causal-memory

Name: causal-memory Review
Item: causal-memory
Rating: 3.0
Author: Aaron Matthews

Skill Development Usable

Works inClaude Code

Usable Scanned — metadata only

Enables AI agents to learn from past decisions and outcomes without losing causal context during memory compression, reducing repeated mistakes and improving…

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Ask Claude to analyze past code decisions and their outcomes to avoid repeating mistakes.
Generate patterns from agent decisions that led to successful deployments vs. failed attempts.
Find root causes of recurring bugs by examining causal chains of previous code changes.

101 starsApache-2.0 (commercial OK)FreeQuick setup

Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Why it matters

Enables AI agents to learn from past decisions and outcomes without losing causal context during memory compression, reducing repeated mistakes and improving decision quality over time.

Best for

AI system builders implementing long-running agents or autonomous workflows that need persistent learning across compressed memory cycles.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/JingxuanC/causal-memory

By JingxuanC

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

claude plugins install JingxuanC/causal-memory

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

After installing, paste this into Claude:

Analyze past code decisions and their outcomes to avoid repeating mistakes

CostFree

Trust Signals Auto-scanned

Stars101Contributors6Last updated2026-10-16LicenseApache-2.0 (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-10-22 · scanner v1

Community Pulse Emerging

Discussed on Hacker News

When is causal broadcast not enough for causal memory? — Hacker News · 19 pts
When is causal broadcast not enough for causal memory? — Hacker News · 7 pts
CIT – Autonomous Cognitive Architecture with Persistent Causal Memory — Hacker News · 1 pts

3 mentions across 1 sources

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 80 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

Things to check

Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

3/5

Versatility

3/5

Reliability

3/5

Security

3/5

Overall score3.00 / 5.00 UsableEvaluatedOct 2026

Scored from trust signals (evidence-eval-v1): 80 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

← Back to the Claude Observatory