by caspianmoon · MCP Server · ★ 693
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Evidence-first local memory for AI agents with temporal versions, admission policies, citations, explainable recall, MCP, and audit tooling.
| Stars | 693 |
| Forks | 60 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 58.819926173556/100 |
| Open Issues | 2 |
| Last Updated | 2026-08-17 |
| Created | 2024-11-07 |
| Platforms | mcp, python |
| Est. Tokens | ~13k |
These tools work well together with memoripy for enhanced workflows:
Looking for a memoripy alternative? If you're comparing memoripy 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.
A memory OS that makes your OpenClaw agents more personal while saving tokens.
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context ac
Hypernetworks that update LLMs to remember factual information
One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosyst
Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It
Explore other popular mcp server tools:
memoripy is Evidence-first local memory for AI agents with temporal versions, admission policies, citations, explainable recall, MCP, and audit tooling.. It is categorized as a MCP Server with 693 GitHub stars.
memoripy is primarily written in Python. It covers topics such as ai, llm, memory.
You can find installation instructions and usage details in the memoripy GitHub repository at github.com/caspianmoon/memoripy. The project has 693 stars and 60 forks, indicating an active community.
memoripy is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to memoripy on Agent Skills Hub include EverMemOS, agentic-context-engine, automem. 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: