BrainLayer
Persistent memory for MCP agents using semantic search and knowledge graphs
Visit brainlayer.etanheyman.com ↗What is BrainLayer?
BrainLayer solves AI agent amnesia by providing persistent memory across sessions. It stores architecture decisions, debugging insights, and preferences in a local SQLite database, then retrieves them via hybrid semantic and keyword search. Agents can search 700K+ knowledge chunks, explore entity relationships in a knowledge graph, and maintain context through restarts and context window compactions.
Designed for developers using Claude Code and MCP-compatible agents, BrainLayer includes a 17-tool MCP surface, a 13-tool Python transport, and an optional macOS companion app called BrainBar. Installation is simple: `pip install brainlayer`. The maker says it was built with Claude Code.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered BrainLayer automatically. Evidence: GitHub EtanHey/brainlayer; repo has AGENTS.md, CLAUDE.md. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces
Manage teams of AI agents to run your business from one dashboard
Persistent memory for AI agents across Claude Code, Cursor, and MCP clients