MemoryMesh

SQLite for AI memory. Persistent memory layer for MCP agents and coding copilots — local-first, zero cloud, works in 5 minutes.

See it in action: Claude Code remembering project decisions across sessions.

Up and running in 5 minutes

pip install memorymesh-mcp
cp config.example.yaml ~/.memorymesh/config.yaml
# edit config.yaml — point at your folders
memorymesh index ~/Documents
memorymesh search "how did I configure the debounce"

Wire it into Claude Desktop. Find the config file at:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

• Windows: %APPDATA%\Claude\claude_desktop_config.json

• Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "memorymesh": {
      "command": "uv",
      "args": [
        "run",
        "--directory", "/absolute/path/to/memory-mesh",
        "memorymesh", "start"
      ]
    }
  }
}

Restart Claude Desktop. The 15 tools appear automatically.

Related MCP server: NOUZ MCP Server

Why it exists

Every AI conversation starts from zero. Claude doesn't know which architecture decision you made last week. Cursor doesn't remember the bug you fixed yesterday. The context dies when the session ends.

Mem0 requires a cloud account. Zep needs a running server and a database. LangMem ties you to the LangChain ecosystem. None of them speak MCP natively.

MemoryMesh runs entirely on your machine. It indexes your files into a local SQLite + ChromaDB store and exposes them through 15 MCP tools. It never touches the network unless you configure a connector. Any MCP client — Claude Desktop, Cursor, your own agent — gets persistent memory with one config change.

How it works

The indexer watches your files, chunks them with format-aware parsers, and stores embeddings locally. The search engine fuses dense and sparse results, then a cross-encoder reranker scores the candidates.

                   ┌──────────────────────────────┐
  MCP clients ───▶ │         MemoryMesh           │
(Claude Desktop,   │  ┌────────────────────────┐  │
 Cursor, agents)   │  │ MCP Tools (FastMCP):   │  │
                   │  │  search_memory         │  │
                   │  │  list_sources          │  │
                   │  │  get_document          │  │
                   │  │  index_now             │  │
                   │  └──────────┬─────────────┘  │
                   │             ▼                 │
                   │     Search Engine             │
                   │   dense + BM25 → RRF          │
                   │             │                 │
                   │   ┌─────────┴──────────┐      │
                   │   ▼                    ▼      │
                   │ ChromaDB            BM25      │
                   │ (embeddings)     (sparse)     │
                   │   ▲                    ▲      │
                   │   └──────── Indexer ───┘      │
                   │                ▲              │
                   │           Watchdog            │
                   └────────────────┬──────────────┘
                                    ▼
                             Your filesystem

Indexing: file watcher detects changes → SHA-256 dedup skips unchanged files → parser (txt/md/pdf/docx/code/obsidian/email/calendar/browser) → chunker (tree-sitter for code, by-heading for markdown, recursive for text) → sentence-transformers embeddings → ChromaDB + BM25.

Search: query → query expansion (lexical variants + HyDE) → parallel dense + sparse search → Reciprocal Rank Fusion (k=60) → bge-reranker-v2-m3 reranker → top-k results with path, preview, score, and metadata.

RAG (optional): ask_memory → search_memory retrieval → Ollama generate() → grounded answer with cited sources.

What's included

MemoryMesh ships with hybrid search (dense embeddings + BM25 + RRF + cross-encoder reranker), hot/warm/cold memory tiers with configurable forgetting decay, and an episodic event timeline. 47 connectors pull data from Jira, Notion, GitHub, Slack, email, browser history, Spotify, and more. 15 MCP tools expose everything to any MCP-compatible client. A real-time file watcher re-indexes changed files within seconds, without a manual trigger.

MCP Tools

Once running, these tools are available to any MCP-compatible client:

All tools are backwards-compatible — new fields are added without changing existing signatures.

How MemoryMesh compares

How MemoryMesh compares to similar projects:

MCP native means it was built for MCP from day one — not bolted on after. The 15 tools follow additive versioning — new fields are added without removing existing ones.

Per-agent permissions means per-client identity, ACL by source and operation, token-bucket rate limiting, and token revocation are built into the core — not added as middleware.

Configuration

Everything lives in config.yaml. See config.example.yaml for a fully commented reference. Key highlights:

sources:
  - name: documents
    path: ~/Documents
    recursive: true
    extensions: [.txt, .md, .pdf, .docx]

  - name: projects
    path: ~/Projects
    recursive: true
    extensions: [.py, .js, .ts, .go, .rs, .md]

  - name: obsidian
    path: ~/obsidian-vault
    source_type: obsidian     # activates wikilink + frontmatter parser

  - name: emails
    path: ~/Mail
    source_type: email        # parses .mbox files

embeddings:
  model: all-MiniLM-L6-v2    # swap to paraphrase-multilingual-MiniLM-L12-v2 for PT/EN

search:
  default_top_k: 10
  hybrid:
    enabled: true
  reranker:
    enabled: true             # cross-encoder reranker (recommended)
    model: BAAI/bge-reranker-v2-m3
  query_expansion:
    enabled: true
    n_lexical_variants: 1

# Optional: local LLM for ask_memory tool + HyDE query expansion
ollama:
  enabled: false              # set true after: ollama pull llama3
  model: llama3

server:
  transport: stdio            # stdio | streamable-http

Global ignore list protects sensitive paths by default: .env, *.key, id_rsa*, secrets/, .ssh/, .aws/, .git/, node_modules/.

Benchmarks

Benchmark results will be published here. Scripts are already in benchmarks/ and runnable locally — contributions with reproducible numbers are welcome.

• bench_indexing.py — indexing throughput (chunks/s, MB/s) on a synthetic corpus

• bench_search_latency.py — p50/p95/p99 search latency across hybrid/dense/sparse modes

• bench_embedding_models.py — speed vs. quality comparison across three embedding models

Privacy & security

Three commitments that do not change across versions:

1. No data leaves your machine. No telemetry. No external API calls unless you explicitly opt in — and even then, there is a WARNING in the log.

2. HTTP listener binds to 127.0.0.1 only by default. Exposing to other interfaces requires an explicit config override.

3. Logs never contain document content or queries in cleartext. The audit log records query hashes, not queries.

Encryption at rest is available as of v0.8.0. Run memorymesh keygen to generate a key, then enable encryption.enabled: true in config.yaml. The SQLite metadata store can be exported as an encrypted backup with memorymesh backup.

Roadmap

Full details in ROADMAP.md.

Troubleshooting

• UnicodeDecodeError on a text file — MemoryMesh tries UTF-8, UTF-8 BOM, cp1252, latin-1 in order. If a file still fails, it is logged and skipped.

• Watcher doesn't fire on a network drive / WSL mount — set watcher.use_polling: true in config.yaml.

• Tesseract not found — install it system-wide and ensure it is in PATH. Windows: UB-Mannheim installer.

• Embedding model mismatch after changing config — run memorymesh reindex --all. The CLI refuses to start if the model ID stored in ChromaDB does not match the config.

Contributing

Contributions are welcome — bug reports, new connectors, integration examples, and documentation improvements all help. Open an issue to discuss before submitting a large PR.

Acknowledgements

Architecture informed by studying LlamaIndex, LangChain, PrivateGPT, AnythingLLM, MemGPT, and Haystack — understanding what each does well and what it does not. And to chroma-mcp and the MCP Python SDK for showing what MCP-native looks like in practice.

MIT. See LICENSE.