Havuz
Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.
Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.
EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster
Etiketler yükleniyor…
- 1.201
Tactical AI Workspace Monitor & EDR
1,1/gün ort. +0 son gün 0 commit 0 yazar TypeScript 14 Mar 2026 güncellendi 19 Mar 2026 - 1.202
Poirot is a deep research agent kernel built for those who care about how agents are architected.
2,5/gün ort. +0 son gün 0 commit 0 yazar Python 28 Tem 2026 güncellendi 28 Tem 2026 - 1.203
Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation,
2,1/gün ort. +0 son gün 0 commit 0 yazar Shell 10 Tem 2026 güncellendi 16 Eyl 2026 - 1.204
An agent design team you control: 10 agents that run an inclusive design process while you direct.
1,1/gün ort. +0 son gün 0 commit 0 yazar Shell 18 Mar 2026 güncellendi 23 Haz 2026 - 1.205
Create product launch assets with Remotion, then review and distribute them through guarded, dry-run-first workflows.
2,1/gün ort. +0 son gün 0 commit 0 yazar JavaScript 10 Tem 2026 güncellendi 06 Eyl 2026 - 1.206
WAI Play - AI web game testing and quality evaluation platform
2,6/gün ort. +0 son gün 0 commit 0 yazar Python 04 Ağu 2026 güncellendi 31 Ağu 2026 - 1.207
Agent Skills for theming AI desktop apps: reference image → reversible Codex/WorkBuddy skin → verify, repair, publish. | 给 AI 桌面应用换肤的 Agent
2,2/gün ort. +0 son gün 0 commit 0 yazar CSS 15 Tem 2026 güncellendi 09 Ağu 2026 - 1.208
Community-maintained skills for specialized HyperFrames workflows.
3,3/gün ort. +1 son gün 0 commit 0 yazar JavaScript 25 Ağu 2026 güncellendi 5 gün önce - 1.209
Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signe
1,5/gün ort. +0 son gün 0 commit 0 yazar 31 May 2026 güncellendi 21 Eyl 2026 - 1.210
Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.
1,4/gün ort. +0 son gün 0 commit 0 yazar TypeScript 12 May 2026 güncellendi 9 gün önce - 1.211
Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats
1,2/gün ort. +0 son gün 0 commit 0 yazar TypeScript 21 Nis 2026 güncellendi 07 Tem 2026 - 1.212
SRT 驱动的双后端 B-roll Agent Skill:自动路由 HyperFrames / Remotion,集成 152 张 Shotcraft 镜头卡
2,2/gün ort. +0 son gün 0 commit 0 yazar TypeScript 20 Tem 2026 güncellendi 10 Eki 2026 - 1.213
Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.
1,8/gün ort. +1 son gün 0 commit 0 yazar 28 Haz 2026 güncellendi 26 Tem 2026 - 1.214
Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data
1,5/gün ort. +0 son gün 0 commit 0 yazar Shell 30 May 2026 güncellendi 30 May 2026 - 1.215
Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.
2,6/gün ort. -1 son gün 0 commit 0 yazar Shell 09 Ağu 2026 güncellendi 10 Ağu 2026 - 1.216
Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with
1,3/gün ort. +0 son gün 0 commit 0 yazar TypeScript 05 May 2026 güncellendi 19 Eyl 2026 - 1.217
Expert-thinking AGENTS.md profiles that teach AI agents to reason like senior scientists and engineers.
1,5/gün ort. +1 son gün 0 commit 0 yazar Python 03 Haz 2026 güncellendi 02 Eki 2026 - 1.218
Create reusable bots powered by Claude Code, Codex, or OpenCode. Run them locally across your repositories with persistent threads and permi
4,5/gün ort. +0 son gün 0 commit 0 yazar TypeScript 17 Eyl 2026 güncellendi 21 gün önce - 1.219
Keeps your Claude session warm for you
2,2/gün ort. +0 son gün 0 commit 0 yazar Python 20 Tem 2026 güncellendi 28 Tem 2026 - 1.220
Claude skill that analyzes images, websites, and Figma files and generates a structured design.md with token system, component inventory, an
1,4/gün ort. +0 son gün 0 commit 0 yazar Python 18 May 2026 güncellendi 15 Eyl 2026 - 1.221
Research-backed, eval-driven skills for AI agents
2,5/gün ort. +0 son gün 0 commit 0 yazar Python 03 Ağu 2026 güncellendi 22 Eyl 2026 - 1.222
The open source multi-agent simulation from the Developer Keynote at Google Cloud Next '26. A deployable reference architecture for autonomo
1,1/gün ort. +1 son gün 0 commit 0 yazar Python 27 Mar 2026 güncellendi 3 gün önce - 1.223
开源的企业版的数字员工工作台, OPC-Nexus(One Person Company Nexus)是一款本地优先的桌面 AI Agent 管理器。它为单人公司 / 独立开发者提供统一的 AI 数字员工管理平台 —— 从 Agent 创建、任务编排、多引擎接入,到消息渠道集成、
2,4/gün ort. +0 son gün 0 commit 0 yazar TypeScript 31 Tem 2026 güncellendi 03 Eyl 2026 - 1.224
Give Claude its own dev team: one supervisor, four specialists, and bulletproof plans/builds without losing context.
1,1/gün ort. +0 son gün 0 commit 0 yazar TypeScript 01 Nis 2026 güncellendi 19 Nis 2026 - 1.225
Evidence-backed AI industry intelligence — trends, source updates, daily data refreshes, and weekly decision briefs.
2/gün ort. +0 son gün 0 commit 0 yazar TypeScript 11 Tem 2026 güncellendi 28 Ağu 2026 - 1.226
Autonomous multi-branch research lab. Branches compete for compute budget. The system converges on what works.
