agent-as-a-judge
👩⚖️ Agent-as-a-Judge: The Magic for Open-Endedness
👩⚖️ Agent-as-a-Judge: The Magic for Open-Endedness
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.
AgentX 致力于让小白也能无门槛通过自然语言打造属于自己的 Agent。AgentX 采用了自研 MCP 网关,模型高可用组件打造高可用
🐹 An Intelligent Phone That Never Sleeps.
A Visio diagram-reconstruction toolkit inspired by ppt-master, rebuilding flowcharts, architecture diagrams and paper figures from images into editable .vsdx files, with SVG/PNG export.
End-to-end documentation to set up your own local & fully private LLM server on Debian. Equipped with chat, web search, RAG, model management, MCP servers, image generation, and TTS.
Model Context Protocol (MCP) to enable AI LLMs to trade using MetaTrader platform
Figma to React Converter
HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
Streamystats is a statistics service for Jellyfin, providing analytics and data visualization.
Browse the web, directly from Cursor etc.
Local Anthropic-compatible AI gateway with cheap-first routing, quality gates, safe model handoffs, and an embedded cost dashboard.
收录可以免费使用能力较强的AI的合集,尽量筛选较为稳定的平台,但希望合理预期,免费,稳定,高性能是不可能三角A list of highly capable AI models you can use for free. We’ve tried to select the most stable platforms, but keep in mind the "impossible triangle": you can’t always have free, stable, and high performance all at once.
A self-hosted, multi-user, agent-first Agent workbench.
A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.
Use any web browser or WebView as GUI, with Zig in the backend and modern web technologies in the frontend, all in a lightweight portable library.
A toolkit for applying LLMs to sensitive, non-public data in offline or restricted environments
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
Multi-AI agent terminal collaboration tool
Materials for the LLM Engineering Essentials course
A minimal autonomous code-agent CLI built with Qwen Code
Hypernetworks that update LLMs to remember factual information