Havuz

One-click sandboxes for AI agents, with egress policy, MCPs, skills and audit. Built on NVIDIA OpenShell.

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

Run a coding agent in a staged workspace, review its file changes, and apply only what you keep.

Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.

A sandbox service for running untrusted, agent-authored code that reports the isolation boundary each run executed behind. Lessons, no clone

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

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

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

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

OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, manage

Runs Claude Code and pi agents in parallel on your Mac, one Docker sandbox per issue. A host agent hands out the work, watches every sandbox

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

Open-source, self-hosted alternative to Claude Managed Agents: run Claude Code, Codex, Hermes, DeepSeek Harness and Pi as managed Agents on

Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack

Prompt-injection, jailbreak and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanit

Run OpenClaw, Hermes and your own agents in microsandbox microVMs. One reviewable TOML role sets image, allowed domains and host-bound secre

Retired. Excalibur (xcb) routed coding tasks across Codex and Claude Code subscriptions. Source and releases are preserved for reference.

Control plane for swarms of sandboxed AI agents: run, fork, pause, steer, and checkpoint agents that each work inside their own isolated san

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

Open-source sandboxes for AI agents and code execution.

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?

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies i

Lightweight Linux sandbox for AI agents. Kernel-native isolation (namespaces, cgroups, seccomp, Landlock) with REST API, MCP bridge, and web

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

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

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

Safely run untrusted repos (fake-interview malware, infostealers, RATs) in a locked-down, ephemeral container. No host secrets reachable, ne

Your setup, on cloud machines, for coding agents. Fork your own dev machine in seconds and let Claude Code and Codex work on it.

epoint.az ödəniş gateway-inin lokal sandbox-u. Bir konteynerdə: API, ödəniş səhifəsi, callback-lər və dashboard.

Minimal surface, complete architecture: a small, local-first coding-agent harness that re-derives the invariants of DeepSeek Harness with fe

A new kind of IDE for agentic engineering

A desktop app for creating and managing isolated Mac environments.

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

Self-hosted AI gateway with a built-in dashboard. OpenAI-compatible API, multi-tenant, sandboxed code execution, MCP integrations, file stor

Open-source continuation of Daytona — secure, elastic sandbox infrastructure for AI code execution and agent workflows. Community fork of th

Vmware Workstation 17 Pro - Local Windows build featuring every professional module and a simple install routine.

自托管 AI Coding Agent（Rust）：常驻 Runtime 撑起终端 / 浏览器 / 手机三端；每行改动可追溯到具体 Agent 与工具调用，子 Agent 的活由退出码裁决，检查点回退、目标 token 预算与验收清单跨轮次跨重启累计，用量与反馈账本留在本地。接任

herdr plugin that mirrors a git worktree into an E2B sandbox — one box or a branch-per-agent fleet, with a TUI dashboard

Give Pi one typed tool instead of a toolbox.

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

Your agent, across all your machines. A self-hosted, web-based AI agent: one server holds every conversation and works in a cloud sandbox or

🔒 Jail OpenCode, Claude Code, Copilot CLI and OmO in micro-VMs: only your project folders, only the networks you allow.

Open-source, self-hosted AI agent for terminal, Telegram and Raspberry Pi. Local Ollama or Claude/Codex workers, enforced by a deterministic

Security-first, self-hosted AI agents - isolation you can prove, not just promise.

MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-

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

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

Warm, disposable GitHub Actions runners with Docker Sandboxes microVM isolation across Linux, macOS, and Windows hosts. Designed for teams t

🪝 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

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