Open-source, secure environment with real-world tools for enterprise-grade agents.
Repository Index
142,273 visible repositories in the index
1–24 of 28 · Most stars
🧱 easy, fast, programmable and local-first microVM runtime and library
A secure Python sandbox, written in Rust, for code written by AI.
- python
- rust
- sandbox
- sandboxing
An Autonomous LLM Agent for Complex Task Solving
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
- agent-framework
- ai-agents
- ai-safety
- compliance
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
The World's First Virtual Terminal for AI Agents
- agent-sandbox
- agent-tools
- ai-agents
- bash
A computer you can curl ⚡
- ai
- open-webui
- agentic-ai
- ai-agents
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
- google-meet
- meeting-assistant
- meeting-minutes
- meeting-notes
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents
- meta-agents
- meta-optimization
- runtime-supervision
- workflow-automation
Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app
Sandboxes for coding agents, CI runners and RL training
- agent-runtime
- sandbox
- browser-agent
- browser-use
E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can connect to any LLM for secure computer use.
A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel-based team collaboration. Under the hood, it is powered by a Claude Code–based agent.
Give any AI agent the ability to code
A ChatGPT plugin that allows you to load and edit your local files in a controlled way, as well as run any Python, JavaScript, and bash script. (No longer active - check https://github.com/ykdojo/safeclaw/)
NekroAgent 是一个面向多人互动场景的跨平台 Agent 框架,集 Claude Code 沙盒执行、工作区编排、长期记忆、结构化 MCP 管理与可视化控制台于一体,兼具高扩展性、多模态交互、实时状态推送和自动化运行能力。项目支持 QQ、Discord、Telegram、Minecraft、BilibiliLive、WeChat、Email、SSE(SDK) 等多种平台接入,应用于构建高智能聊天机器人,可扩展为具备代码执行、工具调用、插件协作和复杂任务处理能力的通用 Agent 系统
The Cloud Sandbox Built for AI Agents
Lightweight and portable LLM sandbox runtime (code interpreter) Python library.
- code-generation
- code-interpreter
- large-language-models
- llm-sandbox
The repository host gives no description.
Judging backend server for the DMOJ online judge.
- online-judge
- sandbox
- competitive-programming
- computer-science
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
- cybersecurity
- security
- agent-security
- agents
Safely run your agents using any coding harness
- harness
- harness-ai
- security
The repository host gives no description.