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
A self-evolved, sovereign desktop AI agent built for real-world action — beyond model wrappers and coding copilots. / 真实实践中自我演化的独立桌面 AI Agen
3/gün ort. +0 son gün 231 commit 4 yazar TypeScript 30 Mar 2026 güncellendi dün - 2
This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind
5,7/gün ort. +4 son gün 49 commit 2 yazar Python 24 Eki 2026 güncellendi 3 gün önce - 3
Helixent is a small library for building ReAct-style AI agent loops based on the Bun stack.
3,3/gün ort. +0 son gün 0 commit 0 yazar TypeScript 06 Nis 2026 güncellendi 21 May 2026 - 4
A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at a
3,2/gün ort. +0 son gün 0 commit 0 yazar Python 17 Haz 2026 güncellendi 29 Haz 2026 - 5
A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.
1,2/gün ort. +0 son gün 0 commit 0 yazar TypeScript 10 Tem 2026 güncellendi 30 Ağu 2026 - 6
Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks
0,5/gün ort. +0 son gün — commit Go 13 Mar 2026 güncellendi 4 gün önce - 7
MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-
0,4/gün ort. +0 son gün — commit Python 17 Haz 2026 güncellendi 08 Tem 2026 - 8
Claude Code 源码逆向恢复项目 | Source Map 逆向 · 架构分析 · 可运行版本 | 1900+ 文件 · 51万行代码 · 12章节课程
0,3/gün ort. +0 son gün — commit TypeScript 01 Nis 2026 güncellendi 2 gün önce - 9
Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded
0,3/gün ort. +0 son gün — commit Python 11 May 2026 güncellendi 5 gün önce - 10
Autonomous framework for long-running agents: a charter guides Claude Code, Codex or Pi through an actor, critic and scribe loop for hours.
0,5/gün ort. +0 son gün — commit Python 05 Eyl 2026 güncellendi bugün - 11
Loop Engineering — a skill for designing & reviewing autonomous/semi-autonomous agent loops (Claude Code, Codex, Copilot, Gemini).
0,2/gün ort. +0 son gün — commit Python 23 Haz 2026 güncellendi 24 Haz 2026 - 12
Long-running autonomy for Pi: draft goals, build projects from specs, run audited task queues, and recover interrupted work. Independent aud
0,3/gün ort. +0 son gün — commit TypeScript 20 Tem 2026 güncellendi 2 gün önce - 13
A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set
0,2/gün ort. +0 son gün — commit Python 23 Haz 2026 güncellendi 01 Eki 2026 - 14
Acta: A Decision-Centric Runtime for Agents
0,6/gün ort. +0 son gün — commit TypeScript 20 Eyl 2026 güncellendi 29 gün önce - 15
A menu-bar macOS agent loop: every N minutes it asks Claude/Codex what's overloading your Mac and suggests one-click, risk-checked fixes.
0,2/gün ort. +0 son gün — commit Swift 19 Haz 2026 güncellendi 26 Tem 2026 - 16
chatablex AI Agent.
0,1/gün ort. +0 son gün — commit 13 May 2026 güncellendi 12 Tem 2026