mmnto-ai/totem
The persistent memory and context layer for AI agents.
The persistent memory and context layer for AI agents.
npx skills add mmnto-ai/totemThe persistent memory and context layer for AI agents.
Rust hexagonal-architecture framework for AI agents — skill system, tool registry, two-tier memory (ring + persistent), and serializable lifecycle events
Recently updated agent-skill-related GitHub repository: PublicDotCom/claw-skill-public-dot-com.
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
One toolkit, every agent — drop decentralized, all-TEE, OpenAI-compatible Chutes.ai inference into Claude, Hermes, OpenClaw, Codex, or any OpenAI-compatible client.
Auto harness engineering meta-repo: discuss → curate → bootstrap a context-engineered project for Claude Code, Cursor, Copilot, and other AI coding agents.
Claude skills for Jujutsu VCS