Search results for "sandbox"
the easiest way to run natural language-described workflows automatically
Secure, Fast, and Extensible Sandbox runtime for AI agents.
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on you
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, GitHub Copilot, OpenRouter), custom skills, and MCP servers.
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 โ a secure foundation
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
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.
Security scanner for AI-generated ("vibe-coded") code. Runs SAST, DAST, and sandboxed exploit simulation across 15+ languages using 30+ tools. Catches what LLMs introduce before it ships โ wit
Open-source sandboxes for code execution, browser use, and AI agents.
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 โ no Do
A secure, durable runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
PraisonAI ๐ฆ โ Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, R
GitHub Agentic Workflows Firewall
AI-native runtime for the GolemCore ecosystem with skills, plugins, MCP, memory, and Hive.
Build and run autonomous AI agents with OpenClaw, Hermes, multiple model providers, orchestration, delegation, memory, skills, schedules, and chat connectors.
.NET (C#) boilerplate code generator that transforms an EF Core model into a fully customizable .NET (C#) + Angular web app
Run a fleet of AI agents on Kubernetes. Administer your cluster agentically
Agent! connects any AI to your Mac. 13 LLM providers โ cloud, local, or on-device. It writes code, builds Xcode projects, manages git, organizes files, automates Safari, controls any app, and handl
EdgeCrab ๐ฆ A Super Powerful Personal Assistant inspired by NousHermes and OpenClaw โ Rust-native, blazing-fast terminal UI, ReAct tool loop, multi-provider LLM support, ACP protocol, gateway adapters
Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI),
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
Autonomous AI agent that contributes to open source โ discovers repos, analyzes code, generates fixes, and submits PRs
SRE Agent - CNCF Sandbox Project
AgenticX is a unified, production-ready multi-agent platform โ Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical m
Autonomous CLI agent integrations for the Spring AI ecosystem with Claude Code, Gemini CLI, and secure sandbox execution
Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall isolation for Linux and macOS
Custom plugins for hermes-agent โ goal management, inter-agent bridge, model selection, cost control
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms
A local sandbox for your AI agents
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Give any AI agent a full desktop โ it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, internal tools. No API needed. One Docker comm
Cognithor - Agent OS: Local-first autonomous agent operating system. 16 LLM providers, 17 channels, 112+ MCP tools, 5-tier memory, A2A protocol, knowledge vault, voice, browser automation, Computer-us
Knowledge Engine for AI Agent Memory in 6 lines of code
Python Deep Agent framework built on top of Pydantic-AI, designed to help you quickly build production-grade autonomous AI agents with planning, filesystem operations, subagent delegation, skills, and
Advanced Mastra AI coding agent with secure sandbox execution, comprehensive file management, and multi-language support for Python, JavaScript, and TypeScript development workflows
Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of ta
Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. โ rebuilt from scratch. Unified architecture on your S3.
Rust SDK for packaging, securing, and operating portable AI agents.
mcpc is a CLI client for MCP. It supports persistent sessions, stdio/HTTP, OAuth 2.1, JSON output for code mode, proxy for AI sandboxes, and much more.
Nuwax Agent OS - The world's first universal agent operating system, building your private vertical general-purpose agent. ้็จๆบ่ฝไฝๆไฝ็ณป็ป๏ผๆ้ ไฝ ็งๆ็ๅ็ฑป้็จๆบ่ฝไฝใๆฐไธไปฃAIๅบ็จ่ฎพ่ฎกใๅผๅใๅฎ่ทตๅนณๅฐ๏ผๆ ้ไปฃ็ ๏ผ่ฝปๆพๅๅปบ๏ผ้ๅๅ็ฑปไบบ็พค๏ผๆฏๆๅค็ง็ซฏๅๅธๅAPI๏ผๆไพๅฎๅ็
Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway
An Agent Harness crafting around your project. From Desktop, CLI, editors, chatbots, APIs โ everywhere you work.