1,1/gün ort. +0 son gün 0 commit 0 yazar Python 30 Mar 2026 güncellendi 07 Ağu 2026 - 1.227
Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas
1,9/gün ort. +1 son gün 0 commit 0 yazar Python 07 Tem 2026 güncellendi 01 Eyl 2026 - 1.228
KSoR (Knowledge System of Record) is an open-source SDK for building governed, authoritative knowledge systems for humans and AI agents. It
2,8/gün ort. +0 son gün 0 commit 0 yazar TypeScript 17 Ağu 2026 güncellendi 01 Eki 2026 - 1.229
协调探索、执行和独立评审,让复杂任务按明确职责并行推进,由主 Agent 统一验收。
2/gün ort. +1 son gün 0 commit 0 yazar Python 17 Tem 2026 güncellendi 01 Eki 2026 - 1.230
AI-agent skills for distributed-systems testing
1,3/gün ort. +0 son gün 0 commit 0 yazar 16 May 2026 güncellendi 21 Tem 2026 - 1.231
Open agent skills and tool schemas for Superior Trade — build, backtest, and deploy trading strategies on Hyperliquid
0,9/gün ort. +1 son gün 0 commit 0 yazar JavaScript 08 Mar 2026 güncellendi 10 Eyl 2026 - 1.232
122 个逆向工程 AI 技能:恶意软件分析 / 软件逆向 / 固件嵌入式 / 协议逆向 / 移动应用 / 脱壳反混淆 / 软件破解 / 漏洞挖掘 / 托管代码 / 取证情报 / CTF。
2,8/gün ort. +0 son gün 0 commit 0 yazar JavaScript 17 Ağu 2026 güncellendi 29 gün önce - 1.233
AI-assisted Lean project automation with DAG blueprints, proof orchestration, and multi-agent coding/proving workflows.
1/gün ort. +0 son gün 0 commit 0 yazar Python 22 Mar 2026 güncellendi 17 Ağu 2026 - 1.234
A repository for skills that are essential to my daily work
1,9/gün ort. +0 son gün 0 commit 0 yazar Python 11 Tem 2026 güncellendi 16 Ağu 2026 - 1.235
Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.
1/gün ort. +0 son gün 0 commit 0 yazar Python 21 Mar 2026 güncellendi 21 gün önce - 1.236
Multi-agent autonomous framework — let your AI work while you sleep 🌙
0,9/gün ort. +0 son gün 0 commit 0 yazar Shell 12 Mar 2026 güncellendi 13 Mar 2026 - 1.237
CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skil
3/gün ort. +0 son gün 0 commit 0 yazar Python 26 Ağu 2026 güncellendi 28 Ağu 2026 - 1.238
Agent-native PowerPoint manipulation — one CLI lets AI agents inspect, edit, create, and verify .pptx files through atomic JSON patches. Pac
1,5/gün ort. +0 son gün 0 commit 0 yazar Python 09 Haz 2026 güncellendi 04 Ağu 2026 - 1.239
system prompt of claude fable 5
1,5/gün ort. +0 son gün 0 commit 0 yazar Python 10 Haz 2026 güncellendi 04 Tem 2026 - 1.240
`xxg-portrait-rebuild-light` is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and backgrou
2,5/gün ort. +1 son gün 0 commit 0 yazar Python 11 Ağu 2026 güncellendi 09 Eki 2026 - 1.241
从 165 个顶级 AI 产品系统提示词中蒸馏出的 15 个可执行 Agent skill
1,2/gün ort. +0 son gün 0 commit 0 yazar 04 May 2026 güncellendi 04 May 2026 - 1.242
An AI agent for running, testing, and hardening GitHub Docker Compose apps.一个用于运行、测试和加固 GitHub Docker Compose 应用的 AI Agent。
3,2/gün ort. +0 son gün 0 commit 0 yazar Python 02 Eyl 2026 güncellendi 15 Eyl 2026 - 1.243
The open-source company brain. Run your entire company with AI agents, skills, and a self-improving context.
1,2/gün ort. +0 son gün 0 commit 0 yazar JavaScript 13 May 2026 güncellendi 21 May 2026 - 1.244
Harness-native agent components for Codex and Pi: a DeepSeek V4 Flash subagent and a DSH Minimal mimic for V4 Pro.
2,2/gün ort. +0 son gün 0 commit 0 yazar TypeScript 04 Ağu 2026 güncellendi 17 Eyl 2026 - 1.245
A collaborative workspace where humans and AI agents work together in shared channels
1,1/gün ort. +0 son gün 0 commit 0 yazar TypeScript 27 Nis 2026 güncellendi 07 May 2026 - 1.246
Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.
0,9/gün ort. +0 son gün 0 commit 0 yazar JavaScript 19 Mar 2026 güncellendi 23 Nis 2026 - 1.247
Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub
1,6/gün ort. +0 son gün 0 commit 0 yazar TypeScript 24 Haz 2026 güncellendi 22 Ağu 2026 - 1.248
IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-aud
1/gün ort. +0 son gün 0 commit 0 yazar JavaScript 16 Nis 2026 güncellendi 7 gün önce - 1.249
AgentReach (reach): Point your coding agent at any box you can SSH into. The server never gets your agent.
2,4/gün ort. +0 son gün 0 commit 0 yazar Go 14 Ağu 2026 güncellendi 23 Eyl 2026 - 1.250
HiCAD,一款AI驱动的CAD建模平台
1,1/gün ort. +0 son gün 0 commit 0 yazar JavaScript 09 May 2026 güncellendi 27 May 2026