E2B
14,961Secure sandboxes for AI-generated code execution.
Activity band details
Activity band A to F: a bin of a score that adds GitHub stars (log scale), a push to the upstream repository in the 12 months before `as_of`, the number of declared integration surfaces and, where the catalogue records them, citing papers and benchmark evaluations. It measures popularity and activity. It is not a level of evidence: no band means a paper cites the tool or that it was measured. Recency is judged as of 2026-11-22.
Computed band: D
(raw score 4.67).
Shown band: D
.
Facets:
documented_in=0evaluated_on=0integration_surfaces=1paper_citations=0recent_push=2stars=1.67
Source of truth: pipeline/maturity/score.py
Description
Cloud-hosted sandboxed runtime for executing AI-generated code with isolation, snapshotting, and fine-grained resource limits. Per-session ephemeral environments with filesystem and network controls.
Why it's included
Canonical recovery × post_generation × fully_autonomous exemplar. Sandboxed execution is a load-bearing supervision primitive for autonomous coding agents.
Security notes
Hosted sandbox provider. Review data-residency and tenancy isolation posture for sensitive workloads. Local/on-prem alternatives (Daytona, Modal, Firecracker) are worth evaluating for high-trust environments.
Addresses failure modes
These tags are the catalog's claim about what E2B is built to catch or prevent. A tag is not a test result. SAICA-Bench has not measured E2B, so none of these tags is tested here.
- Supply-chain attack — Slopsquatting, typosquatting, compromised MCP servers.
- Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.
- Scope creep — Actions outside declared task boundary.
Related tools
Composes with: Context Hub