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. 7551
    Real World DevOps Implementation Project on AWS
    Java created 10mo ago pushed 5d ago argocdcicddocker
    +5.0/wk
    measured
    ★ 180
    31
  2. 7552
    NaorisProtocol bot
    Python created 10mo ago pushed 49d ago naorisprotocol-botroadmapweb3
    —
    stale
    ★ 180
    18
  3. 7553
    Let your agents understand what's happening locally, in real time — every experience across a city, with times, prices, booking links and images
    created 46d ago pushed 23d ago agent-skillai-agentsclaude-skill
    —
    stale
    ★ 179
    20
  4. 7554
    The BotBus protocol: how a menu bar app on your computer and the companion apps on your phone and watch stay in sync — with public fixtures. BotBus lets you follow, approve and start Codex and Claude Code tasks from anywhere: https://botbus.io/en
    Swift created 42d ago pushed 30d ago ai-agentsandroidclaude-code
    —
    stale
    ★ 179
    19
  5. 7555
    Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as library / MCP server / HTTP cluster.
    Rust created 7mo ago pushed 11d ago agent-memoryai-agentsanthropic
    +2.0/wk
    measured
    ★ 179
    38
  6. 7556
    An open-source software platform for all-scenario wireless communication and sensing research
    C++ created 6mo ago pushed 46d ago airsimbeamformingckm
    —
    stale
    ★ 179
    18
  7. 7557
    从手机、平板或电脑浏览器继续 Codex App 会话,兼容官方登录、API 与自定义模型服务。Self-hosted browser access to your existing Codex chats, with local/SSH sessions, approvals and notifications.
    Python created 40d ago pushed 5d ago ai-agentscodexcodex-app
    +2.6/day
    measured
    ★ 179
    32
  8. 7558
    Wireshark-like forensic analysis for Model Context Protocol communications Capture, inspect, and investigate all HTTP requests and responses between your IDE and MCP servers
    JavaScript created 12mo ago pushed 6mo ago aauthai-agentai-agent-tools
    flat
    measured
    ★ 179
    7
  9. 7559
    An open-source inference engine for AI functions in SQL
    Python created 3mo ago pushed 4d ago ai-sqlarrowdatabase
    +5.0/wk
    measured
    ★ 179
    26
  10. 7560
    Robotics Data Toolkit | Convert between robotics dataset formats (RLDS, LeRobot v2/v3, Zarr, HDF5, Rosbag). Inspect, visualize, and analyze datasets. Works with HuggingFace Hub. Built for OpenVLA, Octo, LeRobot, and Diffusion Policy workflows.
    Python created 9mo ago pushed 23d ago data-qualitydata-quality-checksdataset-conversion
    —
    stale
    ★ 179
    20
  11. 7561
    Real-time HFT bot for Polymarket crypto Up/Down markets combining CLOB order books, Chainlink feeds and multi-exchange prices with TWAP and Black-Scholes probability models; paper mode and backtests.
    Python created 24d ago pushed 24d ago black-scholeschainlinkcrypto
    +2.9/day
    measured
    ★ 179
    31
  12. 7562
    An open research workbench for idea discovery, autonomous mathematics, and evidence-grounded rebuttals.
    Python created 43d ago pushed 31d ago ai-agentsclaudecodex
    —
    stale
    ★ 178
    19
  13. 7563
    面向 Codex、Claude Code 等 AI Agent 的医学绘图 Skill,基于可信证据制作医学插画、科普漫画与科研示意图,提供可编辑成果与审核记录。 · Evidence-backed medical illustration, comics and research figures for Codex, Claude Code and other AI agents, with editable output and review records.
    Python created 2mo ago pushed 30d ago agent-skillsclaude-codecodex
    —
    stale
    ★ 178
    19
  14. 7564
    pg0 - Zero-config PostgreSQL with pgvector
    Rust created 11mo ago pushed 4d ago embeddedpostgressqlite
    +2.0/wk
    measured
    ★ 178
    24
  15. 7565
    SaaS boilerplate/starter-kit in Go+React with Stripe integration, multi-tenant support, comprehensive features and AI-agent ready
    Go created 8mo ago pushed 23d ago ai-agentsgogolang
    flat
    measured
    ★ 178
    20
  16. 7566
    Flowpay — Payments Without Internet
    Kotlin created 4mo ago pushed 4d ago androidfintechindia
    +2.0/wk
    measured
    ★ 178
    24
  17. 7567
    Zero-code K8s sidecar for log sanitization. Detects secrets via Entropy Analysis, preserves JSON integrity, and redacts PII deterministically. 🛡️
    Go created 9mo ago pushed 5d ago devsecopsentropygdpr
    flat
    measured
    ★ 178
    21
  18. 7568
    ESP32 2.4 GHz SDR
    C created 32d ago pushed 4d ago esp32sdrzephyr-rtos
    +4.0/wk
    measured
    ★ 178
    25
  19. 7569
    🛡 Official AI Security Tool module for CVE-2026-75604 (Next.js Windows Unauthenticated Remote Code Execution) with safe in-app execution, deep vulnerability validation, and DevSecOps-ready security auditing workflows.
