Your AI forgets
everything. Fix that.

Local-first memory for MCP agents. Every decision, correction, and preference - indexed and searchable in <50ms. Nothing leaves your machine.

Get startedView source
claude ~ myproject
❯
⎇ main | 🔧 7284,291 tokens
🤖 Opus 4.6 (1M context)
The problem

Your AI has amnesia

Every session starts from zero. Your agent doesn't remember the architecture decision from last week, the debugging approach that worked, or that you prefer tabs over spaces.

You explain the same context dozens of times. It suggests patterns you've already rejected.

The fix

Install. Index. Search.

BrainLayer indexes your AI conversations into 284K searchable chunks. Hybrid search (semantic + keyword + knowledge graph) finds the right memory in <50ms.

SessionStart hooks auto-inject relevant context before you even ask. Everything stays on your machine. One SQLite file.

MCP tools

Seven tools. One protocol.

Core - what you use daily
brain_searchHybrid semantic + keyword + KG search across all memory
brain_storePersist decisions, learnings, corrections with tags and importance
brain_recallProactive context injection at session start
Advanced
brain_entityKnowledge graph entity lookup
brain_digestIngest large content, auto-extract entities and relations
brain_subscribeWatch for new matching memories in real time
brain_unsubscribeStop watching a subscription
Works with

Any MCP client

Claude Code
Claude Code
Cursor
Cursor
Zed
Zed
VS Code
VS Code
Codex
Codex
Kiro
Kiro
Gemini CLI
Gemini CLI
Getting started

Three steps

01

Install from PyPI

02

Configure MCP and index conversations

03

Start real-time indexing

Stop repeating yourself.

Three commands. Persistent memory. Your data stays yours.