Ranked by total stars
Most starred
The established names across every category, newest star count first. This board ignores growth entirely, so it includes repositories whose momentum we cannot yet measure.
-
7951A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.—stale★ 13616
-
7952给 AstrBot 的可落地 AI 记忆与生活层:五类记忆、混合检索、遗忘治理、情绪边界、自主生活循环。不覆盖人格。+18/daymeasured★ 13646
-
7953基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat+5.0/wkmeasured★ 13529
-
7954Self improving agents through iterations+1.0/wkmeasured★ 13522
-
7955Distribute and run transformer encoders with a single file.—stale★ 13516
-
7956Auto-updated leaderboard of trending claude-skills and AI agent repos, refreshed every 15 minutes+2.0/wkmeasured★ 13523
-
7957This repository includes codes for comprehensive tutorials in Control / Robotics Engineering. The link of YouTube video tutorials are mentioned in description.flatmeasured★ 13516
-
7958Privacy-first, local-only barcode scanning SDK for Web, Node.js, React, iOS and Android with multi-format decoding, realtime tracking, batch scanning, and native/WASM engines.−1.0/daymeasured★ 13521
-
7959Подписки для обхода ограничений на территории Российской Федерации. Софт для сбора и проверки публичных конфигураций.+4.0/wkmeasured★ 13534
-
7960金蝶云星空 MCP Server:让 Claude/Cursor 等 AI 助手用自然语言直接查询、操作 ERP(采购/销售/库存/财务/附件等 101 个工具)+1.4/daymeasured★ 13532
-
7961fintech wallet platform same to cloud-native microservices system designed to power digital financial operations—stale★ 13517
-
7962Moo — fnOS 第三方应用中心:三源同步 / 智能归类 / 安装更新 / 多渠道通知 / GitHub 加速+3.1/daymeasured★ 13534
-
7963DSH RedTeam 模式:把 DeepSeek Harness 变成红队作战指挥台——一个靶标名称拉起信息收集/漏洞检测/漏洞利用/内网渗透四个角色,资产与战果实时落入本地 SQLite 事实库(仅供已授权测试)—stale★ 13520
-
7964The Boring query platform - Connect and query anything+1.0/wkmeasured★ 13514
-
7965Zero-config entity resolution feeding a durable identity layer: messy records from any source become stable golden entities, a Customer 360 with provenance, merge/split and audit. Fellegi-Sunter beats hand-tuned Splink. Arrow-native/Rust, 250M rows in 11.2 min. Python + edge TypeScript (WASM), SQL-native in Postgres & DuckDB, 97 MCP tools + REST.+1.0/wkmeasured★ 13526
-
7966Local security intelligence for CVE triage - 40 data sources and 41 tools, risk scores and an MCP server for AI agents, all in native Rust. Private by default.+3.1/daymeasured★ 13533
-
7967🍟 麦麦省钱助手 —— 麦当劳中国官方 MCP 的省钱点餐 Agent Skill:官方 calculate-price 实时核价 + 券组合优化 + 沉默成本体检与多单用券排程,官方券/套餐/团购券/积分四渠道同口径算终局价。免登录在线试算。−2.0/wkmeasured★ 13520
-
7968A self-hosted web GUI for managing Linux servers, Docker containers, apps, files, services and backups.+6.0/wkmeasured★ 13526
-
7969DSH最稳定,最高效的破甲插件:token 级重试环 + 三层技能路由(形态/父/叶)+ 分级 prefill + 拒答阶梯 L0–L3 + finish_reason 四路分流 + 请求体级整形—stale★ 13520
-
7970Agent Skill for 15–90 s motion graphics, promo and character videos: reference analysis, seven stage gates, Remotion and HyperFrames engines.+1.0/daymeasured★ 13527
-
7971Kumoss turns natural-language requests into compliant, plan-validated Terraform/OpenTofu pull requests - with drift correction, policy gates, and human review. Multicloud, bring-your-own LLM.+5.2/wklifetime avg★ 13526
-
7972GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.−4.0/wkmeasured★ 13419
-
7973Turn repeated Claude Code, Codex, and Cursor prompts into reusable slash commands. Local Python history extractor + Agent Skill.—stale★ 13421
-
7974Claude Code Prompt Mechanism Visualizer — Electron desktop app+2.0/wkmeasured★ 13437
-
