9.3k repos tracked
updated 3d ago
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.

Biggest movers New & notable Most starred 9.3k repositories
  1. 7951
    A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.
    TypeScript created 4mo ago pushed 2mo ago agent-frameworkagent-loopagent-verification
    —
    stale
    ★ 136
    16
  2. 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。
    JavaScript created 11d ago pushed 5d ago agplai-companionastrbot
    +18/day
    measured
    ★ 136
    46
  3. 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
    Python created 6mo ago pushed 4d ago agentai-agentai-automation
    +5.0/wk
    measured
    ★ 135
    29
  4. 7954
    Self improving agents through iterations
    Python created 11mo ago pushed 4d ago agent-learningagent-memoryagentic-workflows
    +1.0/wk
    measured
    ★ 135
    22
  5. 7955
    Distribute and run transformer encoders with a single file.
    Rust created 12mo ago pushed 2mo ago edge-aiembeddingsencoder
    —
    stale
    ★ 135
    16
  6. 7956
    Auto-updated leaderboard of trending claude-skills and AI agent repos, refreshed every 15 minutes
    Python created 5mo ago pushed 7d ago ai-agentsai-codingai-development
    +2.0/wk
    measured
    ★ 135
    23
  7. 7957
    This repository includes codes for comprehensive tutorials in Control / Robotics Engineering. The link of YouTube video tutorials are mentioned in description.
    HTML created 10mo ago pushed 2mo ago control-engineeringcontrol-engineering-educationcontrol-systems
    flat
    measured
    ★ 135
    16
  8. 7958
    Privacy-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.
    TypeScript created 8mo ago pushed 7d ago androidbarcodecomputer-vision
    −1.0/day
    measured
    ★ 135
    21
  9. 7959
    Подписки для обхода ограничений на территории Российской Федерации. Софт для сбора и проверки публичных конфигураций.
    created 9mo ago pushed 14d ago aggregatorblacklistbypass
    +4.0/wk
    measured
    ★ 135
    34
  10. 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)
    Python created 7mo ago pushed 14d ago ai-agentai-toolsclaude
    +1.4/day
    measured
    ★ 135
    32
  11. 7961
    fintech wallet platform same to cloud-native microservices system designed to power digital financial operations
    TypeScript created 4mo ago pushed 56d ago cloud-walletfinancialfinancial-wallet
    —
    stale
    ★ 135
    17
  12. 7962
    Moo — 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
    Go created 45d ago pushed 4d ago app-storedockerfnos
    +3.1/day
    measured
    ★ 135
    34
  13. 7963
    DSH 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)
    JavaScript created 59d ago pushed 14d ago ai-agentattack-surfacedeepseek-harness
    —
    stale
    ★ 135
    20
  14. 7964
    The Boring query platform - Connect and query anything
    TypeScript created 12mo ago pushed 3mo ago agentic-aiaiclickhouse
    +1.0/wk
    measured
    ★ 135
    14
  15. 7965
    Zero-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.
    Python created 7mo ago pushed 4d ago data-cleaningdata-engineeringdata-matching
    +1.0/wk
    measured
    ★ 135
    26
  16. 7966
    Local 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.
    Rust created 22d ago pushed 6d ago artificial-intelligencecisa-kevcve
    +3.1/day
    measured
    ★ 135
    33
  17. 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。
    Python created 30d ago pushed 17d ago agent-skillagent-skillschinese
    −2.0/wk
    measured
    ★ 135
    20
  18. 7968
    A self-hosted web GUI for managing Linux servers, Docker containers, apps, files, services and backups.
    TypeScript created 29d ago pushed 3d ago cloudcloud-osgui
    +6.0/wk
    measured
    ★ 135
    26
  19. 7969
    DSH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
    JavaScript created 15d ago pushed 13d ago ai-agentanti-censorshipcli
    —
    stale
    ★ 135
    20
  20. 7970
    Agent Skill for 15–90 s motion graphics, promo and character videos: reference analysis, seven stage gates, Remotion and HyperFrames engines.
    JavaScript created 38d ago pushed 8d ago agent-skillsai-videoclaude-code
    +1.0/day
    measured
    ★ 135
    27
  21. 7971
    Kumoss 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.
    Python created 6mo ago pushed 4d ago agentic-aiai-agentsai-infrastructure
    +5.2/wk
    lifetime avg
    ★ 135
    26
  22. 7972
    GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.
    Python created 4mo ago pushed 28d ago agent-memoryai-safetybenchmark
    −4.0/wk
    measured
    ★ 134
    19
  23. 7973
    Turn repeated Claude Code, Codex, and Cursor prompts into reusable slash commands. Local Python history extractor + Agent Skill.
    Python created 51d ago pushed 11d ago agent-skillsai-agentsanthropic
    —
    stale
    ★ 134
    21
  24. 7974
    Claude Code Prompt Mechanism Visualizer — Electron desktop app
    HTML created 8mo ago pushed 16d ago ai-toolsanthropicclaude
    +2.0/wk
    measured
    ★ 134
    37
  25. 7975
    Qwen3.8-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).
    Python created 2mo ago pushed 24d ago 256k-contextcpu-offloadingdual-gpu
    +4.0/wk
    measured
    ★ 134
    23
  26. 7976
    A 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.
