Havuz

Proper sandboxing for agentic coding and web browsing

Security scanner for Agent Skills — uncover hidden threats before deployment.

An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27

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

An open-source workspace for coding agents, running on your own machine. More work. Less AI waste. Same subscriptions.

A hypervisor and sandbox cloud for self-hosting AI agents and RL

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

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

CLI for Local Isolated Environments for Coding Agents

Secure runtime for code-mode agents. Open source, Apache-2.0.

A fast, embeddable JavaScript engine for Go: QuickJS-NG reimplemented in pure Go, no cgo.

在網路受限的 Docker Dev Container 裡安全執行 Claude Code，透過 iptables/ipset 防火牆白名單限制 AI Agent 的對外連線，降低資料外洩與誤操作風險。改自 Anthropic 官方 .devcontainer 參考實作。

Self-hosted platform for running AI coding agents (Claude Code, Codex, …) in isolated sandboxes – web UI, CLI, API and MCP

Agent interoperability and security, out of the box. The network layer underneath A2A: reachable, end-to-end sealed and payable agents witho

Wiggle, Claude’ın kod çalıştırma ortamına benzediği iddia edilen araç ve paket setini Docker image olarak yerelde çalıştırmayı sağlar.

Neden yükseliyor · Claude’ın kod çalıştırma ortamının yerelde kullanılabilir bir kopyası olduğu iddiası ve beraberindeki araçlar ile skill dosyaları ilgi çekici. Ancak 23 günlük geçmiş, 91 yıldız, son 28 günde 7 commit ve tek farklı yazar, benimseme ya da sürdürülebilirlik konusunda güçlü kanıt oluşturmuyor.

ParaGravity, Google Antigravity için ayrı hesapları ve çalışma alanlarını bağımsız profillerde çalıştırıp yönetmeye yarayan bir CLI aracıdır.

Neden yükseliyor · Beş günlük yaşına karşılık 216 yıldız ve son 28 günde 39 commit dikkat çekici erken ilgi ve geliştirme aktivitesine işaret ediyor; ancak bu kadar kısa geçmişte yıldızlar kalıcı benimseme kanıtı değil. Üç farklı yazar katkısı, aktivitenin yalnızca tek yazara bağlı olmadığını gösterse de topluluk ölçeği hakkında güçlü sonuç çıkarmak için yeterli değil.

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit

A safe, zero-dependency expression language for rules, filters, and templates

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

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

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

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

TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool calling.

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Strong agent. Short leash

Aggregated Kubernetes apiserver and e2b-compatible data plane for warm-pooled agent sandboxes on microVMs. Sandboxes are served from per-nod

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

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

Effect building blocks for agentic ai

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

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

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

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

Local AI agent sandbox runtime with Firecracker, gVisor, and NVIDIA GPU sandbox support.

Sandboxed OCI container images for AI coding agents, built reproducibly with Nix.

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

Micro-VM sandbox for AI agents: isolated, gated and auditable, to prove what your agents did

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

Deterministic bytecode VM for agent execution - verified images, snapshots and a hash-chained replay journal

WorkBuddy Multi-Account Manager & Automated Check-in Toolkit (多账号轮换、全域工作区打通与自动化签到)

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

A new kind of IDE for agentic engineering

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

Self-hosted, privacy-first Markdown editor & live preview. Documents never leave your browser: no backend, no tracking, strict CSP, sandboxe

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

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

Ocean Drive, Miami Beach at golden-hour sunrise: a photoreal open-world Three.js sandbox in the browser. Walk, drive any car, hit the beach.

Polyglot, deterministic, sandboxed WASM runtime. Run or compile any language to one sealed, reproducible artifact.

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

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