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
Architecture diagrams and checkable docs from your codebase — ERD, C4, API and lifecycle — generated from Prisma, OpenAPI or GraphQL. One HT
8,6/gün ort. +0 son gün +10,7 son 30g 15 commit 1 yazar JavaScript 19 Eyl 2026 güncellendi 7 gün önce - 2
Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.
1,5/gün ort. +0 son gün +2,5 son 30g — commit JavaScript 04 Ağu 2026 güncellendi 20 gün önce - 3
A minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核，理解 LangGraph/ADK 底层的工作原理
1,5/gün ort. +2 son gün +1,6 son 30g 5 commit 1 yazar Python 04 Ağu 2026 güncellendi 13 gün önce - 4
独立、可自托管的 AI 动态心智状态引擎：驱动力、念头池、疲惫、睡眠与意图。
2,1/gün ort. +0 son gün +0,5 son 30g 0 commit 0 yazar JavaScript 22 Tem 2026 güncellendi 04 Eyl 2026 - 5
动物塑 AI 的身体参考：内分泌 → 器官 → 耳朵尾巴爪子 → 说话方式。以犬科为例，含亲密场景状态机，附九个真实踩过的坑。
0,9/gün ort. +0 son gün +0,1 son 30g — commit Python 15 Eyl 2026 güncellendi 01 Eki 2026 - 6
A machine-enforced workflow protocol for AI coding agents that eliminates false progress. Tasks require verifiable evidence to close, while
0,2/gün ort. +0 son gün +0,1 son 30g — commit Rust 04 May 2026 güncellendi 5 gün önce - 7
Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in saf
0,2/gün ort. +0 son gün +0,1 son 30g — commit Python 27 May 2026 güncellendi 09 Ağu 2026 - 8
An executable, no-code SDLC graph that carries a feature from spec to PR — with explicit nodes, guards, bounded retry loops, and durable sta
0,2/gün ort. +0 son gün +0,1 son 30g — commit Python 31 Tem 2026 güncellendi 21 Eyl 2026 - 9
Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live s
1,6/gün ort. +0 son gün +0 son 30g 0 commit 0 yazar Python 12 May 2026 güncellendi 02 Eki 2026 - 10
An open-source agent workflow engine & meta-harness: orchestrates Claude, Codex, and Pi to run multi-step work as a folder-as-agent pipeline
0,2/gün ort. -1 son gün +0 son 30g — commit Ruby 25 Nis 2026 güncellendi bugün - 11
Claude Code plugin that stops "almost done" loops — declare your stages in workflow.json, runs them as a state machine that auto-retries unt
0,1/gün ort. +0 son gün +0 son 30g — commit Shell 09 Nis 2026 güncellendi 15 May 2026 - 12
🪝 透明可控的 AI Agent 终端 | 状态机 · 多层记忆系统 · 沙箱防御 · 完整审计 · 多人设多技能
0,1/gün ort. +0 son gün +0 son 30g — commit Python 24 Nis 2026 güncellendi 10 Ağu 2026 - 13
Put an AI agent on rails: mount a Burr state machine as an MCP server so the agent can only take the next allowed step, with every step reco
0,1/gün ort. +0 son gün +0 son 30g — commit Python 19 May 2026 güncellendi dün - 14
A polygraph for your state machine: an LLM derives a formal model from your code, then Polygraph replays real traces against it and exhausti
0,1/gün ort. +0 son gün +0 son 30g — commit JavaScript 07 Tem 2026 güncellendi 13 Eyl 2026 - 15
🧠 The UI's brain in a state machine. Write once, run it on any JS runtime.
0,1/gün ort. +0 son gün +0 son 30g — commit TypeScript 13 Haz 2026 güncellendi 2 gün önce - 16
Deterministic-first execution engine for agent workflows in Go: the LLM extracts at the edge, a deterministic state machine decides. Zero de
1/gün ort. +0 son gün -0,1 son 30g — commit Go 29 Tem 2026 güncellendi 07 Ağu 2026 - 17
Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, own
1,2/gün ort. +0 son gün -0,1 son 30g 8 commit 1 yazar JavaScript 19 Ağu 2026 güncellendi 11 gün önce