    TypeScript created 5mo ago pushed 26d ago ai-gatewayauto-routingdeveloper-tools
    flat
    measured
    ★ 134
    19
  27. 7977
    Chat with SEC filings for any investment question
    Python created 11mo ago pushed 11mo ago aifinanceinvesting
    flat
    measured
    ★ 134
    6
  28. 7978
    FinTech AI Solution for SMEs to calculate financial values
    TypeScript created 4mo ago pushed 56d ago ai-solutionfintechfintech-ai
    —
    stale
    ★ 134
    17
  29. 7979
    fintech app
    TypeScript created 4mo ago pushed 56d ago appfintechfintech-agent
    —
    stale
    ★ 134
    17
  30. 7980
    Legal 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.
    Python created 8mo ago pushed 41d ago ai-agentsanthropicclaude
    +1.0/wk
    measured
    ★ 134
    19
  31. 7981
    Autonomous multi-agent crypto intelligence & trading ecosystem for Robinhood Chain L2 (EVM #4663) operated via Discord Command Center, Terminal TUI, REST API, & Telegram
    TypeScript created 2mo ago pushed 56d ago ai-agentmultiagentrobinhood
    —
    stale
    ★ 134
    17
  32. 7982
    A Codex skill that delegates work to ChatGPT on the web.
    JavaScript created 57d ago pushed 47d ago ai-agentsautomationchatgpt
    —
    stale
    ★ 134
    18
  33. 7983
    Highly Scalable RecSys ML & Data system
    Python created 8mo ago pushed 35d ago apache-flinkapache-sparkapche-kafka
    +1.0/wk
    measured
    ★ 134
    20
  34. 7984
    An 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.
    Python created 8mo ago pushed 7d ago agentaiai-agents
    +4.0/wk
    measured
    ★ 134
    25
  35. 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。
    Go created 25d ago pushed 12d ago aiagentaisecuritycybersecurity
    −1.0/wk
    measured
    ★ 134
    20
  36. 7986
    Kapso 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
    Python created 11mo ago pushed 12d ago ai-agentsautonomous-agentscoding-agents
    —
    stale
    ★ 134
    20
  37. 7987
    The agentic pentesting environment that lives on your machine. AI agent teams, visual workflows and your own tools, 100% local.
    TypeScript created 21d ago pushed 4d ago ai-agentsbug-bountyelectron
    +6.3/day
    measured
    ★ 134
    38
  38. 7988
    Find 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.
    Python created 7mo ago pushed 2mo ago agent-memoryaiai-agents
    flat
    measured
    ★ 133
    14
  39. 7989
    Agent 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.
    Python created 2mo ago pushed 2mo ago agent-skillsai-agentsclaude-code
    —
    stale
    ★ 133
    16
  40. 7990
    [COLMW'26 Spotlight] AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters
    Python created 3mo ago pushed 12d ago diffusion-language-modelsefficient-inferenceinference-server
    flat
    measured
    ★ 133
    20
  41. 7991
    SNDR 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.
    Python created 6mo ago pushed 39d ago awqconsumer-gpucuda
    flat
    measured
    ★ 133
    18
  42. 7992
    Unofficial Python client for Kalshi's prediction markets API
    Python created 9mo ago pushed 3mo ago algorithmic-tradingapi-clientfinance
    +1.0/wk
    measured
    ★ 133
    14
  43. 7993
    Open-source Stellar and Soroban API for peer-to-peer USDC settlement, wallet authentication, orders, and escrow coordination.
    TypeScript created 32d ago pushed 21d ago fintechnestjspayments
    —
    stale
    ★ 133
    20
  44. 7994
    Local-first observability CLI for Codex and Claude Code
    TypeScript created 2mo ago pushed 41d ago claude-codeclicodex
    —
    stale
    ★ 133
    18
  45. 7995
    Skill pack for Claude Code that helps you monitor and troubleshoot your K8s clusters superintelligently
    Shell created 6mo ago pushed 40d ago agentsaiclaude
    −1.0/wk
    measured
    ★ 133
    18
  46. 7996
    Your Google services (RCS, Gemini, Google Wallet, DroidGuard timestamps, Play Integrity attestations, Play Protect Certification) read on-device. No internet, root required.
    Kotlin created 35d ago pushed 4d ago androidattestationdroidguard
    +3.6/day
    measured
    ★ 133
    35
  47. 7997
    Android interception tool for component communication and attack-surface mapping
    JavaScript created 6mo ago pushed 17d ago androidandroid-securitybug-bounty
    +1.0/wk
    measured
    ★ 133
    21
  48. 7998
    A fast, keyboard-driven HTTP intercepting proxy and pentesting toolkit for the terminal built for humans and AI agents alike.
    Crystal created 4mo ago pushed 4d ago bugbountyclicrystal
    +3.0/wk
    measured
    ★ 133
    24
  49. 7999
    An open source plugin for enabeling claude to gain offensive pentesting capabilities
    Python created 7mo ago pushed 5mo ago ai-pentestingai-red-teamclaude
    +2.0/wk
    measured
    ★ 133
    11
  50. 8000
    Skills related to Data Engineering Work for Claude Code
    Shell created 9mo ago pushed 13d ago claudeclaude-codeclaude-skills
    +3.0/wk
    measured
    ★ 133
    38
← previous page 160 of 187 next →