Lists (1)
Sort Name ascending (A-Z)
Stars
KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.
将冰冷的离别化为温暖的 Skill,欢迎加入数字生命1.0!Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
PrismMl Bonsai vs Qwen3.5 Benchmark
Agent skill to turn any arxiv paper into a working implementation
Self-hosted Kanban board with browser terminals for AI coding agents. Hook-driven auto-tracking — manage tmux/zellij sessions and git worktrees from one board.
"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)
AI agents running research on single-GPU nanochat training automatically
A framework-agnostic, git-native standard for defining AI agents
Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.
Use Claude Code, Cursor CLI or Codex on mobile and web with CloudCLI (aka Claude Code UI). CloudCLI is a free open source webui/GUI that helps you manage your Claude Code session and projects remotely
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
An understudy watches. Then performs.
omo; the best agent harness - previously oh-my-opencode
OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
🚀 「大模型」1小时从0训练67M参数的视觉多模态VLM!🌏 Train a 67M-parameter VLM from scratch in just 1 hours!
Implementation of the MetaController proposed in "Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning" from the Paradigms of Intelligence team at Google
Self-referential self-improving agents that can optimize for any computable task
OpenYak — open-source local AI agent for Windows, macOS, and Linux. A private, BYOK alternative to Claude Code, Claude for Work, and OpenAI Codex with 20+ tools, 100+ models via OpenRouter, MCP, an…
Adaptive Test-time Learning and Autonomous Specialization
A PPM (Partial Per Matching) Word & Letter predictor in Node. Thanks to @google for the ppm original code