E2B
Sandboxed cloud environments for AI agents to run code.
Key features
- One Linux microVM per agent session with shell and browser
- Run sandboxes on E2B cloud or AWS, GCP, or Azure
- Run Python or JavaScript and return charts, tables, and images
- Pause, resume, snapshot, or fork a sandbox
- Desktop with mouse, keyboard, and a live screen stream
- Category
- Agents
- Who it's for
- Teams that build and run AI agents.
- Tags
- sandboxterminaljavascriptpythonimage-video
- Website
- e2b.dev
- Listed
- 2026-09-15
Frequently asked questions
Is E2B free?
E2B has a free plan, with paid tiers for more usage or features.
How much does E2B cost?
Paid plans from $150/month, according to its pricing page.
What is E2B used for?
Sandboxed cloud environments for AI agents to run code. Typical uses: one Linux microVM per agent session with shell and browser; run sandboxes on E2B cloud or AWS, GCP, or Azure; run Python or JavaScript and return charts, tables, and images.
What are the best E2B alternatives?
Alternatives in the same category include Omnara, Haystack, Composio, Flowise, Modal.
Related in Agents
See all →- Chainguard Workspaces Isolates untrusted code in Chainguard-hardened microVMs so agents cannot steal your secrets. In beta.
- Docker Agentic Platform Runs your agents in isolated sandboxes on Docker-managed cloud infrastructure. Experimental.
- OpenShell Safe, private runtime for fleets of autonomous AI agents. Sandboxes enforce file, syscall, and network policy. Apache 2.0.
- Agensh Self-organized multi-agent harness. Agents claim sub-tasks and merge progress without a central orchestrator. MIT.
- Agentic Batch Changes Describe a change in plain language. The agent scopes it across your indexed codebase and tracks it through to merge.
- Agno Python framework for agents, formerly Phidata.