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
Open-source skills for designing and reviewing software with AI agents
190,3/gün ort. +1.337 son gün +928,9 son 10g 119 commit 18 yazar Python 13 Eyl 2026 güncellendi 2 gün önce - 2
面向 AI 编程智能体的任务包工作流工具，用可验证的范围、证据和 Git 门禁管理长期改动。(Task-package workflow for AI coding agents with verifiable scope, evidence, and Git gates.)
1,7/gün ort. +35 son gün +35 son 1g — commit Python 02 Eki 2026 güncellendi dün - 3
Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until a
18,6/gün ort. +8 son gün +18,3 son 25g 7.330 commit 1 yazar JavaScript 07 Eki 2026 güncellendi 5 gün önce - 4
Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Clau
11,3/gün ort. +4 son gün +14 son 30g 30 commit 4 yazar HTML 02 Tem 2026 güncellendi 2 gün önce - 5
Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory
8,6/gün ort. +7 son gün +11,3 son 30g 771 commit 18 yazar TypeScript 10 May 2026 güncellendi 2 gün önce - 6
Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives
2,8/gün ort. +14 son gün +9,6 son 30g 80 commit 4 yazar JavaScript 31 May 2026 güncellendi 2 gün önce - 7
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
7,6/gün ort. +1 son gün +3,2 son 30g 33 commit 4 yazar Python 30 Nis 2026 güncellendi 9 gün önce - 8
Spec-driven development that doesn't stop at the code: coding agents take an idea to release, and you make the calls.
4,3/gün ort. +0 son gün +2,4 son 5g 36 commit 2 yazar Python 26 Eki 2026 güncellendi 2 gün önce - 9
Specs your AI agent can't ignore. A deterministic compiler that turns your rules into checks: no AI inside, same input, same verdict. Rust ·
0,3/gün ort. +0 son gün +2 son 11g — commit Rust 24 Haz 2026 güncellendi dün - 10
A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance
2,6/gün ort. +0 son gün +1,5 son 30g 15 commit 1 yazar 31 Mar 2026 güncellendi 9 gün önce - 11
Bounded-autonomy plugin harness for agents. Intent to implementation: ready, then go.
2,8/gün ort. +0 son gün +1,4 son 30g 1 commit 1 yazar Python 31 May 2026 güncellendi 18 gün önce - 12
Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers
1,5/gün ort. +0 son gün +1,2 son 30g 27 commit 5 yazar Shell 24 Nis 2026 güncellendi 3 gün önce - 13
Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.
0,7/gün ort. +4 son gün +1,2 son 30g — commit JavaScript 12 Ağu 2026 güncellendi dün - 14
Minimalistic, project-agnostic skills and rules for AI coding agents
0,5/gün ort. +0 son gün +0,8 son 30g — commit Shell 25 May 2026 güncellendi 2 gün önce - 15
Your whole product team, not just a coding agent. Plan → design → build → QA, with you as the PM who signs off.
0,2/gün ort. +0 son gün +0,6 son 17g — commit TypeScript 02 Tem 2026 güncellendi 7 gün önce - 16
An open standard for agent-native software requirements.
0,8/gün ort. +0 son gün +0,5 son 2g — commit Rust 09 Eki 2026 güncellendi dün - 17
Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discu
4,4/gün ort. -1 son gün +0,4 son 30g 0 commit 0 yazar Shell 21 Mar 2026 güncellendi 26 Tem 2026 - 18
Open standard for software intent in the AI agent era.
2,6/gün ort. +0 son gün +0,4 son 30g 0 commit 0 yazar TypeScript 04 Tem 2026 güncellendi 19 Tem 2026 - 19
Linked-Intent Development - a SDD methodology for agentic coding
0,6/gün ort. +0 son gün +0,4 son 30g — commit Python 11 Nis 2026 güncellendi dün - 20
A featherweight spec-driven development template with a Memory Bank, for Claude Code, GitHub Copilot and JetBrains Junie.
0,8/gün ort. +0 son gün +0,4 son 30g — commit 02 Ağu 2026 güncellendi 27 Eyl 2026 - 21
Build a software startup without writing code. Not vibe coding: a proven team workflow (requirements, design, test-first build, QA, release
0,8/gün ort. +0 son gün +0,3 son 12g — commit Python 14 Eki 2026 güncellendi 4 gün önce - 22
Coding agents için SPEC, test gauntlet’i ve kanıt raporu odaklı bir geliştirme iş akışı sunuyor.
Neden yükseliyor · 63 günde 738 yıldız dikkat çekici ilgiye işaret ediyor; ancak son 28 günde commit ve farklı yazar yok. Bu nedenle yükselişin güncel geliştirme ivmesiyle sürdüğüne dair kanıt bulunmuyor.
7,7/gün ort. +0 son gün +0,2 son 30g 0 commit 0 yazar Python 27 Tem 2026 güncellendi 18 Ağu 2026 - 23
Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.
0,3/gün ort. +0 son gün +0,2 son 30g — commit TypeScript 05 Nis 2026 güncellendi 7 gün önce - 24
Use these guidelines for writing good Gherkin scenarios. Feed it as context to AI specs, agents, and skills.
