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…
- 51
A lightweight local-first CLI that orchestrates AI agent CLIs (claude, codex) into powerful workflows with a simple YAML.
0,1/gün ort. +0 son gün — commit Python 11 Haz 2026 güncellendi 18 Haz 2026 - 52
The pit crew for agentic coding.
0,3/gün ort. +0 son gün — commit TypeScript 18 Ağu 2026 güncellendi 15 gün önce - 53
Call the Google Antigravity CLI (agy) headlessly from any non-TTY context — Windows ConPTY + POSIX pty + MCP server. Fixes the empty-output
0,1/gün ort. +0 son gün — commit Python 13 Haz 2026 güncellendi bugün - 54
The factory that builds software — and itself. A runtime for self-improving agentic loops: the tracker is the control plane, git is the trut
0,2/gün ort. +0 son gün — commit JavaScript 03 Ağu 2026 güncellendi 02 Eki 2026 - 55
Evidence-grounded AI secretary for Claude Code and Codex, with frozen context, deterministic retrieval, bounded quality review, and explicit
0,2/gün ort. +0 son gün — commit JavaScript 17 Ağu 2026 güncellendi 21 Ağu 2026 - 56
Engineering-first OpenAI Codex guide: 14 modules, 9 installable skills, reproducible benchmarks, testing, review, orchestration, and a Livin
0,2/gün ort. +0 son gün — commit Python 24 Tem 2026 güncellendi 5 gün önce - 57
An open-source learning lab for operational ontologies, with a runnable reference implementation for typed objects, rules, evidence, human-r
0,1/gün ort. +0 son gün — commit JavaScript 12 May 2026 güncellendi bugün - 58
Jev for every agentic development workflow — the System One decision model wired into whatever harness an agent codes in: OpenCode today, Cl
0,3/gün ort. +0 son gün — commit TypeScript 19 Eyl 2026 güncellendi 28 gün önce - 59
A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.
0,1/gün ort. +0 son gün — commit 28 Haz 2026 güncellendi 07 Eyl 2026 - 60
A practical methodology for mapping business processes and designing safe, measurable AI-agent automation pilots.
0,1/gün ort. +0 son gün — commit Python 12 May 2026 güncellendi 7 gün önce - 61
OpenMirai — the open-source, Rust-native engine for running AI agents anywhere. One binary, any LLM, your rules.
0,1/gün ort. +0 son gün — commit Rust 29 May 2026 güncellendi 04 Eyl 2026 - 62
Quality-first Codex skill for verified delegation across native subagents and Codex/Claude CLI workers.
0,1/gün ort. +0 son gün — commit Python 18 Tem 2026 güncellendi 14 gün önce - 63
Runtime-adaptive steering layer and portable control contract for hard agentic work: durable goals, proportional control, bounded delegation
0,1/gün ort. +0 son gün — commit Ruby 23 Haz 2026 güncellendi 27 Tem 2026