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.
β281Updated last week
Alternatives and similar repositories for arrakis:
Users that are interested in arrakis are comparing it to the libraries listed below
- Prompt engineering, automated.β296Updated 2 weeks ago
- Deep Research for your internal dataβ303Updated this week
- π€ Headless IDE for AI agentsβ179Updated 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.β112Updated last month
- β84Updated 3 months ago
- Letting Claude Code develop his own MCP tools :)β96Updated last month
- Build reliable AI Workflows and Agents with humans in the loop, structured outputs and durable execution.β357Updated last week
- Simple AI coder that can do most of my work for me, including working on himself.β235Updated this week
- E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can connect to any LLM for secure computer use.β574Updated this week
- the simplest self-building general autonomous agentβ303Updated 5 months ago
- CodeAct Agent SDK with an AST-based code execution engine, enabling stop/start workflows, tool-level state management, and enhanced obserβ¦β207Updated this week
- Infrastructure for AI code interpreting that's powering E2B.β376Updated this week
- Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and versβ¦β288Updated last week
- β122Updated last month
- Claude Deep Research config for Claude Code.β163Updated 3 weeks ago
- Like Claude Artifacts but lives in a single static HTML page which you can use with any language model of your choosingβ204Updated last month
- β183Updated 4 months ago
- Giving Claude ability to run code with E2B via MCP (Model Context Protocol)β200Updated 2 weeks ago
- Manage multiple AI agents like Claude Code and Aider. 10x your productivityβ413Updated this week
- β133Updated 2 months ago
- β86Updated last month
- Foyle is a copilot to help developers deploy and operate their applications.β124Updated 3 weeks ago
- An example chatbot application built on the Letta API, which makes each chatbot a stateful agent (agent with memory) under the hood.β26Updated 2 weeks ago
- For LLMs to better code with Jina APIβ144Updated this week
- Verdict is a library for scaling judge-time compute.β193Updated 3 weeks ago
- A toolkit for building computer use AI agentsβ155Updated 3 weeks ago
- Example code and guides for building with Scrapybaraβ117Updated 3 weeks ago
- Gumloop Unified Model Context Protocol (guMCP)β302Updated this week
- Smithery connects language models to Model Context Protocols, allowing you to build agents that use resources and tools without being oveβ¦β157Updated last week
- The Moshi speech-to-speech model, deployed to Modal with a realtime CLI chatβ56Updated 6 months ago