mcp-memory-service
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/doobidoo/mcp-memory-service with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/doobidoo/mcp-memory-service'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/doobidoo--mcp-memory-service)HTML
<a href="/listings/doobidoo--mcp-memory-service"><img src="/api/listings/doobidoo--mcp-memory-service/badge.svg" alt="findsafeskills safety rating" /></a>Install
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 11 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- {
- "name": "mcp-memory-service",
- "owner": { "name": "doobidoo", "url": "https://github.com/doobidoo" },
- "plugins": [
- {
- "name": "mcp-memory-service",
- "source": "./claude-hooks",
- "description": "Semantic memory for Claude Code sessions"
- }
- ]
- }
README.md · README · 372 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # mcp-memory-service
- ## Persistent Shared Memory for AI Agent Pipelines
- Open-source memory backend for AI agents — **REST API, MCP, OAuth, CLI, dashboard**. One self-hosted service, every transport.
- Agents store decisions, share causal knowledge graphs, and retrieve
- context in 5ms — without cloud lock-in or API costs.
- **Works with LangGraph · CrewAI · AutoGen · any HTTP client · Claude Desktop · OpenCode**
- ---
- [](https://mcpmemory.services)
- [](https://opensource.org/licenses/Apache-2.0)
- [](https://pypi.org/project/mcp-memory-service/)
- [](https://pypi.org/project/mcp-memory-service/)
- [](https://pepy.tech/projects/mcp-memory-service)
- [](https://hub.docker.com/r/doobidoo/mcp-memory-service)
- [](https://github.com/doobidoo/mcp-memory-service/actions/workflows/ci.yml)
- [](https://github.com/doobidoo/mcp-memory-service)
- [](https://github.com/doobidoo/mcp-memory-service/graphs/contributors)
- [](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/remote-mcp-setup.md)
- [](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/oauth-setup.md)
- [](https://deepwiki.com/doobidoo/mcp-memory-service)
- [](https://glama.ai/mcp/servers/doobidoo/mcp-memory-service)
- Getting started: [English](https://mcpmemory.services/) · [Deutsch](https://mcpmemory.services/de/) · [Español](https://mcpmemory.services/es/) · [日本語](https://mcpmemory.services/ja/) · [简体中文](https://mcpmemory.services/zh-cn/) · [繁體中文](https://mcpmemory.services/zh-tw/) · [Français](https://mcpmemory.services/fr/) · [Português (Brasil)](https://mcpmemory.services/pt-br/) · [한국어](https://mcpmemory.services/ko/)
- ---
- <div align="center">
- <video src="https://mcpmemory.services/assets/videos/knowledge-graph-3d.mp4" poster="https://mcpmemory.services/assets/images/knowledge-graph-3d-poster.png" width="820" autoplay loop muted playsinline controls>
- <a href="https://mcpmemory.services/"><img src="https://mcpmemory.services/assets/images/knowledge-graph-3d.png" alt="3D knowledge graph — memories as a glowing, interactive galaxy" width="820"></a>
- </video>
- <p><em>▶ <a href="https://mcpmemory.services/">The 3D knowledge graph in motion</a></em> — every memory a glowing node, every relationship a curved edge.</p>
- </div>
- ---
- ## Why Agents Need This
- Your AI assistant forgets everything when you start a new chat. You spend 10 minutes re-explaining your architecture. **Again.** MCP Memory Service captures project context, architecture decisions, and code patterns automatically — new sessions start with everything already known.
- | Without mcp-memory-service | With mcp-memory-service |
- |---|---|
- | Each agent run starts from zero | Agents retrieve prior decisions in 5ms |
- | Memory is local to one graph/run | Memory is shared across all agents and runs |
- | You manage Redis + Pinecone + glue code | One self-hosted service, zero cloud cost |
- | No causal relationships between facts | Knowledge graph with typed edges (causes, fixes, contradicts) |
- | Context window limits create amnesia | Autonomous consolidation compresses old memories |
- **Key capabilities for agent pipelines:**
- - **Framework-agnostic REST API** — no MCP client library needed; the live endpoint list is at `/api/docs`
- - **Knowledge graph** — agents share causal chains, not just facts
- - **`X-Agent-ID` header** — auto-tag memories by agent identity for scoped retrieval
- - **`conversation_id`** — bypass deduplication for incremental conversation storage
- - **SSE events** — real-time notifications when any agent stores or deletes a memory
- - **Embeddings run locally via ONNX** — memory never leaves your infrastructure
- ---
- ## 🚀 Get Started in 60 Seconds
- > Not sure which setup fits? The **[Setup Guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/setup-guide.md)** walks you to the right path in under a minute.