    created 41d ago pushed 20d ago ai-hackingai-security-toolcve-2026-75604
    flat
    measured
    ★ 178
    20
  20. 7570
    AgentCall lets AI Agents join meetings with voice, video & screen-share to build together. Supports Google Meet, Teams, Zoom (Beta)
    Python created 7mo ago pushed 16d ago agent-skillsagentcallai-agent
    +2.0/wk
    measured
    ★ 177
    23
  21. 7571
    Offline Clash Royale AI agent research: native simulation, imitation learning, PPO, and interactive evaluation. 离线对局模拟、模仿学习、强化学习与交互评测。
    Python created 2mo ago pushed 36d ago artificial-intelligenceclash-royaledeep-learning
    —
    stale
    ★ 177
    19
  22. 7572
    ⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.
    TypeScript created 5mo ago pushed 4d ago ai-agentsai-toolsbrowser-automation
    +4.0/wk
    measured
    ★ 177
    27
  23. 7573
    A lightweight, low-allocation, high-performance HTTP client library for ESP32.
    C++ created 9mo ago pushed 5d ago arduinoarduino-libraryesp32
    +1.7/day
    measured
    ★ 177
    45
  24. 7574
    运动世界校园纯 Python 协议实现,包含 NetSecKit 4.2.4、GeeTest v4、全链路协议分析与自动化套件,脱离 Android App 与 Native SO 依赖。
    Python created 2mo ago pushed 12d ago androidandroid-reverse-engineeringautomation
    +3.0/day
    measured
    ★ 177
    33
  25. 7575
    Local-first AI agent for Chrome: browser automation, web research, and data extraction with your own model.
    HTML created 28d ago pushed 9d ago ai-agentbrowser-agentbrowser-automation
    +3.4/day
    measured
    ★ 177
    33
  26. 7576
    PolyTutor overview of Polymarket trading bots: strategy guides (copy trading, market making, dump-hedge, last-seconds, sports), case studies, and engineering notes. Smart trading. Real edge.
    created 24d ago pushed 24d ago documentationpolymarketpolytutor
    +3.0/day
    measured
    ★ 177
    31
  27. 7577
    Stop your coding agent from stalling real work on self-invented bookkeeping - receipts, hashes, locks, certification rituals. Ship first, then verify. Skill for Claude Code, Codex, and other agents.
    Shell created 2mo ago pushed 2mo ago agent-skillsagentsagentskills
    —
    stale
    ★ 176
    16
  28. 7578
    DSH plugin — free OpenCode Zen models for DeepSeek Harness (DSH). Free LLM API, no API key needed. 在 DSH 中使用 OpenCode Zen 免费模型,无需 API key
    TypeScript created 2mo ago pushed 28d ago cordiscordis-plugindeepseek
    —
    stale
    ★ 176
    19
  29. 7579
    Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark speculative decoding (~75 tok/s), full benchmarks, OpenAI Codex CLI integration
    Shell created 2mo ago pushed 2mo ago deepseekdgx-sparkllm-inference
    flat
    measured
    ★ 176
    15
  30. 7580
    Background removal that keeps what matters: glass, camouflage, text, glow and line art. BiRefNet fine-tune, MIT.
    Python created 4mo ago pushed 3mo ago background-removalbirefnetcamouflage
    +1.0/wk
    measured
    ★ 176
    28
  31. 7581
    AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发执行,让变更有依据、交付有证据。用创意编织现实。
    JavaScript created 39d ago pushed 9d ago aegisagentic-codingai-agent
    +8.0/day
    measured
    ★ 176
    39
  32. 7582
    Agent Skill: realistic handwriting with the Inko API — solve & hand-write homework, write on your own notebook paper, phone-photo looks, PDF. For Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode.
    Python created 42d ago pushed 32d ago agent-skillsai-agentschinese
    +4.7/day
    measured
    ★ 176
    36
  33. 7583
    One policy. Any motion. Train universal whole-body tracking in mjlab—swap clips, not checkpoints.
