Havuz

Run untrusted Erlang inside an Elixir host, on the same BEAM, with no ambient authority.

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

Self-hosted agent runtime: run any harness in isolated sandboxes with streaming UI,HITL, budgets and durable events.

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

Static reverse engineering of untrusted files with verifiable, byte-anchored evidence. Open tools (Ghidra, JADX, LIEF, YARA-X, Babel) in loc

Agent dashboard runs reliability scans, skills, and network access probes.

The Omarchy Development Kit

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

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

Run Claude Code, Codex and other coding agents in a local VM on a clone of your project, then review their changes like a pull request. Mac

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

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

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

The most comprehensive comparison of platforms offering cloud runtime / sandbox / VM compute for agents. By boat.dev.

Governed AI agents for sensitive data and business-critical apps. Agents never hold credentials: a gateway checks every call against per-res

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.

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

Agents you can inspect, replay and trust. An agent framework for TypeScript and Python, built on an append-only event log.

A hidden Omarchy desktop for your AI agents: they launch, drive and screenshot apps and shell plugins there, never on yours.

A pure-Go JavaScript runtime built for running many small plugin sandboxes fast.

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifac

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.

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

The OpenAI Agents API, open source and self-hosted. Run Codex, Claude Code or MiniMax Code on your own machines with your own models, throug

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)

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

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

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

Execute agent-generated TypeScript in isolated WebAssembly, with runtime-enforced semantic permissions.

aside-codemode, Aside içindeki JavaScript REPL üzerinden dosya araması ve browser işlerini tek çağrıda çalıştırıp modele yalnızca seçilmiş sonuçları döndürür.

Neden yükseliyor · 14 günlük yaşına karşılık 124 yıldız ve son 28 günde 287 commit görünmesi, hızlı bir başlangıç ve yoğun geliştirme faaliyetine işaret ediyor. README'deki ölçülebilir arama ve browser örnekleri de ilgiyi artırabilir; ancak yükselişin kesin nedeni bilinmiyor. Commit'lerin yalnızca 2 farklı yazardan gelmesi, faaliyetin geniş katılımla desteklendiğini göstermiyor.

100% free, open-source personal agents for your messaging apps, tools, and services

A sandbox for the third-party APIs you depend on. Built from the provider's spec, it fails on purpose, and it replays the exact failure prod

多文件夹 workspace：让 DSH（DeepSeek Harness）的 Agent 不只能读写主目录，还能同时读写你添加的其他文件夹。Multi-folder workspace for DeepSeek Harness: let the agent read and w

Finds and fixes agent network access risks in OpenShell and Docker sandboxes.

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

Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in tool

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

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.

Strong agent. Short leash

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

useAgent, farklı coding agent’lara ortak workspace, izole computer ortamı ve ekip araçları sunan self-hosted bir çalışma platformudur.

Neden yükseliyor · 29 günde 361 yıldız ve son 28 günde 314 commit dikkat çekiyor; agent’ları ortak bir çalışma ortamı ve gerçek bilgisayar erişimiyle birleştirme fikri güncel bir ihtiyaca hitap ediyor. Ancak commitlerin tek yazardan gelmesi, hareketliliğin geniş katkı veya benimsemeyle desteklendiğini göstermiyor; yükselişin kesin nedeni verilerden bilinmiyor.

Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KV

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

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

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

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

OpenSandbox sandbox backend for LangChain Deep Agents - run agent-generated code and file operations in an isolated OpenSandbox environment.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and

Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed hist