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.
-
8351Non-destructive scanner for CVE-2026-109618 / CVE-2026-109619 (PHP core RCE). Subdomain recon via crt.sh + subfinder, robust banner grabbing, version-based detection.+2.0/wkmeasured★ 11122
-
8352Self-hosted Google search scraper for Python. Scrape Google SERP results with a real Chrome browser and your own residential proxy. Self-hosted SERP API alternative with JSON output, an HTTP API and an MCP server for AI agents.+2.9/daymeasured★ 11132
-
8353Open-source Helm charts, forged to last. The alternative to Bitnami — official upstream images, Apache 2.0 licensed, Cosign signed.—stale★ 11120
-
8354Dex lets your agent build your analytics.+1.1/daymeasured★ 11127
-
8355Native macOS terminal for running many Claude Code and Codex sessions side by side. Projects, worktrees, live agent status, Allow/Deny from the sidebar, resumable conversations, pull request status and file previews. Built with SwiftUI.—stale★ 11121
-
8356dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。+4.0/wkmeasured★ 11024
-
8357Execute Python from Erlang using dirty NIFs with GIL-aware execution, rate limiting, and free-threading supportflatmeasured★ 11018
-
8358Open-source knowledge base for people and AI agents. Rich-text editing, hybrid search, GraphRAG, and MCP. Self-host with Docker or use DocsMint Cloud.flatmeasured★ 11021
-
8359Local-first cinematic still archive for filmmakers. Search your frames by look, mood, technique or director with SigLIP semantic search; ingest video and URLs; build moodboards. Free desktop app for Win/Mac/Linux, Pro unlocks studio tools. Your library stays on your disk.−2.0/wkmeasured★ 11020
-
8360记得她说过的每一句话,也记得你答应过的每一件事。A self-hosted AI chief of staff for your chats — remembers what they said and what you promised.flatmeasured★ 11018
-
8361LabVLA: Grounding Vision–Language–Action Models in Scientific Laboratoriesflatmeasured★ 11016
-
8362One-command vLLM installation for NVIDIA DGX Spark with Blackwell GB10 GPUs (sm_121 architecture)—stale★ 1106
-
8363Open-source, self-hosted rank tracker and AI-visibility monitor built on the DataBlue SERP API. Bring your own key. AGPL-3.0.—stale★ 11018
-
8364Active Directory security assessment in Rust: directory discovery, Tier-0 path analysis, supported validation, and evidence reporting.+1.0/wkmeasured★ 11022
-
8365Scan-to-Practice: a field-tested AI skill and methodology for turning scanned learning materials into structured practice products.flatmeasured★ 11014
-
8366Application-level quota management for Laravel with calendar periods, Eloquent integration, middleware, and multiple storage backends.flatmeasured★ 11012
-
8367A graph database provides Cypher query, fluent builder and management UI implemented in Golang.flatmeasured★ 11010
-
8368🐚 The AI assistant that just works. One self-hosted app for every model you already pay for: Claude Code, Codex, Copilot, Gemini, Ollama and more. Chat from your desktop, phone or Telegram.+1.0/wkmeasured★ 11022
-
8369Open-source AI video clipping generator — production-ready Next.js SaaS that auto-extracts viral shorts, Reels, and TikToks from long-form YouTube videos. Stripe billing, credits, NextAuth, and Prisma included.+4.0/wkmeasured★ 11027
-
8370A HUD for Claude Code, Codex and 16 more coding agents. Know your quotas, tokens and sessions at a glance, answer requests and jump back in one click. On your screen, phone and watch.—stale★ 11021
-
8371Multi-agent research execution system: paper reproduction, benchmark evaluation, AutoResearch and claim-evidence graphs+9.8/daymeasured★ 11041
-
8372Autonomous AI Lead Generation, Social Discovery & Smart Conversational Growth Agent for Threads & Instagram. Multi-platform with native browser CDP.—stale★ 10921
-
8373An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.—stale★ 10920
-
8374Self-hosted RAG search engine — 34 formats, BM25+hybrid search, multi-LLM (Gemini/OpenAI/Claude/Ollama), FastAPI + Docker, production-ready in 3 minflatmeasured★ 1097
-
8375AI agent operating system for Blender 5.2: bpy knowledge base, AGENT_OK execution contract, 3D-print production gate, worked keyboard and desktop-robot builds.+2.0/wkmeasured★ 10923