- **1. Install:**
- ```bash
- pip install "mcp-memory-service[sqlite]"
- ```
- The `[sqlite]` extra brings the local ONNX embedding model. Without it, semantic
- search falls back to hash embeddings.
- <details>
- <summary><strong>Using uv instead of pip</strong></summary>
- Install the `memory` command into its own environment:
- ```bash
- uv tool install "mcp-memory-service[sqlite]"
- ```
- Or skip the install and let your client start the server through `uvx`:
- ```json
- {
- "mcpServers": {
- "memory": {
- "command": "uvx",
- "args": ["--from", "mcp-memory-service[sqlite]", "memory", "server"]
- }
- }
- }
- ```
- </details>
- **2. Configure your AI client:**
- <details open>
- <summary><strong>Claude Desktop</strong></summary>
- Add to your config file:
- - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
- - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
- - **Linux**: `~/.config/Claude/claude_desktop_config.json`
- ```json
- {
- "mcpServers": {
- "memory": {
- "command": "memory",
- "args": ["server"]
- }
- }
- }
- ```
- Restart Claude Desktop. Your AI now remembers everything across sessions.
- </details>
- <details>
- <summary><strong>Claude Code</strong></summary>
- ```bash
- claude mcp add memory -- memory server
- ```
- Restart Claude Code. Memory tools will appear automatically.
- </details>
- <details>
- <summary><strong>Agent pipelines (REST API — LangGraph, CrewAI, AutoGen, any HTTP client)</strong></summary>
- ```bash
- MCP_ALLOW_ANONYMOUS_ACCESS=true memory server --http
- # REST API running at http://localhost:8000
- ```
- Store a memory with `POST /api/memories`, search with `POST /api/search`, retrieve by tag
- with `POST /api/search/by-tag`. Send `X-Agent-ID: <id>` on a store request and the server
- tags the memory `agent:<id>`, which a tag search then scopes retrieval by.
- Worked examples per framework, the tag conventions and the async patterns:
- **[docs/agents/](https://github.com/doobidoo/mcp-memory-service/tree/main/docs/agents)**
- </details>
- <details>
- <summary><strong>OpenCode</strong></summary>
- ```bash
- MCP_ALLOW_ANONYMOUS_ACCESS=true memory server --http
- ```
- The plugin ships as repository files for the local plugin directory, so clone the
- repository once even if you installed from PyPI. Install steps, the `/memory` slash
- command and the endpoint override:
- **[opencode/README.md](https://github.com/doobidoo/mcp-memory-service/blob/main/opencode/README.md)**
- </details>
- <details>
- <summary><strong>Codex (automatic memory hooks)</strong></summary>
- Start the Memory Service HTTP API, then install the hooks from this repository:
- ```bash
- python3 codex/install_hooks.py
- ```
- Restart Codex and review the hooks with `/hooks`. They retrieve project context,
- capture new learnings, and checkpoint outcomes before compaction and at session end.
- See [Codex hook setup](codex/README.md) for prerequisites, authentication, and project-local installation.
- </details>
- <details>
- <summary><strong>claude.ai and ChatGPT (browser — Remote MCP)</strong></summary>
- Remote MCP puts persistent memory in the browser on any device, no desktop app required:
- OAuth 2.0 over HTTPS, self-hosted or cloud-hosted. Both claude.ai and ChatGPT
- (Developer Mode) connect to the same endpoint.
- Cloudflare Tunnel quick start, Let's Encrypt, nginx, Caddy and Docker production setups:
- **[Remote MCP Setup](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/remote-mcp-setup.md)** ·
- [5-minute tutorial](https://mcpmemory.services/blog/remote-mcp-tutorial.html)
- </details>
- <details>
- <summary><strong>Advanced: custom backends and team setup</strong></summary>
- ```bash
- git clone https://github.com/doobidoo/mcp-memory-service.git
- cd mcp-memory-service
- python scripts/installation/install.py
- ```
- Choose from **SQLite** (local, fast, single-user), **Cloudflare** (cloud, multi-device
- sync), **Hybrid** (5ms local reads with background cloud sync — recommended for
- production) or **Milvus** (dedicated vector DB: Lite file, self-hosted, or Zilliz Cloud).
- For self-hosted team setups, the Hybrid backend can sync to another **HTTP MCP Memory Service**
- instead of Cloudflare using `MCP_HYBRID_SECONDARY_BACKEND=http`.
- For long-lived services, prefer Docker Milvus or Zilliz Cloud over Milvus Lite —
- [why](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/milvus-backend.md#which-uri-to-use).
