# e2b-dev/runtime > E2B's open-source runtime: the backend that runs isolated Firecracker microVM sandboxes where AI agents execute untrusted code. Includes the API, orchestrator, edge router, and envd inside each VM. - Magnitude: 1.1 out of 10 — Steady - Stars: 1,630 total · +2 stars on 2026-09-28 (UTC), ≈ 4 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Go · License: Apache-2.0 · Created: 2023-08-10 · Last push: 2026-09-28 - GitHub: https://github.com/e2b-dev/runtime · Homepage: https://e2b.dev/?utm_source=github&utm_medium=referral&utm_campaign=repo_website&utm_content=runtime · Page: https://gitnova.dev/en/r/e2b-dev/runtime ## Useful for - Run a sandbox for agent code execution via the Python or JS SDK - Deploy the full E2B Embed stack on a single Linux host with KVM via docker compose - Set up pause/resume and forking of sandboxes for long-running agent sessions ## Why it’s here - 2 stars so far today, about 4 expected by the end of the day. - Recent forks include notable developers: @xxuejie (261 followers). ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 450 - Issues and pull requests: 3,654 - Watchers: 10 - Average over the last week: 5 per day - Usual pace: 15 per day - Latest release: 2026.30 (2026-09-10) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-04 … 2026-11-02: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 09-15 4.8, 09-16 6.0, 09-17 5.8, 09-18 3.3, 09-19 2.3, 09-20 1.7, 09-21 1.8, 09-22 1.3, 09-23 1.4, 09-24 1.6, 09-25 1.6, 09-26 1.1, 09-27 1.6, 09-28 1.1 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-28 10:29 UTC, updated every 30 minutes.