by JingxuanC · MCP Server · ★ 71
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.
| Stars | 71 |
| Forks | 8 |
| Language | Rust |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 54.4948118848624/100 |
| Open Issues | 12 |
| Last Updated | 2026-09-10 |
| Created | 2026-07-26 |
| Platforms | mcp, rust |
| Est. Tokens | ~22k |
These tools work well together with causal-memory for enhanced workflows:
Looking for a causal-memory alternative? If you're comparing causal-memory with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Composable mathematics tools for agents
A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec +
One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher
DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisio
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU
You.com skills and plugins for web search, content extraction, research, finance, and integration discovery, h
Explore other popular mcp server tools:
causal-memory is Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.. It is categorized as a MCP Server with 71 GitHub stars.
causal-memory is primarily written in Rust. It covers topics such as agent-memory, causal-inference, deepseek-harness.
You can find installation instructions and usage details in the causal-memory GitHub repository at github.com/JingxuanC/causal-memory. The project has 71 stars and 8 forks, indicating an active community.
causal-memory is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to causal-memory on Agent Skills Hub include jacobian, engramory, cetus. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: