Havuz

TrueForge, LLM çağrıları, araç kullanımı, oturum durumu ve kullanıcı onaylarını yöneten; UI ve API üzerinden kullanılabilen açık kaynak bir agent runtime sunuyor.

Neden yükseliyor · Agent runtime alanına kapsamlı, çalıştırılabilir bir ürün sunuyor; README'de SDK, UI, sandbox, MCP ve dağıtım seçenekleri aynı çözümün parçaları olarak gösteriliyor. 66 günde 5.982 yıldız ve son 28 günde 289 commit ile 17 farklı yazar, güçlü ilgi ve kayda değer geliştirme hareketliliğine işaret ediyor; bu ölçümler tek başına üretim olgunluğunu kanıtlamıyor.

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.

Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with defau

An agent with its own cloud and wallet. Prompt in, live link out. Written in Rust. CA: 0xa2753fd0bc86b8ceb55ffd2698679c7f214785f1

Claude Code skill for product videos: real browser capture, branded composition, and local mastering.

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

Follow RSI: human-reviewed progress in recursive self-improvement, with a Harness evolution evidence base.

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in

A harness for embodied intelligence — connecting agents, robot skills and the physical world through execution, feedback and recovery.

A minimal local coding agent in Go — a faithful port of Sebastian Raschka's mini-coding-agent, with no LLM framework.

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

Open-source terminal coding agent and SDK. Bring your own key for 25+ providers or a local model, with sandboxed subagents. Part of Directio

A token efficient, local LLM friendly agentic coding harness: a complete agent runtime (agent loop, tool pipeline, sandboxing, session persi

CLI for discovering local skills and agent profiles and installing them across coding clients through format adapters.

AI framework for Ruby/Rails developers

QuantClaw is a plug-and-play task-type routing quantization plugin for OpenClaw.

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。

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

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

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

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

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

Map, inspect, and audit AI-agent markdown ecosystems (skills, agents, commands, hooks) as a graph.

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

An agent / harness multiplexer that allows you to access your agents from any device and machine

基于pi agent core构建的harness agent

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

Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter jo

Multi-agent coding factory made fast.

Self-hosted 多用户 WeChat / 微信 AI 智能体控制台，支持 Web 管理、Docker部署、MCP、Skills、记忆、定时任务、沙盒执行和长期运行，支持分享AI Bot给团队成员。

A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS

Hive Agents harnest agent loop localfirts

10,000+ CLI tools. One CLI to access. Zero configuration

Make Worlds with Code — your coding agent writes procedural three.js scenes, games and objects, screenshots them, and fixes what it sees.

An AI agent for your desktop and terminal.

Web UI for spinning up isolated devcontainer instances for multiple simultaneous Claude Code workflows using VS Code.

Run any AI agent — Claude Code, GAP, LangGraph DeepAgents — in a hermetic sandbox. Reference implementation of the Harness Protocol.

AgenticFlowX is a VS Code workflow layer for AI coding. It gives you chat-first coding, Code / Explore / Spec modes, actionable markdown pre

agents-go workbench