Replit Agent / Code Execution API

license

Proprietary

source

closed

service

proprietary(Replit managed Autoscale Deployments, no self-host)

open-part

third-party isolation primitive omegajail(github.com/omegaup/omegajail) + an ARCHIVED thin client (replit-code-exec, ISC, read-only since 2025-02-11)

Closed managed service. The sandbox primitive (omegajail) is open source but it is a third-party dependency, not Replit's own open core, and the thin client is archived; there is no self-hostable open product, so an open dependency under a closed service is not open_core. Reclassified from open_core (borderline).

• https://replit.com/blog/ai-agents-code-execution recorded 2026-06-04

  Code Execution API uses omegajail (open source unprivileged container sandbox) on Replit's proprietary Autoscale Deployments; replit-code-exec PyPI client; Python-focused

• https://github.com/replit/replit-code-exec recorded 2026-06-04

  Replit code-exec client: stateless API for AI agents, runs untrusted Python in ephemeral unprivileged containers using omegajail (github.com/omegaup/omegajail); ISC license; repo ARCHIVED read-only 2025-02-11

• https://blog.replit.com/ai-agents-code-execution recorded 2026-06-04

  canonical Replit blog: Code Execution API uses omegajail on Autoscale Deployments, ~100ms, Python-focused (Feb 2024)

Replit platform serves >50M users (Replit docs/coverage) and runs >1M live projects on Cloud Run (Google Next '26, primary). The code-execution API specifically discloses no standalone usage figures, so adoption is attributed to the Replit Agent/platform surface it powers, not the raw API. Placed at 4 (platform-surface reach); the API alone would be lower.

• https://cloud.google.com/blog/products/serverless/whats-new-for-cloud-run-at-next26 recorded 2026-06-04

  Replit runs >1M live projects (on Cloud Run), primary-source scale signal for the Replit surface

• https://replit.com/products/agent recorded 2026-06-04

  Replit Agent product page (the agent surface the code-exec API backs)

Fast container-level execution tuned for agent code-eval, but container (not microVM) isolation, narrow language focus, and no persistence put it mid-tier vs microVM-backed peers. Note: the public self-serve client (replit-code-exec) is archived (2025-02-11); the capability now lives inside the Replit Agent surface.

• https://replit.com/blog/ai-agents-code-execution recorded 2026-06-04

  omegajail container sandbox, ~100ms start, Python-focused, stateless (stateful-Repl experiment discontinued)