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
Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development
1/gün ort. +0 son gün — commit Python 28 Mar 2026 güncellendi dün - 52
端到端智能体平台：把本机的 AI Agent 变成人人可用的 Web 产品（Vue 3 + Flask + Go WS 网关 + Docker 部署）
0,9/gün ort. +0 son gün — commit Python 08 Eki 2026 güncellendi 9 gün önce - 53
A workflow harness that helps AI coding agents plan, review, test, and ship safer code.
0,9/gün ort. +0 son gün — commit Shell 25 Mar 2026 güncellendi 10 Eyl 2026 - 54
Open-source terminal coding agent and SDK. Bring your own key for 25+ providers or a local model, with sandboxed subagents. Part of Directio
0,9/gün ort. +0 son gün — commit TypeScript 21 Nis 2026 güncellendi bugün - 55
Official codebase for the paper "Sharpening Tax in Post-Training"
0,9/gün ort. +0 son gün — commit Python 30 Eyl 2026 güncellendi 03 Eki 2026 - 56
A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.
0,8/gün ort. +0 son gün — commit TypeScript 22 Eyl 2026 güncellendi 5 gün önce - 57
An open-source build system that compiles your specs and architecture into working code.
0,8/gün ort. +0 son gün — commit Python 06 Mar 2026 güncellendi 07 Ağu 2026 - 58
Official implementation of “Harness Optimization for Agentic Multi-Reference Image Generation”
0,8/gün ort. +0 son gün — commit Python 25 Eyl 2026 güncellendi 29 Eyl 2026 - 59
Recommend AI coding harness changes from repository context and coding signals, then distribute approved rules, skills, hooks and agents to
0,8/gün ort. +0 son gün — commit Go 15 Eki 2026 güncellendi 17 gün önce - 60
Tinybot is a lightweight personal AI Agent that is constantly evolving
0,7/gün ort. +0 son gün 2 commit 1 yazar Rust 09 Nis 2026 güncellendi 11 gün önce - 61
AI coding agent for Visual Studio 2022/2026 — chat, inline completion, and five autonomous agents that explore, plan, patch, and verify buil
0,7/gün ort. +0 son gün — commit C# 03 May 2026 güncellendi 3 gün önce - 62
Fa - Factory Agent. Cross-platform AI agent harness for Dart and Flutter — streaming providers, agent loop with tools, session persistence,
0,7/gün ort. +0 son gün — commit Dart 13 Tem 2026 güncellendi bugün - 63
Desktop app for harness engineering, loop engineering, graph engineering—and whatever comes next in local AI-agent workflows.
0,7/gün ort. +1 son gün — commit Rust 30 Mar 2026 güncellendi 5 gün önce - 64
A benchmark for evaluating LLM × harness performance.
0,7/gün ort. +0 son gün 0 commit 0 yazar Python 15 May 2026 güncellendi 03 Ağu 2026 - 65
智能体 = 大模型 + Harness。深入剖析 Harness 工程原理、设计、实现与实践！
0,7/gün ort. +0 son gün 6 commit 3 yazar Python 05 Nis 2026 güncellendi dün - 66
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. +0 son gün — commit JavaScript 12 Ağu 2026 güncellendi dün - 67
An Orchestrate multiple coding agent desktop app
0,7/gün ort. +0 son gün 1 commit 1 yazar TypeScript 28 Haz 2026 güncellendi 5 gün önce - 68
CLI for discovering local skills and agent profiles and installing them across coding clients through format adapters.
0,7/gün ort. +0 son gün — commit Python 18 Eyl 2026 güncellendi 11 gün önce - 69
WorkBuddy Tools — 在不同账号间无缝衔接你的工作。支持国内版/国际版多账号管理、快速切换、选择性数据迁移与 Token 用量统计，全部本地运行。
0,7/gün ort. +0 son gün — commit Python 14 Eyl 2026 güncellendi 3 gün önce - 70
OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact a
0,7/gün ort. +0 son gün 0 commit 0 yazar TypeScript 24 May 2026 güncellendi 09 Eyl 2026 - 71
The DeepSeek and OpenRouter Harness built on Elixir
0,7/gün ort. +1 son gün — commit Elixir 17 Ağu 2026 güncellendi bugün - 72
开源 · 本地优先的 AI 智能体：编程与实干兼备。 自带模型密钥，内置 MCP、技能、插件、工作流、知识库以及数据库。
0,7/gün ort. +0 son gün — commit TypeScript 30 Ağu 2026 güncellendi dün - 73
Small, modular coding-agent harness for Node.js
0,6/gün ort. +0 son gün — commit JavaScript 28 Ağu 2026 güncellendi 04 Eyl 2026 - 74
Enables LLM to use a cli environment.
0,6/gün ort. +0 son gün 256 commit 2 yazar Python 25 May 2026 güncellendi dün - 75
AI framework for Ruby/Rails developers
0,6/gün ort. +0 son gün 9 commit 1 yazar Ruby 05 May 2026 güncellendi 16 gün önce - 76
Aetox harness: a local-first Windows AI environment - model, skills, team and memory as one system. Two doors - an Assistant that adapts to
0,6/gün ort. +2 son gün 149 commit 2 yazar Go 03 May 2026 güncellendi bugün - 77
QuantClaw is a plug-and-play task-type routing quantization plugin for OpenClaw.