-
837618 portable Agent Skills for voice-native AI, human judgment, microbets, social tact, writing, life systems, and safe deployment.—stale★ 10919
-
8377The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. Industrial protocols (OPC-UA, Modbus) on the roadmap.flatmeasured★ 10915
-
8378Independent Claude Skills for the whole smart home: Home Assistant, ESPHome, Node-RED, custom integrations, dashboards, and fab-ready hardware design.flatmeasured★ 10921
-
8379Production-ready Multi-Tenant SaaS Platform built with Nuxt 4, Supabase, PostgreSQL RLS, PWA, AI-ready architecture, and full Arabic/English localization.flatmeasured★ 10920
-
8380Universal crypto-first platform for payments, subscriptions and software license management+3.0/wkmeasured★ 10927
-
8381Evidence-first AI workflow for economic and financial research: literature → identification → data → econometrics → verifiable LaTeX. 43 data sources, 58 method modules, 18 AI skills, 30 journal templates.+1.0/wkmeasured★ 10922
-
8382An MCP server and Next.js web app for querying S&P 500 company data from Supabase, with tools for company info, news, officers, and SEC filings, plus embedded MCP App UI resources, Elicitation, and Sampling support.flatmeasured★ 10921
-
8383A Rust library implementing quantitative market making strategies, starting with the Avellaneda-Stoikov model. This library provides the mathematical foundations and domain models necessary for building automated market making systems for financial markets.—stale★ 10919
-
8384Opinionated, actively maintained list of modern, lightweight tools and practices for Spring Boot 4.x and beyond.—stale★ 10918
-
8385The most comprehensive, step-by-step roadmap for breaking into defensive cybersecurity. From absolute zero to your first Blue Team role. Every skill, tool, certification, and resource you need. No experience required.+4.0/wkmeasured★ 10923
-
8386Run Claude Code, Codex, Kimi, OpenCode, Hermes and one of the 26 other coding agents using MCP , CLI or TUI , WebUI.—stale★ 10920
-
8387A language model trained from scratch and running offline on an ESP32-S3 with a touchscreen chat interface.+4.0/wkmeasured★ 10924
-
8388Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md / CLAUDE.md.+5.0/wkmeasured★ 10925
-
8389LLM agents: curated papers on planning, memory, tool use, multi-agent systems, evaluation, and safety.+5.0/wkmeasured★ 10930
-
8390Generative dynamics on manifold. For Robotics Planing. Control. Learning.flatmeasured★ 10920
-
8391Kumo 蜘蛛 is a domain OSINT & security reconnaissance framework. Drop a domain, get everything back in real time across 29 parallel modules: DNS, open ports, leaked credentials, infostealer infections, vulnerable endpoints, subdomains, CVEs, malware families, and more.+1.0/daymeasured★ 10927
-
8392Curated list of self-hosted open-source AI: local LLMs, chat UIs, agents, MCP servers, RAG, speech and image generation. Health-checked weekly, dead projects removed automatically.+21/daylifetime avg★ 10946
-
8393MCP server for AI agents to read and interact with Elysium, Kinetiq’s Arbitrum Orbit L2 on Hyperliquid+19/daylifetime avg★ 10945
-
8394Offline video material retrieval platform for semantic search, subtitle search, Agent API, and AI-assisted editing.+3.2/wklifetime avg★ 10924
-
8395Open-Source Intelligent Command Layerflatmeasured★ 10821
-
8396Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.+2.0/wkmeasured★ 10827
-
8397Terminal database client with AI chat and an MCP server+1.0/wkmeasured★ 10821
-
8398The agent harness you can fork. A working agent loop with compaction, sessions, approvals, a terminal REPL, a local dashboard and ACP, where every tool, skill, hook and policy is a file you can change. Build your own internal or coding agent on any model.+1.0/wkmeasured★ 10822
-
8399辞达 Cídá · 现代中文高质量表达 Skill。让 AI 依循任务目标、文本证据与话语机制,把值得表达的思想说清楚、说自然、说得有分寸。—stale★ 10820
-
8400WorkWit: a self-hosted, open-source (MIT) enterprise AI Agent platform for office automation — built-in contract review & resume screening, 40+ skills, MCP connectors, multi-tenant RBAC. Deploy with one Docker Compose.—stale★ 10815