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…
- 351
2026 Next-Gen AI Photo Background Remover & Object Removal Tool
0,4/gün ort. +0 son gün — commit HTML 15 Haz 2026 güncellendi bugün - 352
千笔一文 Novel — 人 AI 共写的长篇网文创作台:条目化世界书 · 正则 must 契约(确定性复检,违规拦住锁定)· 三层审校(引证验真 + 投票)· 同人文外部导入可整批撤销 · 升级不动书稿 · BYOK 全本地 · MIT。A long-form fiction
0,6/gün ort. +0 son gün — commit Python 15 Ağu 2026 güncellendi 27 Eyl 2026 - 353
The Agency — a roster of 200+ specialist AI agent personas (engineering, design, marketing, sales, security, GIS, game-dev & more) for Claud
0,4/gün ort. +0 son gün — commit Shell 05 Tem 2026 güncellendi 05 Tem 2026 - 354
34 FinOps specialist AI agents + 6 named-pattern playbooks. Drop into Claude Code, Copilot, Cursor, Windsurf, Aider, Gemini CLI. MIT.
0,2/gün ort. +0 son gün — commit Shell 24 Nis 2026 güncellendi 28 Nis 2026 - 355
AI Paper Reviewer: LLM-based tool for academic paper review
0,3/gün ort. +0 son gün — commit Python 01 Haz 2026 güncellendi bugün - 356
Ecossistema de Engenharia de Estudos com IA Fundamentada (NotebookLM + Gemini Estudantes). Metodologia N.A.G. (Nucleo de Aprendizagem Guiada
1,1/gün ort. +1 son gün — commit 21 Eyl 2026 güncellendi 23 gün önce - 357
Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes
0,3/gün ort. +0 son gün — commit Python 09 May 2026 güncellendi 10 Eyl 2026 - 358
Advertising prompt agent for Image2: turns business briefs and reference images into debranded, production-ready image prompts.
0,3/gün ort. +0 son gün — commit TypeScript 02 May 2026 güncellendi 06 May 2026 - 359
A structured failure-analysis workflow that assumes your plan already failed and works backward to find every reason why. Based on Gary Klei
0,3/gün ort. +0 son gün — commit 03 May 2026 güncellendi 30 Haz 2026 - 360
Operational doctrine for practical AI systems design.
0,3/gün ort. +0 son gün — commit PowerShell 10 Haz 2026 güncellendi 31 Ağu 2026 - 361
A reasoning skill for AI agents to improve complex judgment, premise auditing, counterargument pressure, and verifiable conclusions.
0,3/gün ort. +0 son gün — commit 31 May 2026 güncellendi 06 Haz 2026 - 362
Agent Skills for working UX designers. Challenge ideas, find blind spots, use the real design system, preserve evidence and decisions, and c
0,6/gün ort. +0 son gün — commit Python 20 Ağu 2026 güncellendi 04 Eyl 2026 - 363
AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks
0,2/gün ort. +0 son gün — commit 17 Nis 2026 güncellendi 5 gün önce - 364
See how you really use AI — X-ray your AI coding sessions locally
0,2/gün ort. +0 son gün — commit Python 10 Mar 2026 güncellendi 24 Haz 2026 - 365
Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Op
0,2/gün ort. +1 son gün — commit Shell 23 Nis 2026 güncellendi 04 May 2026 - 366
把一批文章样本自动炼化成可复用的写作风格档案,并生成一个按该风格写作的专属 Claude skill。/ A Claude Code skill that distills writing samples into a reusable style profile and for
0,3/gün ort. +0 son gün — commit Python 15 May 2026 güncellendi 15 May 2026 - 367
CLI text optimizer built on GEPA. Uses Agentic Coding CLI's as mutator and observer -- no api keys required
0,2/gün ort. +0 son gün — commit TypeScript 18 Nis 2026 güncellendi 27 gün önce - 368
13 prompts to control how Claude communicates — choose your style, cut the noise.
0,2/gün ort. +0 son gün — commit 24 Nis 2026 güncellendi 25 Nis 2026 - 369
High-assurance, artifact-agnostic prompt for authorized security labs, exploit-chain research, PoC validation, and evidence-led reporting.
0,5/gün ort. +0 son gün — commit 01 Ağu 2026 güncellendi 01 Ağu 2026 - 370
Methodology + templates for a trustworthy, traceable, self-growing AI data-analyst agent: metrics-first, independent read-only validation, a
0,4/gün ort. +0 son gün — commit 30 Haz 2026 güncellendi 30 Haz 2026 - 371
Codex skill for transcript-driven MiniMax-H3 B-roll planning, T01-T21 motion templates, approval-gated generation, and balanced typography c
0,5/gün ort. +0 son gün — commit Python 10 Ağu 2026 güncellendi 14 Ağu 2026 - 372
A modular AI-ready story-development skill engine built on Pixar’s 22 Rules, Story Spine, Hero’s Journey, South Park causality, and characte
0,2/gün ort. +0 son gün — commit 10 Mar 2026 güncellendi 07 Tem 2026 - 373
Claude Skills for Ableton Live producers. Workflows for Claude Code, Cursor, Codex, and Gemini CLI. Pairs with any Ableton MCP server. MIT.
0,2/gün ort. +0 son gün — commit 27 Nis 2026 güncellendi 23 Eyl 2026 - 374
A terminal-native prompt composer for power users running multiple coding agents.
