Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)
- adaptive-computation
- early-exiting
- kv-cache
- llm
142,273 visible repositories in the index
1,393–1,416 of 1,816 · Most stars
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)
使用 agent-browser-cli 进行浏览器感知与控制。适用于标签页扫描/切换、页面 JS 执行、Cookie、CDP、contentSettings、截图、文件上传、下拉框点击、tmwd_cdp_bridge 初始化和 Web 工具排障
Menu bar app for macOS, Windows and Linux that cuts Claude Code and ChatGPT Codex token costs by ~50%
Have a conversation with ChatGPT using your voice, and have it talk back.
ParseBench - A Document Parsing Benchmark for AI Agents
A proxy server for multiple ollama instances with Key security
✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models
Turn PDFs and EPUBs into audiobooks; subtitles or videos into dubbed videos (including translation), and more. For free. Pandrator uses local models, including voice-cloning (instant, RVC-enhanced, XTTS fine-tuning) and LLM processing. It aspires to be a user-friendly app with a GUI, an installer and all-in-one packages.
Agent-first Creative Workspace
Turn stateless LLMs into a stateful, compounding AI agent. Local-first persistent memory, quantitative decision screens, and governance harness across Claude Code, Antigravity, Cursor, and VS Code. Own the state. Rent the intelligence.
162 MCP tools for AI-powered Godot 4 development. Scene, animation, 3D, physics, particles, audio, shader, input simulation, runtime analysis, navigation, testing & more. $15 one-time.
A Next.js-based AI writing assistant supporting multiple LLM APIs (OpenAI, Claude, Gemini, etc.) with rich style customization features to help content creators improve quality and efficiency.
Create a web based terminal on any website - great for games, animations and real world apps!
Active Learning for Text Classification in Python
An open-source LLM based automatically daily news collecting workflow showcase powered by Agently AI application development framework.
Turn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and Open Source
OpenAI, Anthropic, and Gemini-compatible proxy.
An AI framework for generating and modding osu! beatmaps for all gamemodes from spectrogram inputs.
Free, open-source alternative to Weavy AI, Krea Nodes, Freepik Spaces & FloraFauna AI — node-based AI workflow builder for generative image & video pipelines
A high-performance HTTP/2-enabled proxy server designed specifically to enable Cursor IDE's Composer to use DeepSeek's and OpenRouter's language models. This proxy translates OpenAI-compatible API requests to DeepSeek/OpenRouter API format, allowing Cursor's Composer and other OpenAI API-compatible tools to seamlessly work with these models.
AI 视频解说 Agent 技能包:自动切镜、看画面写解说词、配音混音合成成片,可导出剪映/CapCut 草稿,无需 GPU | Agent skills for narrated video recaps & CapCut drafts
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server that visually maps out the execution plan of any AI coding agent as an interactive flowchart/graph before the agent begins writing code.
基于Stable Diffusion优化的AI绘画模型。支持输入中英文文本,可生成多种现代艺术风格的高质量图像。| An optimized text-to-image model based on Stable Diffusion. Both Chinese and English text inputs are available to generate images. The model can generate high-quality images in several modern art styles.
The official Redis MCP Server is a natural language interface designed for agentic applications to manage and search data in Redis efficiently