Trending AI repositories
Tracked daily across the agentic ecosystem. Velocity is computed from our own snapshot history — collecting the first week of data now; repos are linked to the startups behind them.
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
Command Code AI
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.
Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.
TokenSpeed is a speed-of-light LLM inference engine.
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.
DeepSeek Web browser extension: AI agent workspace with MCP tools, memory, Skills, automation, web search, and conversation export.
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer.
Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.
Debug your AI agents
Token efficient Claude Code full Python rebuild. AI Coding Agent in 260K LoC pure Python. Up to 200X Cost Saving!
AI Agent Team scaffold for Claude Code — 19 roles collaborate through stage gates, enforced by mandatory skills + blocking hooks + DoD checklists. Spec-driven change folders, SIT-audited code reviews, 4-layer hook defense, multi-LLM (DeepSeek/Doubao/Qwen/MiniMax). Tracks: Web · WeChat Mini Program · Apple native (macOS/iOS). 中文/EN README.
Real-time token, cost, and AI limits widget with multi-device sync for Claude Code, Codex, OpenCode, Hermes, OpenClaw, Cursor, Antigravity and more. | 为 AI Tools 打造的即时Token、成本与限额监控桌面组件，支持多设备同步
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.
End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, metering, and full-stack observability. AI quality gating: prompt anchoring, CLIP consistency, AV sync auto-rescue.
让 AI 住在你 MacBook 的刘海里 · 零依赖开箱即用 · 多引擎并行的桌面 AI 伴侣（Swift 6 / SwiftUI / macOS 14+）
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
企业级 AI 资源纳管平台，提供统一 AI网关，纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型，并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表，帮助企业精准控制成本、量化 ROI，高效治理 AI 资产。
帮你的 Claude Science 一键接入你自己的 API：DeepSeek / 通义千问 / 智谱 GLM / Kimi / MiniMax / 小米 MiMo / 硅基流动 / OpenRouter / 任意 OpenAI·Anthropic 兼容端点
deepseek标配coding agent、原生支持模型路由、CodeGraph代码图谱、OCR截图识别、自动上下文压缩、最佳工作模式选择，workflow等功能，从根本上节省Token
Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.
把零散的 Token Plan、Coding Plan、大模型 API 额度聚合成一个虚拟 Plan，一键接入 Claude Code、Claude Desktop App、OpenClaw、OpenCode 等工具 —— 省钱！省 Token！完全本地运行！ Bundle your scattered Token Plan, Coding Plan, and LLM API quotas into a single virtual Plan, and plug it into Claude Code, Claude Desktop App, OpenClaw, OpenCode, and more.
Godot-MCP — Model Context Protocol (MCP) integration for the Godot Engine. AI tools for the Godot Editor in C#, with cloud connection to ai-game.dev. Apache-2.0.
Carbon Code 是一款类似 Claude Code 的代码开发工具，也是中国第一个基于 DeepSeek 的代码开发工具，Token 成本节省 90% 以上。它可以实现自动任务拆分、自动开发、MCP 测试，以及与 Claude、Codex 等多 Agent 协作，能力接近 Claude Sonnet 4.6
A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory management.
一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。
Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.