    Python created 5mo ago pushed 16d ago humanoidsmjlabmujoco
    —
    stale
    ★ 176
    20
  34. 7584
    Research reading list on memory for robotics
    created 10mo ago pushed 28d ago awesomememoryrobotics
    —
    stale
    ★ 176
    19
  35. 7585
    Pass the baton from Claude Code or Codex to a local DeepSeek Harness. An MCP server that hands off tasks and brings the result back.
    JavaScript created 21d ago pushed 5d ago claude-codecodexdeepseek
    +12/day
    measured
    ★ 176
    43
  36. 7586
    Updated weekly — until humanity achieves AI4AI. A survey-grounded catalog of 432 papers on long-horizon agents, benchmarks, harness design, and recursive self-improvement.
    Python created 2mo ago pushed 14d ago agent-benchmarksagent-harnessagi
    —
    stale
    ★ 176
    21
  37. 7587
    One page that tells you whether your homelab is fine.
    Go created 11d ago pushed 4d ago dashboardgohomelab
    +22/day
    lifetime avg
    ★ 176
    48
  38. 7588
    Secure AI-powered remote computer access for ChatGPT, Claude and compatible MCP clients.
    created 6d ago pushed 5d ago ai-commanderai-communicationai-tools
    +57/day
    lifetime avg
    ★ 176
    55
  39. 7589
    一个生产级的深度研究 Agent 系统,从零构建多智能体编排、Red-Blue 对抗降噪、 语义级上下文压缩、跨 Agent 共享记忆四大核心能力,配套 165 次独立实验 + Bootstrap 统计显著性检验的完整评测体系。
    Python created 6mo ago pushed 6mo ago adversarial-trainingasynciodeep-research
    +4.0/wk
    measured
    ★ 175
    14
  40. 7590
    Personal AI agents.
    Swift created 2mo ago pushed 22d ago agent-collaborationai-agentschat
    —
    stale
    ★ 175
    20
  41. 7591
    Open-source research workspace: search academic papers, upload PDFs, inline citations with on-PDF highlights, reader-mode Q&A, and get citation export in four formats.
    TypeScript created 2mo ago pushed 25d ago arxivarxiv-apicitation
    —
    stale
    ★ 175
    20
  42. 7592
    👁️ Review AI generated code and plan changes
    JavaScript created 2mo ago pushed 23d ago agentaicode-review
    —
    stale
    ★ 175
    20
  43. 7593
    First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI.
    TypeScript created 37d ago pushed 3d ago agentai-agentai-assistant
    +2.4/day
    measured
    ★ 175
    35
  44. 7594
    🤖 Curated AI OSINT resources — Google dorks, Shodan queries, GitHub dorks, and techniques to discover exposed LLM endpoints, leaked AI API keys, misconfigured vector databases, and unprotected AI agents
    Python created 7mo ago pushed 10d ago agent-skillsai-osintai-security
    +3.0/wk
    measured
    ★ 175
    30
  45. 7595
    ModelSphere is an open-source LLM inference infrastructure designed to make production-grade model serving simple, efficient, and continuously optimized.
    Shell created 42d ago pushed 4d ago ansibleascendgpu
    +5.0/wk
    measured
    ★ 175
    26
  46. 7596
    🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac и сервере — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, агенты, fine-tuning, лучшие фишки
    Shell created 22d ago pushed 22d ago ai-agentsdeepseekdeepseek-r1
    +2.3/day
    measured
    ★ 175
    30
  47. 7597
    把 B站 / 抖音 / YouTube / 小红书视频一键整理成 Markdown 课堂笔记的 AI Agent Skill:字幕抓取 + 本地语音识别 + 笔记模板,免登录、不调付费 API
    Python created 38d ago pushed 4d ago agent-skillsbilibiliclaude-code
    +2.1/day
    measured
    ★ 175
    31
  48. 7598
    Passive market-making bot for Predict.fun: quotes from live order books, replaces stale orders and cancels on unsafe price/depth; Windows desktop app and web console for Ubuntu servers.
    Python created 24d ago pushed 24d ago desktop-appmarket-makingpredict-fun
    +3.0/day
    measured
    ★ 175
    31
  49. 7599
    3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in parallel, have them check each other’s work, and reduce unnecessary model calls and noisy tool output. Turn on only what you need.
    Python created 5mo ago pushed 20d ago agentic-aiagentic-workflowai-agents
    —
    stale
    ★ 175
    20
  50. 7600
    Agent skills that make DeepSeek models plan, verify and ship like frontier models. npx skills add aicodeking/deepseek-stack
    Python created 11d ago pushed 11d ago agent-skillsclaude-codecline
    +22/day
    lifetime avg
    ★ 175
    47
← previous page 152 of 187 next →