PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

A list of LLMs Tools & Projects

Claude Code skill that transforms vague prompts into structured, expert-level prompts using 7 research-backed frameworks (CO-STAR, RISEN, RISE, TIDD-EC, RTF, CoT, CoD)

Work with LLMs on a local environment using containers

Python SDK for running evaluations on LLM generated responses

A very fast, very minimal prompt optimizer

电子鹦鹉 / Toy Language Model

Awesome QA Skills — a bilingual (zh/en) AI testing Agent Skills library for Codex, Cursor, Claude Code, Kiro, OpenCode, and Trae. Ships 4 testing workflows and 25 testing-type skills (58 skill folders with language parity): independently installable, composable, and eval-ready with skill-up. Covers requirements, strategy, cases, API/performance/sec

Auto-tuned launcher for GGUF models on llama.cpp / ik_llama.cpp — OpenAI-compatible server with multi-GPU tensor-split, MoE expert placement, measured flag tuning (AI Tune), hardware-matched HuggingFace downloads, and crash recovery. An Ollama alternative for multi-GPU rigs.

SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.

Auto-tuned launcher for GGUF models on llama.cpp / ik_llama.cpp — OpenAI-compatible server with multi-GPU tensor-split, MoE expert placement, measured flag tuning (AI Tune), hardware-matched HuggingFace downloads, and crash recovery. An Ollama alternative for multi-GPU rigs.

This is a repository for an nocode object detection inference API using the Yolov3 and Yolov4 Darknet framework.

Autonomous AI agent that contributes to open source — discovers repos, analyzes code, generates fixes, and submits PRs

QA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude Code, Cursor, Copilot, etc.).

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

Action library for AI Agent

This is a repository for an nocode object detection inference API using the Yolov4 and Yolov3 Opencv.

可同时输入多个初版提示词，开启多轮自动优化，连续得到高分后得到最终结果。

PocketGroq is a powerful Python library that simplifies integration with the Groq API, offering advanced features for natural language processing, web scraping, and autonomous agent capabilities. Key Features Seamless integration with Groq API for text generation and completion Chain of Thought (CoT) reasoning for complex problem-solving and more.

50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.

Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.

MCP server for AI image generation and editing with automatic prompt optimization and quality presets (fast/balanced/quality). Powered by Gemini (Nano Banana 2 & Pro).

AI接口自动化测试 Skill：面向 Python + pytest + requests，驱动 Codex / Claude Code 生成、维护和调试接口用例（AI API test automation skill for Python + pytest + requests）

A unified, modular framework for prompt optimization

A unified, modular Framework for Prompt Optimization

Open-source, bilingual AI video-prompt skill — rewrite ideas into model-ready text-to-video prompts. A portable Agent Skill (Claude Code, Codex, OpenClaw, Hermes); generate via Atlas Cloud — Seedance 2.0, Kling, Veo, Hailuo, Wan, Vidu, Gemini Omni, Grok Imagine.

Finish-First Autonomous Agent Loop for Claude Opus 4.7 – 2026 Edition

Deterministic, fail-open tool routing for Hermes Agent with an optional local-model fallback.

Best Prompt Engineering Tools for 2026 AI Workflow Optimization

Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically

Top 10 Claude Prompt Optimization Frameworks 2026

Spec2Case 是生产级 AI 测试用例生成智能体，支持图片/文本需求理解、人工确认、LangGraph 流程编排和 Excel 用例导出。

Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.

XMind Vault

Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.

A curated list of plugins for DeepSeek Harness (dsh) - DeepSeek Harness plugin ecosystem

SkillFoundry — a leading open-source project in the AI/LLM ecosystem.

Rust + CUDA inference engine for NVIDIA RTX PRO 6000 Blackwell and RTX 5090. Serves safetensors and GGUF over an OpenAI-compatible API, with per-device tuned defaults and speculative decode gated byte-identical to plain decode. Hosted instance: inference.tiyuvta.ai

StackQuadrant — a leading open-source project in the AI/LLM ecosystem.