Containerized environments for coding agents: each agent works in its own fresh container and git branch, with execution history and terminal access.
Code Execution
Code execution servers let an assistant execute scripts or work with a runtime. Check isolation, supported languages, time limits and filesystem access before choosing one for your workflow.

Run untrusted Python/JavaScript code in WebAssembly sandboxes.
Access any API through its existing OpenAPI documentation.
Run JavaScript snippets in isolated Docker sandboxes with on-the-fly npm dependency installation and clean teardown.
JavaScript sandbox that uses V8 isolation to run AI-generated code locally, with heap snapshotting for persistent sessions.
Run LLM-generated code in a YepCode sandbox and create custom MCP tools in JavaScript or Python with npm and PyPI packages.
Access any API via its OpenAPI specification, with full JSON Schema support for parameters and request bodies.
Delegate tasks to other AI providers' models, e.g. ask OpenAI to generate an image.
Python runtime interpreter that executes submitted code in an isolated environment.
Submit SLURM jobs, run YAML workflows, monitor GPU resources, manage SSH profiles and sync files with local or SSH-remote HPC clusters.
Control Google Colab notebooks and assign GPUs (T4/L4/A100). Fork of Google's colab-mcp with all tools visible at startup and Windows support.
Agent-oriented programming language: agents emit a JSON AST that the compiler validates, type- and effect-checks, verifies with Z3/SMT and compiles to WASM.
SWI-Prolog execution for LLMs with CLP(FD), negation as failure and recursion.
Execute code through the Piston remote code execution engine.
Code-mode MCP server: collapses user-defined tools into code execution plus docs search, sandboxed in node:vm, WASM or remote microVMs.
Self-hostable GPU-aware job broker: dispatch long-running or GPU jobs that outlive the session, route them by VRAM tier and monitor them across sessions.
Code and logic calculator with an offline core: run code, exact symbolic math, SMT/logic and complexity analysis, with optional gVisor/AppContainer sandboxing.
E2B cloud sandboxes: create isolated Linux VMs, clone repos, run commands, manage files and perform git operations without touching the local machine.
MATLAB integration: execute code, run async jobs with progress reporting, get interactive Plotly plots and expose custom .m functions as tools.
Persistent cloud dev environments for coding agents: create, run commands, checkpoint and fork, with files, services and terminal state kept between calls.
Dedicated Linux VM sandboxes for untrusted, model-generated code: run commands, move files, expose a preview URL and destroy the VM.