BrainLayer — Persistent Memory for AI Agents
BrainLayer is a local-first memory layer that gives any MCP-compatible AI agent persistent memory across conversations. It indexes Claude Code session transcripts into a SQLite database with vector embeddings, enabling semantic search, task-aware retrieval, file history tracking, and session analysis. Everything runs locally — no cloud accounts, no API keys, no Docker. The enrichment pipeline uses local LLMs (Ollama/MLX) to generate 10-field metadata per chunk including summaries, tags, importance scores, and intent classification.
brainlayer
See it in action
Claude Codeopus-4.6
> Type your message...
0K+
Indexed chunks
0
MCP tools
0
Vector dimensions
0
KG entities
Built with
Key features
Hybrid Search
Semantic vectors (bge-large-en-v1.5) + FTS5 keyword search, fused with Reciprocal Rank Fusion.
Local LLM Enrichment
GLM-4.7-Flash generates summaries, tags, importance scores, and intent classification per chunk.
How it works
Conversation
CC sessions → JSONL
Indexing
Chunk + deduplicate
Embedding
bge-large 1024-dim
Hybrid Search
Vec + FTS5 + RRF
MCP Tools
7 tools for agents
Conversation
CC sessions → JSONL
Indexing
Chunk + deduplicate
Embedding
bge-large 1024-dim
Hybrid Search
Vec + FTS5 + RRF
MCP Tools
7 tools for agents
Get started
pip install brainlayerThe journey
01
The Problem
AI agents forget everything between sessions. Every architecture decision, debugging insight, and user preference — gone. Developers repeat themselves constantly, re-explaining context that should be remembered.
02
Single-File Architecture
Built on SQLite + sqlite-vec: one .db file stores everything. No Docker, no database servers, no cloud accounts. Hybrid search combines semantic embeddings (bge-large-en-v1.5, 1024 dims) with FTS5 keyword search via Reciprocal Rank Fusion.
03
MCP Integration
14 MCP tools organized into an Intelligence Layer (think, recall, store, sessions) and a Search Layer (search, context, file_timeline, operations, regression). Any MCP-compatible editor — Claude Code, Cursor, Zed, VS Code — gets instant memory.
04
Local LLM Enrichment
Every indexed chunk gets enriched with 10 metadata fields (summary, tags, importance, intent, symbols, epistemic_level, debt_impact, and more) using local LLMs — Ollama or MLX on Apple Silicon. Zero cloud dependency.
05
Scale: 268K+ Chunks
268,000+ conversation chunks indexed from 9 projects. Session-level analysis extracts decisions, corrections, and learnings. Regression detection tracks what changed since a file last worked.
Part of the ecosystem
VoiceLayer — Voice I/O for AI Coding Agents
2 MCP tools (voice_speak + voice_ask), 5 voice modes, whisper.cpp STT (~300ms), edge-tts, macOS Voice Bar widget, session booking. 236 tests. bunx voicelayer-mcp.
Golems - Autonomous AI Agents
Autonomous AI agent ecosystem — 11 packages + 4 external repos, 7 domain agents, 335K+ memory chunks, multi-LLM routing, Telegram integration. 912 tests.