TIMPS Memory
A 22-layer memory system for AI coding agents that persists across sessions
Visit timps-website.vercel.app ↗What is TIMPS Memory?
TIMPS Memory is a cognitive architecture that gives AI coding agents like Claude Code, Cursor, and Windsurf persistent memory across restarts. Unlike single-layer vector databases, it implements 22 memory layers modeled on human cognition—episodic memory, semantic graphs, procedural memory, and sheaf-theoretic consistency checking—along with 25 deterministic intelligence tools that detect contradictions and track context.
Designed for developers who work with AI coding assistants, TIMPS runs fully local with Ollama, requires no API keys, and integrates as an MCP server. It captures architectural decisions, coding patterns, past bugs, and project conventions so agents can maintain continuity within a codebase across multiple sessions.
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 TIMPS Memory automatically. Evidence: GitHub Sandeeprdy1729/timps; repo has AGENTS.md. View source.
Similar vibe-coded apps
Turn your codebase into a queryable knowledge graph for AI coding assistants
Operating layer for AI coding agents with skills, memory, planning and security
Self-hosted AI agent with persistent memory and multi-platform messaging
Open-source AI platform for short-form video and animated series creation
Open-source canvas workbench for AI-powered image and video creation
Community marketplace for DeepSeek Harness Web themes, pets, plugins
Open-source, AI-native knowledge base with Evernote-style interface