Agent Sandbox is an E2B compatible, enterprise-grade ai-first, cloud-native runtime environment for AI Agents. Allows Agents to securely run untrusted LLM-generated Code, Browser use, Computer use, an
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs direct
Agent ensembles to design, generate, and select the best code for every task.
A tool-use-focused LLM plugin for neovim.
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner to power user!
๐ค Kubernetes for AI Agents. Self-hosted, production-grade runtime for orchestrating LLM swarms and autonomous agents. TypeScript-native.
A curated list of products, benchmarks, and research papers on autonomous code agents. Beyond coding โ they're redefining how software changes the world.
A Model Context Protocol (MCP) server that gives Claude direct control over Strudel.cc for AI-assisted music generation and live coding.
Assorted useful tools, almost entirely generated using LLMs
One API for 20+ LLM providers, your databases, and your files โ self-hosted, open-source AI gateway with RAG, voice, and guardrails.
The Next-Gen Agent-Native Skill Recommendation Engine
See your agent think. Real-time observability dashboard for OpenClaw AI agents.
Umple: Model-Oriented Programming - embed models in code and vice versa and generate complete systems. Save yourself lots of coding. Do it collaboratively online in UmpleOnline, in an IDE or on the co
Self-hosted personal AI agent that lives in your DMs. Describe any workflow: triage Gmail, pull a Giphy feed, build a Slack bot, monitor markets. It writes the code, runs it, schedules it, and saves i
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
The Unofficial and Awesome Home Assistant MCP Server
A Model Context Protocol (MCP) server for managing and controlling SSH connections.
A secure, stable Rust alternative to openclaw/moltbot/clawdbot
A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, and a sandboxed runtime for improved safety. Under the hood, it is powered by a Claude Code
Must-read papers on Repository-level Code Generation & Issue Resolution ๐ฅ
Plugin suite + bundled MCP servers for Claude Code. Full delivery lifecycle: Agile pipeline with multi-model AI review, project bootstrap, documentation generation, codebase audits, performance optimi
Open-source calendar sync tool & universal calendar MCP server. Aggregate, sync and control calendars on Google, Outlook, Office 365, iCloud, CalDAV or ICS.
Token-efficient browser MCP server โ structured web pages for AI agents, not raw accessibility dumps
DSPEx - Declarative Self-improving Elixir | A BEAM-Native AI Program Optimization Framework
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Research, create, automate. Work so fast it feels like play. Get an ai co-worker on your machine. It can read-write files, code safely in sandbox, use your browser. Customize it with skills. Integrate
Security-first AI agent orchestration system. Built-in agents with predefined capabilities, strict guardrails on what they can and cannot do, and a four-layer defense system that enforces security at
Open-Sable is a local-first autonomous agent framework with AGI-inspired cognitive subsystems (goals, memory, metacognition, tool use). It can run continuously on your machine, integrate with chat int
An open-source AI assistant framework with skills and agent architecture
The AI agent that lives in your framework/browser
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
kbot โ the AI agent that dreams, learns, and evolves. 764+ tools, 35 agents, 20 providers. Music production, iPhone control, financial analysis, cyber threat intel. Always-on daemon. Runs offline. npm
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
An AI agent for teams, communities, and multi-user environments.
Open-source, secure environment with real-world tools for enterprise-grade agents.
Playwright MCP server
AgentScope Java: Agent-Oriented Programming for Building LLM Applications
Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).
MCP Server for Computer Use in Windows
Single-file memory layer for AI agents, sub mili-second RAG on Apple Silicon. Metal Optimized On-Device. No Server. No API. One File. Pure Swift
Teleton: Autonomous AI Agent for Telegram & TON Blockchain
JSON Agents - A universal JSON-native standard for describing AI agents, their capabilities, tools, runtimes, and governance in a portable, framework-agnostic format. Based on RFC 8259, JSON Schema 2
Git primitives for autonomous coding agents
AI-powered web app builder โ describe it, build it, ship it. 2-agent LangGraph system (Sonnet 4.5 + o4-mini) generates React apps from natural language with live preview and one-click deploy.
