Havuz

Open-source sandboxes for AI agents and code execution.

基于 Rust、Slint 和 Skia 的 AI 算法可视化桌面应用，支持代码对话、文件附件、隔离验证与交互式动画演示。

Train computer-use agents end-to-end on real desktops, at scale: a high-performance runtime where 8K+ live environments on one laptop thread

Omnigent, farklı coding agent'ları ortak bir ortamda çalıştırıp yönetmeye yönelik açık kaynaklı bir orchestration framework'üdür.

Neden yükseliyor · 108 günlük yaşına karşılık 10.271 yıldız ve son 28 günde 1.146 commit ile 22 farklı yazar, hem yüksek ilgiyi hem de belirgin geliştirme aktivitesini gösteriyor. İlginin hangi özelliğinden veya dış etkenden kaynaklandığı verilen verilerle doğrulanamıyor.

Detonate files & URLs in cloud malware sandboxes (Hybrid Analysis, tria.ge, ANY.RUN) and enrich IOCs across MalwareBazaar, ThreatFox, URLhau

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc

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

Capka AI — An open-source, self-hosted sandbox for AI agents. A community-driven alternative to Claude's Cowork

An open source AI roleplay agent harness. One click builds an autonomous character agent that creates with you. Websites, code, music, video

MCP server: build → see → interact → debug loop over native GUI apps

A personal AI agent operating environment you self-host on Cloudflare.

Runtime-neutral AI execution bridge for Claude Agent SDK, Codex app-server, and Agent Client Protocol (ACP).

Run a command in a sandbox with the same flags on every OS — one capability model compiled to Seatbelt (macOS), gVisor (Linux), and AppConta

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

Run coding agents unattended. Agents write the code. Axocoatl writes the receipt. Claude Code, Codex or a local model in a sandbox; the host

Manage OpenClaw in your team (Enterprise) by providing it compute infrastructure, tool integration, Authentication and security primitives

sandboxd, coding agent’ların uygulama oluşturup canlı preview URL’lerinde sunması için Docker tabanlı, self-hosted bir ortam sağlar.

Neden yükseliyor · Kendi sunucusunda çalışan, API üzerinden kullanılabilen bir coding-agent app builder vaadi güncel bir ihtiyaca hitap ediyor; README ayrıca Trendshift görünürlüğünü öne çıkarıyor. Ancak yalnızca 955 yıldız ve bu tanıtım bilgileri yükselişin nedenini kanıtlamaz; son 28 günde 2 commit ve 1 farklı yazar görülmesi geliştirme temposuna dair daha sınırlı kanıt sunuyor.

A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.

A block-based 3D space crafting game: explore procedurally generated planets across many star systems, mine and craft, tame creatures, build

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README

A new kind of IDE for agentic engineering

3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in pa

Highly isolated Linux container environments optimized specifically for mcp-servers. Secure AI agent tool execution.

Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work wi

Autonomous coding-agent loop. Runs Claude Code or Codex against your repo in a Docker sandbox, iterating implementer → reviewer until the pl

Vyomi — the Multi-Cloud Digital Twin Runtime. A faithful, running replica of AWS, GCP & Azure on your machine (real backends, standard SDKs)

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

Dispatch your task backlog to local, interactive AI coding agents. One git worktree per task, sandboxed by default.

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol server

Run Windows and Linux programs on Windows, Linux and Android. A user-mode NT and Linux kernel emulator with WHP/KVM acceleration.

One isolated Lima VM per GitHub project — sandboxed Claude Code/Codex, Docker, Node, signed git

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

forkd, warmed bir microVM snapshot'ından KVM izolasyonunu koruyarak hızlıca yeni sandbox'lar üreten ve çalışan VM'leri branch edebilen bir runtime'dır.

Neden yükseliyor · AI agent'lar için hızlı ve izole çalışma ortamları ihtiyacına doğrudan hitap ediyor; 139 günde 2.910 yıldız dikkat çekici ilgiye işaret ediyor. README, 100 microVM'i yaklaşık 101 ms'de başlatma ve canlı BRANCH için 56 ms p50 ölçümü bildiriyor; bunlar proje dokümantasyonundaki ölçümler, bağımsız doğrulama değil. Son 28 günde 21 commit aktivite gösteriyor, ancak yalnızca 2 farklı yazar katkı tabanının dar olduğunu düşündürüyor.

Run Claude Code, Codex and Gemini CLI as an HTTP API, each on its own sandbox.

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

Run coding agents like infrastructure, not terminal sessions. Warren manages isolation, lifecycle, spend, recovery, and Git delivery on comp

Open-source, multi-model agent for coding, research, and everyday workflows. Independently built engine with our own Alysis Sandbox, strict

Civilization sandbox in your browser. Tribes invent their own languages, cultures and wars, from the stone age to computers. Built in Rust a

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

Durable Cloudflare computers for agents: run repos, steer live workspaces, verify results, and return receipts.

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic

Effect building blocks for agentic ai

All-in-one Docker/Podman image: hermes-agent + hermes-webui + hermes-dashboard in a single container

🪝 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

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

AI pair programming in your terminal — one static binary, sub-ms startup, any model

Cheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, a

⚡ Code mode for agents