0,6/gün ort. +0 son gün — commit Rust 23 Ağu 2026 güncellendi 8 gün önce - 375
Thinking in the Human · Processing in the AI · Truth in the Documentation
0,2/gün ort. +0 son gün — commit 30 Nis 2026 güncellendi 14 Tem 2026 - 376
End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur
0,2/gün ort. +0 son gün — commit Python 06 Mar 2026 güncellendi 16 Tem 2026 - 377
Очеловечить текст нейросети: убирает длинное тире, канцелярит и штампы ChatGPT, не трогая факты. Правила для любой нейросети + скилл для Cla
0,3/gün ort. +0 son gün — commit Python 10 Haz 2026 güncellendi 15 gün önce - 378
Installable Codex skills for goal-setting and marketing operator work.
0,3/gün ort. +0 son gün — commit Python 04 Haz 2026 güncellendi 30 Ağu 2026 - 379
Bedrock is a CLI tool that bootstraps AI-ready project configurations by generating standardized rules, skills, and project context tailored
0,2/gün ort. +0 son gün — commit JavaScript 07 Nis 2026 güncellendi 08 Nis 2026 - 380
High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.
0,3/gün ort. +0 son gün — commit JavaScript 12 Haz 2026 güncellendi 17 Tem 2026 - 381
Create Suno Prompts Using Gemini Flash, works with the Suno API. Create professional-looking timed word-for-word lyrics videos.
0,3/gün ort. +0 son gün — commit TypeScript 15 May 2026 güncellendi 7 gün önce - 382
ASD-STE100 Simplified Technical English as a plugin for Claude Code, Codex & coding agents — clearer, unambiguous LLM output
1,7/gün ort. +0 son gün — commit 08 Eki 2026 güncellendi 25 gün önce - 383
Free Etsy SEO tool for AI assistants — optimize Etsy titles, tags, and listings with live autocomplete research, competitor SERP analysis, a
0,3/gün ort. +1 son gün — commit Markdown 17 May 2026 güncellendi 11 gün önce - 384
The Dream Machine — a config-driven engine for nightly, cloud-scheduled, evidence-gated repository evolution. Composes @metaharness/flywheel
0,5/gün ort. +0 son gün — commit TypeScript 13 Ağu 2026 güncellendi bugün - 385
Spatial prompt engineering through interactive 3D concept graphs
0,2/gün ort. +0 son gün — commit TypeScript 05 Nis 2026 güncellendi 27 Nis 2026 - 386
23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex deskto
0,3/gün ort. +0 son gün — commit Python 25 Haz 2026 güncellendi bugün - 387
Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.
0,4/gün ort. +0 son gün — commit TypeScript 09 Tem 2026 güncellendi 11 Eyl 2026 - 388
Curated Claude and Codex skill collection for local AI workflows, automation, research, and product-building.
0,2/gün ort. +1 son gün — commit Python 14 Mar 2026 güncellendi 14 Mar 2026 - 389
PromptGuard is a single-file AI security platform that scans user prompts in real-time and classifies them as SAFE, SUSPICIOUS, or DANGEROUS
0,3/gün ort. +0 son gün — commit HTML 17 May 2026 güncellendi 14 Eyl 2026 - 390
十三希诺 Agent 工作流 · 中文源库:把工程纪律做成可机检门禁的元工作流 Skill 家族——三级跑道/判级/GATE 12 字段可复跑证据/405 条细则库/五包交付(核心+流程+角色+产品工程+单文件蒸馏),五平台注入适配。docs/ 为开发工作区,实验数据已归档。En
0,6/gün ort. +0 son gün — commit Python 25 Ağu 2026 güncellendi 21 gün önce - 391
支持cc和gpt等订阅的个人 AI 助理 — 语音实时通话派活、任务管理、定时任务、三档安全闸、多供应商热切换
0,5/gün ort. +0 son gün — commit Python 04 Ağu 2026 güncellendi bugün - 392
AI 人生设计师 — 基于斯坦福 Life Design Lab 方法论的 Claude Code Skill,通过深度对话帮你设计人生
0,4/gün ort. +0 son gün — commit Python 08 Tem 2026 güncellendi 10 Tem 2026 - 393
AI skill for rewriting machine-generated text to sound human-written across 9 languages - 5-stage pipeline: cleanup → specificity → tone → r
0,3/gün ort. +0 son gün — commit PowerShell 21 Haz 2026 güncellendi 12 Tem 2026 - 394
A browser game to learn prompt engineering by playing — explore a world and solve challenges by writing prompts. Techniques from OpenAI, Ant
0,4/gün ort. +0 son gün — commit JavaScript 30 Tem 2026 güncellendi 11 Eyl 2026 - 395
Cut Claude Code costs with sourced levers -- prompt caching, model routing, Batch -- plus an installable skill, CLI tools, a cost calculator
0,2/gün ort. +0 son gün — commit TypeScript 08 Mar 2026 güncellendi 2 gün önce - 396
Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right
0,2/gün ort. +0 son gün — commit HTML 25 Nis 2026 güncellendi 11 gün önce - 397
Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent
0,4/gün ort. +0 son gün — commit Python 17 Tem 2026 güncellendi 17 Tem 2026 - 398
Claude skill for behavioral interview prep — mine real experiences, structure them with STAR/CAR, and build a reusable bilingual story bank.
0,3/gün ort. +0 son gün — commit HTML 29 Haz 2026 güncellendi 28 Eyl 2026 - 399
Full AI-assisted workflow for long-form SEO content. JTBD strategy · E-E-A-T · 5-phase production system · Built for B2B.
0,2/gün ort. +0 son gün — commit 28 Mar 2026 güncellendi 28 Mar 2026 - 400
Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses
0,6/gün ort. +1 son gün — commit Python 25 Ağu 2026 güncellendi 31 Ağu 2026