0,3/gün ort. +0 son gün +0,2 son 30g — commit 26 Nis 2026 güncellendi 30 Nis 2026 - 25
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 +0,2 son 30g — commit HTML 25 Nis 2026 güncellendi 11 gün önce - 26
Consort keeps AI-written code clean and correct: a coordinated ensemble of role agents, spec-first and test-driven, driven by a deterministi
0,2/gün ort. +0 son gün +0,2 son 30g — commit TypeScript 23 May 2026 güncellendi dün - 27
Spec-driven multi-agent teamwork for any skills-capable agent (Claude Code, Codex, and more) — plan, dispatch, monitor, QA. No framework loc
0,1/gün ort. +0 son gün +0,2 son 30g — commit Python 20 May 2026 güncellendi 3 gün önce - 28
Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation,
2,2/gün ort. +0 son gün +0,1 son 30g 0 commit 0 yazar Shell 10 Tem 2026 güncellendi 16 Eyl 2026 - 29
Antidote for fluffy specs, a toolkit for fact-driven development with AI agents
1,1/gün ort. +0 son gün +0,1 son 30g 0 commit 0 yazar Rust 29 Nis 2026 güncellendi 03 Haz 2026 - 30
A Claude skill that keeps your AI coding tools from contradicting each other. Generates requirements.md, design.md, and tasks.md before an
0,9/gün ort. +0 son gün +0,1 son 30g — commit Python 18 May 2026 güncellendi 23 May 2026 - 31
Agent skills for the Agentic SDLC: team lifecycle (team-boot, team-learn, team-init, team-repair), software factory, evals, CDR lifecycle wi
1,4/gün ort. +0 son gün +0,1 son 30g 183 commit 6 yazar Python 20 Tem 2026 güncellendi dün - 32
Coding agent orchestration for engineering teams — shipped as a spec plus a working reference implementation.
0,5/gün ort. +0 son gün +0,1 son 30g — commit TypeScript 23 May 2026 güncellendi 29 gün önce - 33
Local-first CLI that reads your Spec-Driven Development artifacts and recommends the best value-for-money AI model to implement them. Powere
0,6/gün ort. +0 son gün +0,1 son 30g — commit Python 20 Tem 2026 güncellendi 24 Eyl 2026 - 34
Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deter
0,3/gün ort. +0 son gün +0,1 son 30g — commit Python 13 Haz 2026 güncellendi 30 Haz 2026 - 35
HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven,
0,5/gün ort. +0 son gün +0,1 son 30g — commit JavaScript 21 Tem 2026 güncellendi dün - 36
Production-grade vibe coding framework with specs, architecture, AI agents, testing, security, code review, CI/CD, and battle-tested workflo
0,9/gün ort. +0 son gün +0,1 son 30g — commit JavaScript 22 Eyl 2026 güncellendi 3 gün önce - 37
Spec-Driven Development skill pack for the Pi coding agent: steering docs, .status gates, EARS, and a PRD→SPEC→TASKS→EXEC→REVIEW pipeline.
0,2/gün ort. +0 son gün +0,1 son 30g — commit 15 May 2026 güncellendi 13 gün önce - 38
A desktop reader for OpenSpec projects - browse changes, trace how requirements evolved, and comment on specs, all from local folders
0,2/gün ort. +0 son gün +0,1 son 30g — commit TypeScript 01 Haz 2026 güncellendi 11 gün önce - 39
The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release
0,1/gün ort. +0 son gün +0,1 son 30g — commit Python 04 May 2026 güncellendi dün - 40
Spec-driven development plugin for Claude Code. SpecManager gives you an agile AI team that takes a feature from interview → PRD → Architect
0,2/gün ort. +0 son gün +0,1 son 30g — commit TypeScript 24 May 2026 güncellendi 5 gün önce - 41
Laravel spec-driven workflow
0,2/gün ort. +0 son gün +0,1 son 30g — commit HTML 08 Tem 2026 güncellendi 18 gün önce - 42
Turn any repository AI-first and run resumable, long-horizon Deep Work Plans with any coding agent — an installable, MIT-licensed agent skil
0,1/gün ort. +0 son gün +0,1 son 24g — commit Python 22 May 2026 güncellendi 6 gün önce - 43
Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, an
0,2/gün ort. +0 son gün +0,1 son 30g — commit TypeScript 18 Tem 2026 güncellendi 2 gün önce - 44
12 agent skills for AI-driven software development — a gated idea-to-ship pipeline: 7w3 design, build-ready specs, executable architecture,
0,2/gün ort. +1 son gün +0,1 son 30g — commit Python 01 Tem 2026 güncellendi 06 Tem 2026 - 45
Turn ambiguous software-change requests into a durable, Beads-backed lifecycle from specification to human-approved implementation and verif
0,2/gün ort. +0 son gün +0,1 son 29g — commit Shell 24 Tem 2026 güncellendi 11 gün önce - 46
A governance layer for Claude Code sessions: hooks that check an agent's commands before they run, a spec-first workflow, and project memory
0,1/gün ort. +0 son gün +0,1 son 30g — commit JavaScript 01 May 2026 güncellendi 6 gün önce - 47
Open-source ADR workflow for coding agents: 14 skills that scaffold and manage Architecture Decision Records, a plan queue and AGENTS.md con
0,1/gün ort. +0 son gün +0,1 son 30g — commit JavaScript 21 May 2026 güncellendi 12 gün önce - 48
Spec-driven software engineering for AI coding agents - a Python CLI that drives brainstorm, spec, plan, and execute phases over markdown ar
0,1/gün ort. +0 son gün +0,1 son 9g — commit Python 09 Tem 2026 güncellendi 9 gün önce - 49
Cross-platform AI agent harness for 12+ hour autonomous development cycles. Spec-driven, DAG-orchestrated, with a 3-critic evaluation pipeli
0,5/gün ort. +1 son gün +0 son 30g — commit TypeScript 08 Nis 2026 güncellendi 15 gün önce - 50
AI agentic skills framework for spec-driven development, built on the organizational model of mafia.
0,4/gün ort. +0 son gün +0 son 30g — commit Shell 13 Nis 2026 güncellendi 7 gün önce