7975Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,865 tok/s; with 64 GB RAM 3,410 tok/s prefill · 84 tok/s decode. New: opt-in uncensored mode (runtime abliteration, no new weights).+4.0/wkmeasured★ 13423
-
7976A self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini compatible endpoints. Routes requests dynamically across 12+ LLM platforms with automatic fallback, key scheduling, rate-limit tracking and encrypted credential storage.flatmeasured★ 13419
-
7977Chat with SEC filings for any investment questionflatmeasured★ 1346
-
7978FinTech AI Solution for SMEs to calculate financial values—stale★ 13417
-
7979fintech app—stale★ 13417
-
7980Legal flags a risk. Finance flags another. We connect and cite. Open-source forensic M&A due diligence: 13 AI agents read your data room across 9 domains (Legal, Finance, Commercial, Tech, Cyber, HR, Tax, Regulatory, ESG), cross-reference findings no single reviewer connects, and trace every one to an exact page & quote.+1.0/wkmeasured★ 13419
-
7981Autonomous multi-agent crypto intelligence & trading ecosystem for Robinhood Chain L2 (EVM #4663) operated via Discord Command Center, Terminal TUI, REST API, & Telegram—stale★ 13417
-
7982A Codex skill that delegates work to ChatGPT on the web.—stale★ 13418
-
7983Highly Scalable RecSys ML & Data system+1.0/wkmeasured★ 13420
-
7984An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qwen3.8-27B runs up to 1.9x faster than llama.cpp.+4.0/wkmeasured★ 13425
-
7985云鲲自动化渗透控制台:功能介绍、使用流程、新增与优化、界面预览。当前仓库仅含文章与截图,暂无产品源码。−1.0/wkmeasured★ 13420
-
7986Kapso by Leeroo: Long-running agents that optimize AI and Data systems, and learn from every experience. #1 open-source on MLE-Bench; ALE-Bench; RelBench—stale★ 13420
-
7987The agentic pentesting environment that lives on your machine. AI agent teams, visual workflows and your own tools, 100% local.+6.3/daymeasured★ 13438
-
7988Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under MIT license.flatmeasured★ 13314
-
7989Agent Skill for complex work: research before asking, ask before planning, plan before building, verify before delivering, independent review before calling it done. Plain text, no runtime.—stale★ 13316
-
7990[COLMW'26 Spotlight] AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Draftersflatmeasured★ 13320
-
7991SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A3B FP8 ~240 tok/s, 27B-int4 hybrid GDN+Mamba, Gemma4 26B/31B AWQ, 256K ctx. 321 patches: TurboQuant k8v4 KV, MTP/DFlash spec-decode, FULL cudagraph, hybrid GDN. vLLM pin dev424 + Control Center GUI.flatmeasured★ 13318
-
7992Unofficial Python client for Kalshi's prediction markets API+1.0/wkmeasured★ 13314
-
7993Open-source Stellar and Soroban API for peer-to-peer USDC settlement, wallet authentication, orders, and escrow coordination.—stale★ 13320
-
7994Local-first observability CLI for Codex and Claude Code—stale★ 13318
-
7995Skill pack for Claude Code that helps you monitor and troubleshoot your K8s clusters superintelligently−1.0/wkmeasured★ 13318
-
7996Your Google services (RCS, Gemini, Google Wallet, DroidGuard timestamps, Play Integrity attestations, Play Protect Certification) read on-device. No internet, root required.+3.6/daymeasured★ 13335
-
7997Android interception tool for component communication and attack-surface mapping+1.0/wkmeasured★ 13321
-
7998A fast, keyboard-driven HTTP intercepting proxy and pentesting toolkit for the terminal built for humans and AI agents alike.+3.0/wkmeasured★ 13324
-
7999An open source plugin for enabeling claude to gain offensive pentesting capabilities+2.0/wkmeasured★ 13311
-
8000Skills related to Data Engineering Work for Claude Code+3.0/wkmeasured★ 13338