SkillRL
[NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
[NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
The Python web framework for building apps.
Kubernetes AI Toolchain Operator
csghub-server is the backend server for CSGHub which helps user to manage datasets, modes, and also run Model Inference, Finetune and Application Spaces.
AI PC starter app for doing AI image creation, image stylizing, and chatbot on a PC powered by an Intel® Arc™ GPU.
A curated, multilingual library of 182 installable AI agent skills for end-to-end academic research—spanning literature discovery, scientific writing, grant development, bioinformatics, drug discovery, clinical research, machine learning, and data analysis.
A lightweight multilingual LLM
Plugin for agents to interact with Chatcut
JZSub: paste one video link and get back the highest-quality MP4 with its cover image and GPT-generated bilingual subtitles, automatically.
AI吟美-人工智能主播-Vtuber-桌宠-智能体
🔱 Vedic/Jyotish AI analysis toolkit | 吠陀占星AI分析工具包——从排盘开始,到以后的长期追问。支持所有可以挂载Skill的平台。感谢大家的支持。
Build fast and accurate GenAI apps with GraphRAG SDK at scale 🌟
Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server.
Enterprise-grade AI resource management platform with a unified AI gateway and token scheduling, managing mainstream models like OpenAI, Azure, Claude and DeepSeek, plus centralized registration and distribution of MCP tools and Skills. Supports dual internal/external pricing, cost attribution, unified authentication, security auditing and efficiency reports to help enterprises control costs, quantify ROI and govern AI assets.
mac code — Claude Code, but it runs on your Mac for free. 35B AI agent at 30 tok/s via Apple Silicon flash-paging. $0/month.
Github Profile analyzer or analyser and reviewer tool. Gives review based on first 100 repos and only includes those forks in which user has contributions to avoid fake results | #1 profile analyzer on github
TRACER: replace 90%+ of your LLM classification calls with a traditional ML model. Formal parity guarantees. Self-improving.
"AgentSpace: Human + Agents. One Team. One Workspace"
☁️ The fastest HTML to markdown convertor on GitHub. Optimized for LLMs and supports streaming.
Expose llms-txt to IDEs for development
Claude Code CLI integration for Unreal Engine 5.7 - Get AI coding assistance with built-in UE5.7 documentation context directly in the editor.
An Agent Skill that makes an LLM write in ASD-STE100 Simplified Technical English. Rules, approved word list, and a check tool.
Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models.
Agentic testing for agentic codebases