{"slug": "e2b", "name": "E2B", "category": "security", "category_name": "Security and passwords", "description": "", "recommenders": 4, "commenters": 6, "warners": 0, "score": 4.056, "rising": 0.02, "first": "2025-11-22", "latest": "2026-08-03", "why": "For boxes.dev we use E2B - they had everything we needed at the time.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 2, "compare": 0, "warn": 0}, "spark": [1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "For boxes.dev we use E2B - they had everything we needed at the time.", "icon": true, "domain": "e2b.dev", "github_repo": null, "official_url": "https://e2b.dev", "pricing": "", "aliases": ["E2B", "e2b"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 786594897, "item_id": 49162181, "url": "https://news.ycombinator.com/item?id=49162181", "by": "dregitsky", "date": "2026-08-03", "stance": "recommend", "quote": "For boxes.dev we use E2B - they had everything we needed at the time.", "excerpt": "For boxes.dev we use E2B - they had everything we needed at the time. I'd love a standardized API / marketplace, but more just to try out new providers with differentiated features or pricing - we probably wouldn't be switching often / using multiple (unless customers asked us for more options). There are so many sandbox providers popping up! Our use case is pretty specific though - one persistent machine that you se", "context": "builds boxes.dev", "use_case": "sandbox VMs for agents", "switched_from": "", "story": "Devtools must be open source"}, {"id": 779023828, "item_id": 48688989, "url": "https://news.ycombinator.com/item?id=48688989", "by": "dbmikus", "date": "2026-06-26", "stance": "recommend", "quote": "Daytona, E2B, OpenComputer, Freestyle, Blaxel, Vercel, Modal, Cloudflare, Tensorlake, Superserve, etc. etc.", "excerpt": "Why do you want to self-host vs. using one of the many providers out there? Daytona, E2B, OpenComputer, Freestyle, Blaxel, Vercel, Modal, Cloudflare, Tensorlake, Superserve, etc. etc. Some of them work by pre-purchasing credits, so you can control the blast radius of spend. Also, if you want a more embedded sandbox runtime as a library instead of a daemon + REST API, you can check out libkrun (and friendly layers on ", "context": "", "use_case": "hosted sandboxes", "switched_from": "", "story": "Run isolated sandboxes with full lifecycle control: AWS introduces MicroVMs"}, {"id": 767969249, "item_id": 47998078, "url": "https://news.ycombinator.com/item?id=47998078", "by": "jdeng", "date": "2026-05-03", "stance": "recommend", "quote": "We used the E2B sandbox solution, and fortunately it supports volume", "excerpt": "Good comparison of the 2 approaches of agent harness. Vita AI[0] also picked the outside model. We used the E2B sandbox solution, and fortunately it supports volume, so we just create volumes for personal skills and organization workspace, and mount them to the sandbox. This elegantly solves the \"file system\" problem you mentioned. [0]: https://www.vita-ai.net (AI agent for content creation & social media management)", "context": "", "use_case": "agent sandbox", "switched_from": "", "story": "The agent harness belongs outside the sandbox"}, {"id": 736237298, "item_id": 46014831, "url": "https://news.ycombinator.com/item?id=46014831", "by": "mritchie712", "date": "2025-11-22", "stance": "recommend", "quote": "Give your agent a computer to use. We use e2b.dev, but Modal is great too.", "excerpt": "Some things we've[0] learned on agent design: 1. If your agent needs to write a lot of code, it's really hard to beat Claude Code (cc) / Agent SDK. We've tried many approaches and frameworks over the past 2 years (e.g. PydanticAI), but using cc is the first that has felt magic. 2. Vendor lock-in is a risk, but the bigger risk is having an agent that is less capable then what a user gets out of chatgpt because you're ", "context": "", "use_case": "agent sandbox computer", "switched_from": "", "story": "Agent design is still hard"}]}], "caveats": [], "who": [{"by": "dregitsky", "context": "builds boxes.dev", "url": "https://news.ycombinator.com/item?id=49162181", "date": "2026-08-03"}], "tags": [], "use_cases": ["sandbox vms for agents", "hosted sandboxes", "agent sandbox", "microvm sandboxing for ai agents", "code sandboxing", "agent sandbox computer"], "compared": [{"slug": "modal", "name": "Modal", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "firecracker", "name": "Firecracker", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49156111", "title": "Devtools must be open source", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48642510", "title": "Run isolated sandboxes with full lifecycle control: AWS introduces MicroVMs", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47990675", "title": "The agent harness belongs outside the sandbox", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46450931", "title": "Ask HN: What is the best microVMs for AI agents?