# E2B

> Secure cloud sandboxes for running AI-generated code.

E2B has a SharkScore of 71.7/100, ranked #17 of 665 in Frameworks & SDKs (updated 2026-11-19).

- Website: https://e2b.dev (e2b.dev)
- Kind: Tool · Pricing: Freemium · from $150/mo
- Maker: E2B
- Repository: https://github.com/e2b-dev/E2B
- Categories: Frameworks & SDKs, Agents & automation
- Verified by the maker: no

## Why it scores 71.7

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 56 | 30% |
| User reviews | no data | 25% |
| Maintenance | 100 | 20% |
| Trust & transparency | 80 | 15% |
| Momentum | no data | 10% |

Evidence covers 87% of the score's weight. Compared with other listings in Frameworks & SDKs.

## Evidence

| Signal | Value |
|---|---|
| Traffic rank (Tranco) | #207.8K |
| GitHub stars | 14.9K |
| Stars, last 90 days | — |
| Downloads, 30 days | 22.6M |
| Reviews | none yet |
| Last update | 0 days ago |
| Uptime, 30 days | 100.0% |
| Public pricing / Free tier / API / MCP | yes / yes / yes / yes |

## RankShark review

Automated evaluation by RankShark · 2026-11-18 · method review-1.0 · https://rankshark.pro/how-we-review
We were not paid for this review.

As of 2026-11-18, E2B provides isolated cloud machines for AI agents, with a free tier and paid plans that add separate usage costs. [E1][E2]

E2B provides isolated Linux microVM sandboxes that agents can use to run code, process data, and use tools. It offers an E2B-hosted cloud and deployment in a customer’s AWS, GCP, or Azure account. [E1][E3]

### Pros

- The free Hobby tier includes a $100 one-time usage credit and allows 10 concurrent sandboxes.
- The vendor lists deployment in its cloud or in customer AWS, GCP, or Azure accounts.
- The vendor provides SDK packages for sandboxes, code interpretation, and desktop use.

### Cons

- The listed plans have separate usage costs in addition to the plan price or credits.
- The Hobby tier limits sessions to 1 hour and concurrency to 10 sandboxes.
- Whether customer data is used for model training is not stated on the pages we checked.

### Pricing

| Plan | Price | Limits |
|---|---|---|
| Hobby | FREE / $100 in credits (+usage costs) | $100 one-time usage credit; sessions up to 1 hour; 10 concurrent sandboxes; default sandbox CPU and RAM. |
| Pro | $150/month (+usage costs) | Sessions up to 24 hours; 100 concurrent sandboxes, expandable to 1,100; custom sandbox CPU and RAM. |
| Enterprise | CUSTOM (+usage costs); starts at a $2,000/mo commit, with 500 concurrent included. | Committed usage and custom billing; multi-day and persistent sessions; tens of thousands of concurrent sandboxes; custom sizes and BYOC deployment. |

Checked 2026-11-18 · https://e2b.dev/pricing

### Sources

- https://e2b.dev/ (fetched 2026-11-18)
- https://e2b.dev/pricing (fetched 2026-11-18)
- https://docs.e2b.dev/ (fetched 2026-11-18)
- https://e2b.dev/privacy (fetched 2026-11-18)
- https://e2b.dev/terms (fetched 2026-11-18)
- https://trust.e2b.dev/ (fetched 2026-11-18)

## Top alternatives

1. [Model Context Protocol](https://rankshark.pro/tools/model-context-protocol) — SharkScore 81.7. Open protocol and SDKs that connect AI apps to tools and data.
2. [AI SDK](https://rankshark.pro/tools/ai-sdk) — SharkScore 77.7. TypeScript toolkit for building AI apps and agents.
3. [LangChain](https://rankshark.pro/tools/langchain) — SharkScore 77.7. Build agents and LLM apps in Python and TypeScript.
4. [LangSmith](https://rankshark.pro/tools/langsmith) — SharkScore 76.9. Tracing, evaluation and monitoring for LLM apps.
5. [Transformers](https://rankshark.pro/tools/transformers) — SharkScore 76.9. Hugging Face's library of pretrained models for text, vision and audio.

---
Source: https://rankshark.pro/tools/e2b · Method v2026-11-18.2: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
