Engraphis
Local-first memory system for AI coding agents with full inspection
Visit engraphis.com ↗What is Engraphis?
Engraphis provides durable, scoped memory for AI agents that work across coding sessions and repositories. Every fact returned includes its source, history, and recall reasoning attached. The system runs locally by default as a free open-core engine with a self-hosted WebUI dashboard, letting developers inspect the complete recall network, trace how memories were retrieved, and see how facts change over time.
Built with Python and designed for coding agents, Engraphis tracks memory with provenance, maintains bi-temporal history so superseded facts stay inspectable, and offers MCP tools for integration. A Pro tier adds hosted analytics, automation, and team collaboration features. The dashboard visualizes the recall graph in real time, showing stations, links, and ranking signals as the agent retrieves context.
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 Engraphis automatically. Evidence: GitHub Coding-Dev-Tools/engraphis; 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