Stars
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Python bindings for access to the on-device model at the core of Apple Intelligence through the Foundation Models framework
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
Skills for Real Engineers. Straight from my .claude directory.
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
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. 🫶
The best-benchmarked open-source AI memory system. And it's free.
Security Scanner for Agent Skills
Secure Node.js Execution Without a Sandbox A lightweight library for secure Node.js execution. No containers, no VMs — just npm-compatible sandboxing out of the box.
OpenShell is the safe, private runtime for autonomous AI agents.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.