basic-memory
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
Basic Memory is an MCP server that gives AI assistants persistent, searchable memory across conversations using plain Markdown files stored locally or synced via cloud. Instead of re-explaining your project context in every chat session, the AI reads and writes structured knowledge to files you control, creating a bidirectional knowledge graph that both humans and AI can edit. It supports semantic vector search, wikilink-based relations, and works with Claude Desktop, Claude Code, Cursor, Codex, VS Code, ChatGPT, and Obsidian. Available as a free local install (Python via uv) or a paid cloud service with cross-device sync.
Key Features
Use Cases
- 01Maintaining project documentation that your AI assistant can read and update across sessions
- 02Building a personal knowledge base of coding patterns, architecture decisions, and learnings
- 03Sharing team knowledge in real-time with cloud workspaces accessible to multiple developers
- 04Tracking technical decisions, observations, and relations between concepts in a graph structure
- 05Integrating AI-generated notes with existing Obsidian or Markdown workflows
- 06Enabling AI assistants to remember context about ongoing projects without manual re-explanation
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
basic-memory — FAQ
What is Basic Memory MCP server?+
Basic Memory is an MCP server that provides persistent, structured memory for AI assistants through Markdown files. It enables AI clients to read, write, and search your knowledge base so conversations can pick up where you left off without re-explaining context.
How do I install Basic Memory locally?+
Install via uv with 'uv tool install basic-memory --prerelease=allow', then add the MCP server configuration to your AI client's config file (e.g., Claude Desktop's claude_desktop_config.json). The --prerelease=allow flag is required because it depends on a FastMCP 4 pre-release.
Which AI clients work with Basic Memory?+
Basic Memory supports Claude Desktop, Claude Code, Codex CLI, Cursor, VS Code, ChatGPT (via Custom GPT actions), and Obsidian. Any MCP-compatible client can connect using stdio or https transport.
Does Basic Memory require API keys or external services?+
The local install is completely free and requires no API keys—it runs entirely on your machine with SQLite storage. Optional semantic search can use local FastEmbed models (no keys) or LiteLLM-backed providers like Cohere (requires API key). The cloud service requires a paid subscription ($15/month).
Is Basic Memory free or paid?+
Basic Memory offers two options: a free, open-source local install (AGPL-3.0 license) and a paid cloud service ($15/month with 7-day trial). Both use the same Markdown format and MCP tools; the cloud version adds cross-device sync, mobile access, and automatic backups.
What are the system requirements for local installation?+
You need Python 3.12+ installed via uv (the fast Python package manager). The server stores data in a local SQLite database by default, or optionally Postgres with Milvus for vector storage. No Docker is required for the standard SQLite setup.
How do I install basic-memory?+
Open the source repository on GitHub and follow its README. basic-memory is a mcp server — MCP Agents Market links you directly to the official repo.
Is basic-memory free?+
basic-memory is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.