The dashboard at localhost:37777 - browse, search, and manage your memories. View graph stats, vector metrics, storage savings, and performance analytics.
Sound familiar?
Every Claude Code session starts fresh. That bug you fixed last Tuesday? Gone. The auth flow you explained in detail? Forgotten. Your team's naming conventions? You'll explain them again.
- "We fixed this exact race condition last week..."
- "No, we use kebab-case for API routes, not camelCase..."
- "The database is Postgres, not MySQL. I told you yesterday..."
- Mnemonic remembers so you don't have to repeat yourself.
// What Mnemonic captures automatically:
Click any observation to explore its relationships - see what causes what, what fixes what, and how concepts evolve
You: Fix the authentication bug in the login flow
Claude: I'd be happy to help! Can you tell me about your authentication setup? What framework are you using? How is the login flow structured?
You: We use NextAuth with Postgres. The flow goes through /api/auth/... We talked about this last week...
5+ minutes of re-explaining context
You: Fix the authentication bug in the login flow
Claude: Looking at your NextAuth setup with Postgres, I see the issue is likely in the callback at /api/auth/[...nextauth].ts. Based on the session validation pattern we established, the fix is...
Instant context. Immediate value.
curl -sSL https://raw.githubusercontent.com/lukaszraczylo/claude-mnemonic/main/scripts/install.sh | bash
irm https://raw.githubusercontent.com/lukaszraczylo/claude-mnemonic/main/scripts/install.ps1 | iex
git clone https://github.com/lukaszraczylo/claude-mnemonic.git
cd claude-mnemonic
make build && make install
# Requires: Go 1.24+, Node.js 18+, CGO compiler
After install, open localhost:37777 to see the dashboard. Start a new Claude Code CLI session - memory is now active.
{{ req.name }}
{{ req.description }}
No Python. No external services. Semantic search with local embeddings is built-in.
{
"CLAUDE_MNEMONIC_WORKER_PORT": 37777,
"CLAUDE_MNEMONIC_CONTEXT_OBSERVATIONS": 100,
"CLAUDE_MNEMONIC_CONTEXT_FULL_COUNT": 25,
"CLAUDE_MNEMONIC_MODEL": "haiku"
}{{ config.name }}
{{ config.description }}
All settings can also be set via environment variables. See full documentation for all options.
Single binary. Fast startup, low memory. Zero runtime dependencies.
FTS5 full-text search. Single file database. Survives restarts.
Hybrid vector storage with LEANN-inspired selective embeddings. 60-80% storage reduction.
Two-stage retrieval: bi-encoder embeddings + cross-encoder reranking for high accuracy.
AST-aware code chunking respects function boundaries for Go, Python, and TypeScript.
Memory-efficient observation relationship graph with edge detection and hub identification.
Open Source
License
Data collection
Unlike anonymous packages, you can verify who built this, read every line of code, and reach out directly with questions.
Your security matters - that's why transparency is non-negotiable.