returns: expired, expiring_soon, similar_pairs
get_memoryARead-only
Fetch full content of a single memory by name.
Use only when you already know the name โ e.g. after retrieve_memory() or recall_memory() which return names in their results alongside compact snippets. Do NOT use for search โ use retrieve_memory() for semantic/text search or recall_memory() for time-based queries like 'last week'. Unlike search, this also returns expired memories (expires_at in the past) โ check expires_at to tell; extend it via update_memory to bring one back.
Inputs: name (required), workspace. Returns: Full memory record returned by get_memory MCP tool.
list_memoriesARead-only
Browse all memories ordered by creation date (newest first). Returns full content (not snippets). Use to enumerate or audit without a specific query.
Inputs: tag, page, page_size, memory_type. Returns: page, items, total, page_size
list_workspacesARead-only
List all workspaces you are a member of (personal + shared).
Inputs: no named parameters. Returns: result
move_memoryA
Move a memory to a different to_workspace.
name: name of the memory to move. workspace: name of the target workspace (must be a member with write access). from_workspace: disambiguate source if the name exists in multiple workspaces.
Inputs: name (required), to_workspace (required), from_workspace. Returns: name, created
recall_memoryARead-only
Search memories by time expression + semantics. Returns names + metadata only.
Examples: "last week", "yesterday", "about Python last month". Use get_memory(name=...) to fetch full content of a specific result. Pass workspace= to search only within a specific workspace.
Inputs: query (required), n_results, workspace, memory_type. Returns: items
retrieve_memoryARead-only
Hybrid semantic + full-text search. Returns names + metadata only.
Use get_memory(name=...) to fetch full content of a specific result. Pass workspace= to search only within a specific workspace.
Inputs: query (required), limit, workspace, memory_type, +1 more. Returns: result
search_by_tagARead-only
Find memories by exact tag match. Returns all results (no pagination).
operation="AND" (default): memory must have ALL specified tags. operation="OR": memory must have AT LEAST ONE of the specified tags. Tags are case-insensitive. Use retrieve_memory() for semantic/text search or list_memories(tag=...) to browse a single tag with pagination.
Inputs: tags (required), operation. Returns: page, items, total, page_size
store_memoryAIdempotent
Save a new memory. Idempotent: returns existing if content already stored.
name: human-readable name, unique within the workspace. workspace: name of the workspace to store into. Omit to store as a personal memory. force: skip near-duplicate check and store unconditionally. expires_at: optional UTC expiry; after it passes the memory is hidden from reads.
Inputs: name (required), content (required), memory_type (required), tags, +4 more. Returns: name, created
update_memoryB
Update an existing memory identified by name. Only provided fields are changed.
new_name: rename the memory to this name. workspace: disambiguate if the name exists in multiple workspaces. expires_at: set or extend the UTC expiry; omit to leave it unchanged.
Inputs: name (required), memory_type (required), tags, content, +4 more. Returns: name, created
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 11 tools
Retrieval tools (retrieve_memory, recall_memory, get_memory, list_memories, search_by_tag) overlap in purpose, but descriptions clearly distinguish semantic/text search, time-based search, direct name lookup, browsing, and exact tag search. CRUD, workspace, and consolidation tools are clearly separate.
Almost all tools follow a consistent snake_case verb_noun pattern (store_memory, update_memory, retrieve_memory, etc.). The one outlier is dream_report, which is noun-based rather than verb-based, but the set remains predictable overall.
11 tools is well-scoped for a memory management server. Each tool appears to cover a distinct operation, and the count sits comfortably within the typical 3-15 range without obvious bloat.
Core memory lifecycle is covered: store, get, update, delete, move, search, list, and expiry handling. Notable gaps remain: there is no create/delete workspace tool despite list_workspaces, and no tool to add or remove tags despite search_by_tag, which could leave agents unable to set up tag-based searches.
Maintenance
Related MCP Connectors
Cloud-hosted MCP server for durable AI memory
Hosted memory for AI agents over MCP. One memory shared by all your agents.
An MCP memory server. One memory your agents share โ across models, devices and apps.
Related MCP Servers
AlicenseAqualityFmaintenanceAn MCP server that integrates with mem0.ai to help users store, retrieve, and search coding preferences for more consistent programming practices.9661Apache 2.0- AlicenseBqualityDmaintenanceProvides dynamic short-term and long-term memory management with keyword-based relevance scoring, time-decay models, and trigger-based recall. Optimized for Chinese language support with jieba segmentation.211BSD 3-Clause

Memory Nexusofficial
AlicenseNot gradedqualityDmaintenancePersistent memory and handoff intelligence layer for MCP agents. Most memory servers retrieve text โ Memory Nexus compounds operational context, learning from usage and progressively synthesizing observations into higher-order intelligence across sessions and tools.MIT- FlicenseNot gradedqualityDmaintenanceProvides persistent AI agent memory using a local vector database for long-term semantic storage and short-term session scratchpads. It enables low-latency memory operations including search, storage, and bulk management without external cloud dependencies.-