Browse: Security
the easiest way to run natural language-described workflows automatically
Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Framework for AI Backend. Build and run AI agents like microservices - scalable, observable, and identity-aware from day one.
SRE Agent - CNCF Sandbox Project
Open-source sandboxes for code execution, browser use, and AI agents.
Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup — a secure foundation
Autonomous CLI agent integrations for the Spring AI ecosystem with Claude Code, Gemini CLI, and secure sandbox execution
A self-hosted AI workspace with chat, code execution, parallel multi-agent orchestration, and a skill marketplace. Runs on macOS and Windows. Everything executes inside a secure Ubuntu sandbox — no Do
A secure, durable runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
Rust SDK for packaging, securing, and operating portable AI agents.
Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall isolation for Linux and macOS
Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway
A secure, stable Rust alternative to openclaw/moltbot/clawdbot
A god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In this virtual world, AI characters possess independent thinking and memory, capable of autonomous social
Frontier self improving AI intern / coworker
Secure AI conversations with documents, video, audio, and more. Personal workspaces for focused context, group spaces for shared insight. Classify docs, reuse prompts, and extend with modular features
A general-purpose coding agent that runs inside an NVIDIA OpenShell sandbox, orchestrated by Deep Agents and powered by NVIDIA Nemotron. The agent writes and executes code in an isolated, policy-gover
Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.
Open-source, secure environment with real-world tools for enterprise-grade agents.
Run AI coding agents in hardened container sandboxes.
Project CodeGuard is an open-source, model-agnostic security framework that embeds secure-by-default practices into AI coding agent workflows. It provides comprehensive security rules that guide AI as
Computer Environments Elicit General Agentic Intelligence in LLMs
A self-improving AI agent that learns from experience. Runs entirely on a local 9B model. Security by absence — dangerous capabilities were never built.
Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds secure-by-default practices into AI coding workflows (generation and review). It ships core security rules, transla
Advanced Mastra AI coding agent with secure sandbox execution, comprehensive file management, and multi-language support for Python, JavaScript, and TypeScript development workflows
Block AI agent access to sensitive macOS paths and log all actions to protect private data during command execution.
A structured multi-agent framework for coordinated AI collaboration
Turn natural language into executable code — right in your browser. Lightweight AI chat powered by GPT-4o with sandboxed JavaScript execution.
🎨 Create stunning logos effortlessly with ai-logo-maker, your offline tool for designing unique identities while keeping your data secure and local.
Build and run local AI agents with multi-model support, modular skills, secure controls, and multi-channel access for personal automation tasks.
Enable local document ingestion and retrieval-augmented generation with a secure, .NET-based pipeline that keeps data on your machine.
Provide open-source AI bots for Lark to automate tasks like brainstorming, project planning, content creation, and monitoring within a secure chat interface.
Simplify AI agent deployment and management with OpenClaw-Turbo’s secure, intuitive interface optimized for Linux and Chinese language support.
🤖 Generate secure, automated repo documentation and pull request checks with a safe-by-default toolchain for coding agents.
Connect AI agents representing humans through the A2A protocol for seamless, secure interaction across apps and tools.
The full-stack framework built for AI. Auth, database, email, mobile — ready in one command.
Self-hosted autonomous AI agent — 9-layer cascade, Docker sandbox, encrypted vault, review/build/control plane, 1407+ tests
Run Claude Code, Gemini, Codex — or any coding agent — in a clean, isolated sandbox with sensitive data redaction and observability baked in.
Safely run untrusted Python code using Pyodide and Deno
Computer use Docker Player (LLM Research)
Skip to content github / docs Code Issues 80 Pull requests 35 Discussions Actions Projects 2 Security Insights Merge branch 'main' into 1862-Add-Travis-CI-migration-table 1862-Add-Travis-CI-migration