0,6/gün ort. +0 son gün 0 commit 0 yazar TypeScript 22 Nis 2026 güncellendi 27 Nis 2026 - 78
Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。
0,6/gün ort. +0 son gün — commit Python 30 Mar 2026 güncellendi 07 Eyl 2026 - 79
A terminal coding interface that brings the DeepSeek Harness kernel's full capability set — special modes, plugins, model & subagent managem
0,5/gün ort. +0 son gün 4 commit 1 yazar TypeScript 14 Ağu 2026 güncellendi 11 gün önce - 80
Open-source desktop AI coding platform with built-in Pi Agent (pi-coding-agent) — a graphical AI programming assistant that lets non-technic
0,5/gün ort. +0 son gün — commit TypeScript 03 Haz 2026 güncellendi 3 gün önce - 81
Open-source enterprise AI workforce platform — containerized roles, declarative skills, MCP tools, policy-driven security, K8s-native schedu
0,5/gün ort. +0 son gün — commit Dockerfile 16 Mar 2026 güncellendi 31 Mar 2026 - 82
Agent Harness Platform — shareable workspaces, MCP tools, skills, memory, and cron/webhook automations. Self-hosted and transparent.
0,5/gün ort. +0 son gün — commit TypeScript 23 Nis 2026 güncellendi 05 Eyl 2026 - 83
Nausicaa treats an Agent run as a dynamic topology of Lanes rather than one fixed linear loop. The model can decide when to observe, fan out
0,5/gün ort. +0 son gün — commit TypeScript 05 Eyl 2026 güncellendi 03 Eki 2026 - 84
One-shot LLM eval cases by NAGI STUDIO - same prompt, different agents (model + harness), runnable artifacts side by side.
0,5/gün ort. +0 son gün — commit HTML 09 Haz 2026 güncellendi 2 gün önce - 85
self-extending sandboxed agentic harness. a loop, two tools and an llm
0,5/gün ort. +0 son gün — commit JavaScript 13 Nis 2026 güncellendi 27 gün önce - 86
CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.
0,5/gün ort. +1 son gün — commit Python 09 May 2026 güncellendi 2 gün önce - 87
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque database
0,5/gün ort. +0 son gün — commit Python 08 Haz 2026 güncellendi 2 gün önce - 88
Mercury CLI: multiple AI coding sessions in one terminal. Mix and match provider and locally hosted models, spawn cross-company agents & wor
0,4/gün ort. +2 son gün — commit TypeScript 04 Eyl 2026 güncellendi bugün - 89
Cross-platform AI agent harness for 12+ hour autonomous development cycles. Spec-driven, DAG-orchestrated, with a 3-critic evaluation pipeli
0,4/gün ort. +0 son gün — commit TypeScript 08 Nis 2026 güncellendi 20 gün önce - 90
Elixir-native LangChain, LangGraph, and DeepAgents for traceable LLM apps: OTP workflows, tools, memory, human-in-the-loop, streaming, custo
0,4/gün ort. +0 son gün — commit Elixir 12 Haz 2026 güncellendi 20 gün önce - 91
A human-governed AI coding workflow that distills ephemeral session context into persistent project memory—making work traceable, reviewable
0,4/gün ort. +0 son gün — commit JavaScript 01 May 2026 güncellendi 12 Tem 2026 - 92
A portable, self-improving SDLC harness for agent fleets — plan → issues → build → test → review → UX-eval → security → ship, on any runtime
0,4/gün ort. +0 son gün — commit Shell 24 Tem 2026 güncellendi 2 gün önce - 93
Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activa
0,4/gün ort. +0 son gün — commit JavaScript 15 May 2026 güncellendi 27 Haz 2026 - 94
Ship AI products powered by the best harnesses without building another agent loop
0,4/gün ort. +1 son gün — commit Swift 21 Tem 2026 güncellendi 3 gün önce - 95
sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nod
0,4/gün ort. +0 son gün — commit TypeScript 18 Haz 2026 güncellendi 3 gün önce - 96
Map, inspect, and audit AI-agent markdown ecosystems (skills, agents, commands, hooks) as a graph.
0,4/gün ort. +0 son gün — commit TypeScript 18 Nis 2026 güncellendi 02 Eyl 2026 - 97
Craft is a Claude Code plugin that asks you the product questions and works out the technical ones. Features get planned, built, and tested,
0,4/gün ort. +0 son gün — commit Shell 01 May 2026 güncellendi bugün - 98
Lightweight Claude Code alternative: ~1.8% lines, ~90% capability
0,4/gün ort. +0 son gün — commit TypeScript 01 Nis 2026 güncellendi 03 Nis 2026 - 99
Continual harness optimization
0,4/gün ort. +0 son gün — commit Python 06 Nis 2026 güncellendi 07 Ağu 2026 - 1000,4/gün ort. +0 son gün — commit Dart 06 Ağu 2026 güncellendi 3 gün önce