Havuz

Munder Difflin, mevcut terminal tabanlı coding agent’larını yerel bir masaüstü uygulamasında koordine eden multi-agent harness’tir.

Neden yükseliyor · Çoklu agent iş akışlarına yönelik ilgiyle, zaten kullanılan terminal CLI’larını tek bir arayüzde birleştirme vaadi örtüşüyor. 119 günde 8.016 yıldız ve son 28 günde 177 commit ile 7 farklı yazar kayda değer ilgi ve geliştirme aktivitesi gösteriyor; README’deki trend rozetleri ise proje beyanı olduğundan tek başına benimseme kanıtı sayılmaz.

LongHorizon-Harness, mevcut AI agent’ların desktop apps ve CLI üzerinde uzun süren görevleri adım adım yürütmesini sağlayan bir Python harness’idir.

Neden yükseliyor · 55 günde 1631 yıldıza ulaşması ve long-horizon computer-use agent’ların pratikteki ilerleme, doğrulama ve toparlanma sorunlarına odaklanması ilgiyi açıklayabilir. README, Hugging Face Daily Papers sıralamasında #1 olduğunu da bildiriyor; bu iddia tek başına benimseme veya teknik başarı kanıtı değil. Son 28 günde commit ve farklı yazar sayısının ikisi de 0 olması, mevcut ivmenin yakın tarihli geliştirme aktivitesiyle desteklenmediğini gösteriyor.

天枢harness是一个的终端编程智能体，它要回答的核心问题是：模型何以稳定地交付——目标不漂移、完成有证据、验证有闭环，不说"应该修好了"。为此它在模型与真实世界之间建立一层认知执行环境（CVM），把目标、状态、证据、资源、权限与终止条件从对话历史中外部化，由运行时持续管理。同

Open-Source Software factory for Open Models

DSH Plugin 插件市场 - DeepSeek Harness Plugin Market (DSH) 下载与安装 · 插件大全

TaiyiForge, Claude, Codex, Cursor ve OpenCode için AI destekli yazılım geliştirmeyi aşamalı ve denetlenebilir bir workflow'a dönüştüren TypeScript tabanlı bir araçtır.

Neden yükseliyor · 115 günlük bir repo için 886 yıldız dikkat çekici; AI coding agent'ları için tekrarlanabilir workflow ve kontrol ihtiyacına denk geliyor olabilir. Ancak yıldızların nedenini doğrulayan ek veri yok ve son 28 günde commit ile farklı yazar sayısı sıfır; bu nedenle ilginin güncel geliştirme faaliyetiyle desteklendiği söylenemez.

Official Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

An organizable, terminal-first agentic workspace with plugins

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud

CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.

The agent harness for .NET: embeddable, extensible, remotely controllable and ready to use.

Build an ETF research agent, one working module at a time. Runnable code, bilingual deep dives, and a traceable 0→1 journey.｜逐模块构建 ETF 投研 Ag

Runs, traces, tool calls, LLM calls, errors, latency, tokens, and eventually detection for agents that appear stuck or caught in loops.

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.

Benzi is code intelligence infrastructure for AI models. It compiles your codebase into a resolved, queryable map of calls, data flow, contr

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud,

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）

HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code,

A workflow harness that helps AI coding agents plan, review, test, and ship safer code.

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

Recommend AI coding harness changes from repository context and coding signals, then distribute approved rules, skills, hooks and agents to

An open-source build system that compiles your specs and architecture into working code.

A benchmark for evaluating LLM × harness performance.

An Orchestrate multiple coding agent desktop app

Evaluating frontier models on real-world ai-infra engineering tasks

零远程行为、子代理协同、支持自主进化的自治 Agent 编队丨 Autonomous Agent Fleet with Zero-Remote Behavior: Sub-agent Collaboration and Self-Evolution

Kit is a coding agent runtime. Claude Code but faster, cheaper and more to the point 🎯

Tools for testing APIs with AI agents

Aetox harness: a local-first Windows AI environment - model, skills, team and memory as one system. Two doors - an Assistant that adapts to

Run agents on a cloud machine. Steer them from your desktop or phone.

A terminal coding interface that brings the DeepSeek Harness kernel's full capability set — special modes, plugins, model & subagent managem

Open-source desktop AI coding platform with built-in Pi Agent (pi-coding-agent) — a graphical AI programming assistant that lets non-technic

Marketplace for agents, skills, plugins, and extensions for the Agav CLI harness.

One-shot LLM eval cases by NAGI STUDIO - same prompt, different agents (model + harness), runnable artifacts side by side.

Agent Harness Platform — shareable workspaces, MCP tools, skills, memory, and cron/webhook automations. Self-hosted and transparent.

self-extending sandboxed agentic harness. a loop, two tools and an llm

A personal AI agent to help you think, create, and get things done. Powered by open models, on your computer or in the cloud.

Elixir-native LangChain, LangGraph, and DeepAgents for traceable LLM apps: OTP workflows, tools, memory, human-in-the-loop, streaming, custo

Mercury CLI: multiple AI coding sessions in one terminal. Mix and match provider and locally hosted models, spawn cross-company agents & wor

A harness for hosted Grok Bot crews. Its core rule: it is not allowed to guess.

A hello-world startup repository for users to help them get started with Agav

Craft is a Claude Code plugin that asks you the product questions and works out the technical ones. Features get planned, built, and tested,

Keep it simple, stupid. A highly performant agent harness inspired by Pi, built in Rust.

Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.

Axon reads the logs your AI coding-agent harnesses already write — Claude Code, Codex, OpenCode — and shows which harness, project, agent, a

Edit a DeepSeek Harness (dsh) custom mode: system prompt, base mode, and plugin switches.

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

Codex harness for consistent AI-assisted development workflows, including agent instructions, standard setup/check/test/eval scripts, CI,