Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
npx add-skill MemTensor/MemOSSelf-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
Source: https://github.com/MemTensor/MemOS
Discovered during the daily awesomeskills.dev agent-skill hunt.
Fabric-specific project context template — six-file context system + medallion scaffold + CI/CD patterns for Microsoft Fabric data engineering projects. Scaffolded via /init-fabric-project Claude Code skill.
Agentic skill for operation research
Search, read, and download curated agent skills via MCP for fast discovery and local use in agent workflows
Composable pi coding agent with MCP, LSP, agent chains, prompt presets, and local eval telemetry
Codex skill for wrong-road exploration, friction analysis, quarry/pivot synthesis, and inspectable creative thinking.
ExAutomatica shared components — reusable tools (crawler, auto-responder, etc.) consumed by the agent fleet via OpenClaw skill packs.