- </details>
- ---
- ## ⚡ Works With Your Favorite AI Tools
- - **Agent frameworks (REST):** LangGraph · CrewAI · AutoGen · OpenClaw/Nanobot · any HTTP client
- - **CLI and terminal (MCP):** Claude Code · Gemini CLI · OpenCode · Codex CLI · Goose · Aider · Amp
- - **Desktop and IDE (MCP):** Claude Desktop · VS Code · Cursor · Windsurf · Raycast · JetBrains · Zed
- - **Chat (MCP):** ChatGPT (Developer Mode) · claude.ai (Remote MCP over HTTPS)
- Full list, plus clients without OAuth such as Home Assistant:
- **[docs/integrations.md](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/integrations.md)**
- ---
- ## ✨ Features
- ### Store and retrieve context
- - 🧠 **Persistent memory** — Keep decisions, notes, and project context across sessions and agents.
- - 🔍 **Semantic and keyword search** — Combine vector search with BM25; use `mode="ranked"`
- to weigh recency, access frequency, and quality. An optional fallback cascade tries
- exact and tag matching when semantic results are sparse.
- - 🏷️ **Scoped retrieval** — Filter by tags with AND/OR matching, natural-language time
- ranges, and store partitions (`default`, `docs`, or `all` for cross-store search).
- - 📝 **Optional search summaries** — Request `summarize=true` for query-aware summaries
- with validated source references. Requires `MCP_SEARCH_SUMMARIZE_ENABLED=true`
- and a configured LLM provider; unavailable summaries fall back to raw results.
- [Search API and examples](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/mastery/api-reference.md)
- - 📄 **Document ingestion** — Import PDF, text, and Markdown with chunking for retrieval.
- Additional formats such as DOCX and PPTX require optional parsing tools.
- [Document ingestion guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/document-ingestion.md)
- ### Capture and maintain knowledge
- - ⚡ **Automatic session capture** — Configurable Claude Code hooks retrieve context and
- save session learnings; the local `memory_harvest` tool extracts decisions, bugs,
- conventions, and lessons from transcripts.
- [Hooks setup](https://github.com/doobidoo/mcp-memory-service/blob/main/claude-hooks/README.md) ·
- [Harvest configuration](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/mastery/configuration-guide.md)
- - 💡 **Autonomous consolidation** — Schedule clustering, compression, association discovery,
- and controlled forgetting. Insight cards surface patterns, trends, and knowledge gaps.
- [Consolidation guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/guides/memory-consolidation-guide.md)
- - 💭 **Beliefs and contradiction handling** — Derive confidence-scored beliefs from
- observations. Heuristic contradiction detection can mark older memories as superseded,
- hiding them from default retrieval while retaining them for explicit lookup.
- - 🤖 **Agent bootstrap profiles** — `memory_bootstrap_profile` assembles behavioral context
- for a new agent within a token budget, with optional task-aware retrieval.
- Requires `MCP_BOOTSTRAP_ENABLED=true`; profiles are not isolated by project.
- - 🧬 **Knowledge graph and entities** — Explore typed causal relationships in the interactive
- graph. 🔗 Entity extraction links @mentions, #tags, URLs, and file paths to a queryable entity graph.
- [Knowledge graph guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/features/knowledge-graph-dashboard.md)
- - 🏠 **Quality scoring** — Use your own OpenAI-compatible endpoint, including Ollama,
- LiteLLM, or vLLM.
- [Configuration guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/mastery/configuration-guide.md)
- ### Run locally and share across devices
- - 🔒 **Local-first storage** — Local ONNX embeddings and SQLite storage keep core memory
- operations on your infrastructure. Optional LLM features use the providers you configure.
- - ☁️ **Cloud or self-hosted sync** — Use Cloudflare or another MCP Memory Service instance
- as a Hybrid secondary. Separately enabled delta-sync exchanges changes between hosts;
- it is off by default.
- [Self-hosted sync guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/guides/self-hosted-sync-hub.md)
- - 📦 **Import, export, and migration** — Move memories through JSON import/export, including
- conversion of mem0 exports.
- [Import/export tools](https://github.com/doobidoo/mcp-memory-service/blob/main/scripts/sync/README.md) ·
- [mem0 migration guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/guides/mem0-import.md)
- - 💾 **Database backups** — Configure scheduled backups or trigger one manually through
- the HTTP API. Inspect backup status and available snapshots through the backup endpoints
- in the live API reference at `/api/docs`.
- - 📊 **Web dashboard** — Search, browse, visualize, and manage memories at `http://localhost:8000`.
- The dashboard has eight tabs — Dashboard, Search, Browse, Documents, Manage, Analytics,
- Quality, API Docs. [Two-minute walkthrough on YouTube](https://youtu.be/W34r8VFoSdQ) ·
- [Web Dashboard Guide](https://github.com/doobidoo/mcp-memory-service/wiki/Web-Dashboard-Guide)
- How it compares to Mem0, Zep and the MCP-native alternatives, benchmark results, and
- deployments people run in production: **[mcpmemory.services](https://mcpmemory.services)**
- ---
- ## 🛠️ Configuration Highlights
- ```bash
- memory launch # Start HTTP server in background (127.0.0.1:8000)
- memory launch --port 8192 # Custom port
- memory info # Status and health
- memory logs --lines 50 # Recent logs
- memory stop # Stop server
- ```
- These commands are optimized for fast startup and avoid loading heavy ML dependencies
- unless needed.
- > ⚠️ **Security note:** the server binds to `127.0.0.1` (localhost only) by default.
- > `--host 0.0.0.0` / `MCP_HTTP_HOST=0.0.0.0` exposes the API to your network — do that
- > only in trusted environments with authentication and firewall rules, or behind TLS
- > termination or a VPN overlay.
- Backends, embedding models, quality scoring and every environment variable:
- **[Configuration Guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/mastery/configuration-guide.md)**
- ---
- ## 📚 Documentation
- - **[Setup Guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/setup-guide.md)** – Decision tree and step-by-step paths
- - **[Agent Integration Guides](https://github.com/doobidoo/mcp-memory-service/tree/main/docs/agents)** – LangGraph, CrewAI, AutoGen, HTTP generic
- - **[Remote MCP Setup](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/remote-mcp-setup.md)** – claude.ai and ChatGPT via HTTPS + OAuth
- - **[Configuration Guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/mastery/configuration-guide.md)** – Backend options and customization
- - **[Architecture Overview](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/architecture.md)** – How it works under the hood
- - **[Knowledge Graph Dashboard](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/features/knowledge-graph-dashboard.md)** – Interactive graph visualization
- - **[Benchmarks](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/BENCHMARKS.md)** – LongMemEval, DevBench, LoCoMo, xerj agent-memory, with run commands
- - **[Migration Guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/MIGRATION.md)** – Upgrading between major versions
- - **[Troubleshooting](https://github.com/doobidoo/mcp-memory-service/tree/main/docs/troubleshooting)** – Common issues and solutions
- - **[Wiki](https://github.com/doobidoo/mcp-memory-service/wiki)** – Long-form guides and API reference
- - **[Full documentation index](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/README.md)** – Everything else
- Also listed on [Glama](https://glama.ai/mcp/servers/doobidoo/mcp-memory-service) and
- [Spark](https://spark.entire.vc/mcps/vb-mcp-memory-service).
- ---
- ## 📦 Releases
- Every release, with upgrade notes:
- [CHANGELOG.md](https://github.com/doobidoo/mcp-memory-service/blob/main/CHANGELOG.md) ·
- [GitHub Releases](https://github.com/doobidoo/mcp-memory-service/releases) ·
- [archived history](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/archive/CHANGELOG-HISTORIC.md)
- ---
- ## 🤝 Contributing
- We welcome contributions! See [CONTRIBUTING.md](https://github.com/doobidoo/mcp-memory-service/blob/main/CONTRIBUTING.md) for guidelines
- and [SECURITY.md](https://github.com/doobidoo/mcp-memory-service/blob/main/SECURITY.md) for reporting a vulnerability.
- Releases, good first issues and new Discussions are announced on our
- [Discord server](https://discord.gg/zrsNMEzmCj), which is also the place for informal chat.
- Claiming an issue, decisions and reviews stay on GitHub.
- Who authors this project, who holds copyright, and what every change passes before
- it reaches `main`: [AUTHORSHIP.md](https://github.com/doobidoo/mcp-memory-service/blob/main/AUTHORSHIP.md).
- **Quick Development Setup:**
- ```bash
- git clone https://github.com/doobidoo/mcp-memory-service.git
- cd mcp-memory-service
- pip install -e . # Editable install
- pytest tests/ # Run test suite
- ```
- ---
- ## Supporting the Project
- MCP Memory Service is maintained by one person. If it saves you or your company time,
- you can support its development via Ko-fi, Buy Me a Coffee or PayPal:
- [SPONSORS.md](https://github.com/doobidoo/mcp-memory-service/blob/main/SPONSORS.md).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.