abshkbh / arrakis
A fully customizable and self-hosted sandboxing solution for AI agent code execution and computer use. It features out-of-the-box support for backtracking, a simple REST API and Python SDK, automatic port forwarding, and secure MicroVM isolation. Perfect for safely running, testing, and backtracking multi-step agent workflows.
☆366Updated 3 weeks ago
Alternatives and similar repositories for arrakis:
Users that are interested in arrakis are comparing it to the libraries listed below
- llm-consortium orchestrates mulitple LLMs, iteratively refines & achieves consensus.☆248Updated this week
- Gumloop Unified Model Context Protocol (guMCP)☆373Updated this week
- Deep Research for your internal data☆313Updated this week
- Build reliable AI Workflows and Agents with humans in the loop, structured outputs and durable execution.☆363Updated last week
- E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can connect to any LLM for secure computer use.☆644Updated this week
- ☆130Updated 2 months ago
- OpenPipe ART (Agent Reinforcement Trainer): train LLM agents☆318Updated this week
- Claude Deep Research config for Claude Code.☆170Updated last month
- An MCP Server that's also an MCP Client. Useful for letting Claude develop and test MCPs without needing to reset the application.☆117Updated last month
- Sidecar is the AI brains for the Aide editor and works alongside it, locally on your machine☆547Updated 3 weeks ago
- ☆85Updated 3 months ago
- Together Open Deep Research☆254Updated 2 weeks ago
- An MCP server that autonomously evaluates web applications.☆669Updated this week
- Helping you select an AI agent framework☆215Updated last week
- 🤖 Headless IDE for AI agents☆184Updated 2 weeks ago
- A MCP server implementation for hyperbrowser☆256Updated 3 weeks ago
- Cognitive Architectures for Multi-Agent Teams☆659Updated this week
- Foyle is a copilot to help developers deploy and operate their applications.☆127Updated last month
- the simplest self-building general autonomous agent☆306Updated 6 months ago
- CodeAct Agent SDK with an AST-based code execution engine, enabling stop/start workflows, tool-level state management, and enhanced obser…☆214Updated this week
- Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborat…☆426Updated 2 weeks ago
- Manage multiple AI agents like Codex, Claude Code, and Aider. 10x your productivity☆650Updated last week
- Letting Claude Code develop his own MCP tools :)☆98Updated last month
- MCPEngine is a client, server, and proxy implementation of model context protocol (MCP) specifically oriented towards Enterprise and real…☆186Updated this week
- Like Claude Artifacts but lives in a single static HTML page which you can use with any language model of your choosing☆205Updated 2 months ago
- A single interface to build and evaluate different agent frameworks☆344Updated this week
- Infrastructure for AI code interpreting that's powering E2B.☆406Updated this week
- Prompt engineering, automated.☆304Updated 2 weeks ago
- Securely run AI-generated code in stateful sandboxes that run forever.☆183Updated 2 weeks ago
- Claude Memory: Long-term memory for Claude☆415Updated 2 weeks ago