Transform any LLM into an autonomous security testing agent with structured prompts for seven-phase vulnerability hunting.
Run AI coding agents in hardened container sandboxes.
Turn natural language into executable code โ right in your browser. Lightweight AI chat powered by GPT-4o with sandboxed JavaScript execution.
Computer Environments Elicit General Agentic Intelligence in LLMs
A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. ๐ก๏ธ
TraceRoot - open-source observability and self-healing layer for AI agents. YC S25
MCAF is a framework for building software products together with AI coding agents.
Your AI-powered SWE teammate, built into your git workflow
Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.
Build AI agents that actually do things. Synapse is an open-source platform for creating, connecting, and orchestrating AI agents powered by any LLM โ local or cloud.
A MCP server to use StatCAN data
Autonomous Offensive Security Intelligence AI-powered multi-agent penetration testing
๐กโ๏ธAI-Powered Penetration Testing Framework with automated vulnerability scanning, multi-agent system, and compliance reporting๐กโ๏ธ
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
๐ก Enforce security policies, redact data, sandbox processes, and verify integrity for Model Context Protocol (MCP) server communication.
Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, spe
โก Enable real-time communication with Claude using this WebSocket server, designed for easy deployment and integration with the Claude Agent SDK.
Self-hosted AI Coding Agent powered by Claude | Autonomous Development Platform | POC for Human-AI Collaboration
Programmatically start (AI) sandboxes on top of CodeSandbox
Complete Workspace Template for OpenClaw - Full agent lifecycle with unified memory system (Markdown + SQLite), self-evolution, RAG. Not for SubAgent/Skill use.
This bridge integrates Ollama into any chat interface and lets you build your own multi-agent pipeline, including a built-in memory database.
Open source local sandboxing for running AI generated code.
Let your agent write code and execute code directly in the browser with WASM
OpenGrok MCP Server is a native Model Context Protocol server that bridges your organization's OpenGrok search engine with AI assistants โ enabling instant, natural language search and deep repository
A collection of Summoner clients and agents featuring example implementations and reusable templates
Lightweight, modular AI agent runtime โ thinks (Hrafn) and remembers (MuninnDB) ๐ฆโโฌ
Open-source autonomous AI assistant with 5-tier security, 62 tools, 14 LLM providers. Written in Rust. Single binary.
Self-hosted autonomous AI agent โ 9-layer cascade, Docker sandbox, encrypted vault, review/build/control plane, 1407+ tests
Fluid, elastic data abstraction and acceleration for BigData/AI applications in cloud. (Project under CNCF)
Nix packages for AI coding agents and development tools. Automatically updated daily.
Cloud native, ultra-high performance AI&API gateway, LLM API management, distribution system, open platform, supporting all AI APIs.๐ฆไบๅ็ใ่ถ ้ซๆง่ฝ AI&API็ฝๅ ณ๏ผLLM API ็ฎก็ใๅๅ็ณป็ปใๅผๆพๅนณๅฐ๏ผๆฏๆๆๆAI API๏ผไธ้ไบOpenAIใAzureใ
Analyze git code changes to generate structured review reports using flexible AI models and integrated workflows.
Build and manage AI-driven workspaces using Next.js, React, and TypeScript with customizable UI and MIT licensing.
BRUNELLA AGENT SYSTEM (BAS) โ A JรVล DIGITรLIS SZERVEZETE
The ultimate native macOS AI Agent. Blends local MLX SLMs with 3D cognitive Metal rendering and autonomous system integrations.
Open infrastructure/control plane for Unchained
An AI guardian that remembers, watches, and acts.
Computer use Docker Player (LLM Research)
Run Claude Code, Gemini, Codex โ or any coding agent โ in a clean, isolated sandbox with sensitive data redaction and observability baked in.
HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research
Safely run untrusted Python code using Pyodide and Deno
An open-source SSPM tool written in Go
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.