Dicklesworthstone/cass_memory_system
Procedural memory for AI coding agents: transforms scattered session history into persistent, cross-agent memory so every agent learns from every other
Based on the README, here's a technical summary: Implements a three-layer cognitive architecture—episodic (raw cass search logs), working (diary summaries), and procedural (confidence-scored playbook rules)—with automatic anti-pattern inversion and 90-day decay halving to prevent stale guidance. Runs on Bun with deterministic reflection fallback when LLM unavailable, validates new rules against historical session evidence before acceptance, and exposes memory via CLI with JSON output for agent integration and optional MCP server.
275 stars.
Stars
275
Forks
34
Language
TypeScript
License
—
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Dicklesworthstone/cass_memory_system"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
kayba-ai/agentic-context-engine
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
MemMachine/MemMachine
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory...
knowns-dev/knowns
The memory layer for AI-native development — giving AI persistent understanding of your software...
rexdivakar/HippocampAI
HippocampAI — Autonomous Memory Engine for LLM Agents
MehulG/memX
A real-time shared memory layer for multi-agent LLM systems.