Claude starts cold.
Retavyn fixes that.

Every Claude session forgets everything — what you worked on, what decisions you made, what you learned. Retavyn gives Claude persistent memory across sessions, automatically.

The problem

Claude is stateless by design. Every new session, it starts fresh — no knowledge of your project history, your naming conventions, the bug you fixed last Tuesday, or the architectural decision you spent three hours debating.

You end up re-explaining context constantly. Retavyn stores what matters and injects it back automatically at session start. You talk to Claude normally. It remembers.

What it looks like

Remember that we moved auth to Cloud Run — the VM was too expensive.

What do you know about our billing pipeline?

Journal today's session.

What have I been working on this week?

No commands to learn. Just talk to Claude.

How it works

Store memories naturally

Tell Claude what to remember in plain language. Memories are stored in a local PostgreSQL database — on your machine, under your control.

Automatic injection at session start

A hook runs at the start of every Claude Code session, dumping all memories into context automatically. No manual steps.

Hybrid search when you recall

Full-text search plus semantic similarity via pgvector — recall works whether you use the exact words or just the general concept.

Works with claude.ai too

Run in HTTP mode with a Cloudflare tunnel and connect to claude.ai as a remote MCP server. Same memories, any interface.

Memory tools

remember

Store a new memory with optional category tagging.

recall

Search memories by keyword, category, or semantic similarity.

update_memory

Edit an existing memory in place.

forget

Delete a memory by ID.

ingest_path

Bulk-import memories from a file or directory.

backfill_embeddings

Generate embeddings for existing memories to enable semantic search.

Stack

Python + FastMCP — lightweight MCP server, minimal dependencies.

PostgreSQL 18 + pgvector — local Docker container, full-text and vector search out of the box.

OpenAI / Cohere — optional embedding providers for semantic search via text-embedding-3-small or embed-english-v3.0.

Claude Code hooks — session startup and post-tool hooks wire everything together automatically.

Cloudflare Tunnel — exposes the MCP server over HTTPS for claude.ai integration without opening firewall ports.

Runs locally. No cloud account required. Your memories stay on your machine.

Claude starts cold.Retavyn fixes that.