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

What is 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

Overview of cass_memory_system

What it is

cass-memory is a procedural memory system for AI coding agents. It transforms scattered session history from multiple agents into persistent, cross-agent memory. The system implements a three-layer cognitive architecture: Episodic Memory (raw session logs), Working Memory (structured session summaries), and Procedural Memory (distilled rules with confidence tracking). This allows every agent to learn from every other agent's experience.

Key features

  • Cross-Agent Learning: Sessions from all AI coding agents (Claude Code, Cursor, Codex, Aider, etc.) feed a unified knowledge base. A pattern discovered in one agent is automatically available to others.
  • Confidence Decay System: Rules have a 90-day half-life; confidence halves every 90 days without revalidation. One harmful mark counts 4× as much as one success. Rules progress through maturity stages: candidate → established → proven.
  • Anti-Pattern Learning: Bad rules are automatically inverted into warnings (anti-patterns) after multiple harmful marks, warning future agents away from the same mistake.
  • Scientific Validation: New rules are validated against historical session data before acceptance. Rules without evidence are flagged as candidates.
  • Graceful Degradation: The system works even when components are missing (no cass, no playbook, no LLM, or offline).

Use cases

  • AI coding agents: Get relevant rules and historical context before starting any task.
  • Developers: Build institutional memory that persists across tools and sessions.
  • Teams: Share patterns discovered by any team member's AI assistant.
  • Power users: Create sophisticated workflows that leverage cross-agent learning.

Getting started

Install via one-liner (Linux/macOS): bash curl -fsSL 'https://raw.githubusercontent.com/Dicklesworthstone/cass_memory_system/main/install.sh?$(date +%s)' | bash -s -- --easy-mode --verify Or via package managers: bash # macOS/Linux (Homebrew) brew install dicklesworthstone/tap/cm # Windows (Scoop) scoop bucket add dicklesworthstone https://github.com/Dicklesworthstone/scoop-bucket scoop install dicklesworthstone/cm For agents, the essential command is: bash cm context '' --json See the repository README for full quickstart instructions.

License and pricing

Open source. The license is not stated in the repository metadata (NOASSERTION).

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/dicklesworthstonecass-memory-system.svg)](https://yunodb.com/tools/dicklesworthstonecass-memory-system?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/dicklesworthstonecass-memory-system?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/dicklesworthstonecass-memory-system.svg" alt="Featured on YunoDB" height="20"></a>