Official website & docs: https://memtomem.com
Give your AI agent a long-term memory.
memtomem turns your markdown notes, documents, and code into a searchable knowledge base that any AI coding agent can use. Write notes as plain .md files — memtomem indexes them and makes them searchable by both keywords and meaning.
flowchart LR
A["Your files\n.md .json .py"] -->|Index| B["memtomem"]
B -->|Search| C["AI agent\n(Claude Code, Cursor, etc.)"]
First time here? Follow the Getting Started guide — you'll have a working setup in under 5 minutes.
| Problem | How memtomem solves it |
|---|---|
| AI forgets everything between sessions | Index your notes once, search them in every session |
| Keyword search misses related content | Hybrid search: exact keywords + meaning-based similarity |
| Notes scattered across tools | One searchable index for markdown, JSON, YAML, Python, JS/TS |
| Vendor lock-in | Your .md files are the source of truth. The DB is a rebuildable cache |
ollama pull nomic-embed-text # local embeddings (~270MB, free)
uv tool install memtomem # or: pipx install memtomemNo GPU? Pick OpenAI in the wizard — see Embeddings.
mm init # 8-step wizard (or: mm init -y for CI)The wizard picks your embedding model, points at the folder you want indexed, and registers memtomem with your AI editor.
"Call the mem_status tool" → confirms the server is connected
"Index my notes folder" → mem_index(path="~/notes")
"Search for deployment" → mem_search(query="deployment checklist")
"Remember this insight" → mem_add(content="...", tags=["ops"])
Other install options
Project-scoped (per-project isolation):
uv add memtomem && uv run mm init # all commands need `uv run` prefixNo install (uvx on demand):
claude mcp add memtomem -s user -- uvx --from memtomem memtomem-serverSee MCP Client Setup for Cursor / Windsurf / Claude Desktop / Gemini CLI.
- Hybrid search — BM25 keyword + dense vector + RRF fusion in one query
- Semantic chunking — heading-aware Markdown, AST-based Python, tree-sitter JS/TS, structure-aware JSON/YAML/TOML
- Incremental indexing — chunk-level SHA-256 diff; only changed chunks get re-embedded
- Namespaces — organize memories into scoped groups with auto-derivation from folder names
- Maintenance — near-duplicate detection, time-based decay, TTL expiration, auto-tagging
- Web UI — visual dashboard for search, sources, tags, sessions, health monitoring
- MCP tools —
mem_dometa-tool routes all non-core actions incoremode for minimal context usage
| Package | Description |
|---|---|
| memtomem | Core — MCP server, CLI, Web UI, hybrid search, storage |
| memtomem-stm | STM proxy — proactive memory surfacing via tool interception |
| Guide | Description |
|---|---|
| Getting Started | Install, setup wizard, first use |
| Hands-On Tutorial | Follow-along with example files |
| Interactive Notebooks | Jupyter notebooks for the Python API — hello, indexing, sessions, tuning, LangGraph |
| User Guide | Complete feature walkthrough |
| Configuration | All MEMTOMEM_* environment variables |
| Embeddings | ONNX, Ollama, and OpenAI embedding providers |
| LLM Providers | Ollama, OpenAI, Anthropic, and compatible endpoints |
| MCP Client Setup | Editor-specific configuration |
| Agent Memory Guide | Sessions, working memory, procedures |
| Web UI | Visual dashboard |
| Hooks | Claude Code hooks for auto-indexing |
See CONTRIBUTING.md for setup instructions and the contributor guide.
Apache License 2.0. Contributions are accepted under the terms of the Contributor License Agreement.