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46135421", "title": "Show HN: Tentropy Core \u2013 open-source to run AI system code in Firecracker VMs", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46013935", "title": "Agent design is still hard", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {"neutral": 1}, "2026-01": {"neutral": 1}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {"recommend": 1}, "2026-06": {"recommend": 1}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 786594897, "item_id": 49162181, "url": "https://news.ycombinator.com/item?id=49162181", "by": "dregitsky", "date": "2026-08-03", "stance": "recommend", "quote": "For boxes.dev we use E2B - they had everything we needed at the time.", "excerpt": "For boxes.dev we use E2B - they had everything we needed at the time. I'd love a standardized API / marketplace, but more just to try out new providers with differentiated features or pricing - we probably wouldn't be switching often / using multiple (unless customers asked us for more options). There are so many sandbox providers popping up! Our use case is pretty specific though - one persistent machine that you se", "context": "builds boxes.dev", "use_case": "sandbox VMs for agents", "switched_from": "", "story": "Devtools must be open source"}, {"id": 779023828, "item_id": 48688989, "url": "https://news.ycombinator.com/item?id=48688989", "by": "dbmikus", "date": "2026-06-26", "stance": "recommend", "quote": "Daytona, E2B, OpenComputer, Freestyle, Blaxel, Vercel, Modal, Cloudflare, Tensorlake, Superserve, etc. etc.", "excerpt": "Why do you want to self-host vs. using one of the many providers out there? Daytona, E2B, OpenComputer, Freestyle, Blaxel, Vercel, Modal, Cloudflare, Tensorlake, Superserve, etc. etc. Some of them work by pre-purchasing credits, so you can control the blast radius of spend. Also, if you want a more embedded sandbox runtime as a library instead of a daemon + REST API, you can check out libkrun (and friendly layers on ", "context": "", "use_case": "hosted sandboxes", "switched_from": "", "story": "Run isolated sandboxes with full lifecycle control: AWS introduces MicroVMs"}, {"id": 767969249, "item_id": 47998078, "url": "https://news.ycombinator.com/item?id=47998078", "by": "jdeng", "date": "2026-05-03", "stance": "recommend", "quote": "We used the E2B sandbox solution, and fortunately it supports volume", "excerpt": "Good comparison of the 2 approaches of agent harness. Vita AI[0] also picked the outside model. We used the E2B sandbox solution, and fortunately it supports volume, so we just create volumes for personal skills and organization workspace, and mount them to the sandbox. This elegantly solves the \"file system\" problem you mentioned. [0]: https://www.vita-ai.net (AI agent for content creation & social media management)", "context": "", "use_case": "agent sandbox", "switched_from": "", "story": "The agent harness belongs outside the sandbox"}, {"id": 743380560, "item_id": 46461285, "url": "https://news.ycombinator.com/item?id=46461285", "by": "h1r1ms", "date": "2026-01-01", "stance": "neutral", "quote": "Its good, also perplexity, gork some more startups uses E2B. https://e2b.dev/ have you tried this one? E2b also uses firecracker.", "excerpt": "Its good, also perplexity, gork some more startups uses E2B. https://e2b.dev/ have you tried this one? E2b also uses firecracker.", "context": "", "use_case": "microVM sandboxing for AI agents", "switched_from": "", "story": "Ask HN: What is the best microVMs for AI agents?"}, {"id": 738167025, "item_id": 46135439, "url": "https://news.ycombinator.com/item?id=46135439", "by": "Jalil9", "date": "2025-12-03", "stance": "neutral", "quote": "Isolation: Firecracker MicroVMs (via E2B)", "excerpt": "Hi HN, I\u2019ve been building a 'Flight Simulator' for AI Engineers to practice fixing production failures (like RAG hallucinations, context window overflows, and rate limit storms). The hardest part was building the execution engine to run untrusted user code securely. I realized this infrastructure is useful on its own, so I open-sourced the core engine today. The Stack: Orchestrator: Next.js 15 (App Router) Isolation:", "context": "", "use_case": "code sandboxing", "switched_from": "", "story": "Show HN: Tentropy Core \u2013 open-source to run AI system code in Firecracker VMs"}, {"id": 736237298, "item_id": 46014831, "url": "https://news.ycombinator.com/item?id=46014831", "by": "mritchie712", "date": "2025-11-22", "stance": "recommend", "quote": "Give your agent a computer to use. We use e2b.dev, but Modal is great too.", "excerpt": "Some things we've[0] learned on agent design: 1. If your agent needs to write a lot of code, it's really hard to beat Claude Code (cc) / Agent SDK. We've tried many approaches and frameworks over the past 2 years (e.g. PydanticAI), but using cc is the first that has felt magic. 2. Vendor lock-in is a risk, but the bigger risk is having an agent that is less capable then what a user gets out of chatgpt because you're ", "context": "", "use_case": "agent sandbox computer", "switched_from": "", "story": "Agent design is still hard"}]}