HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
kstenerud
yoloai
Go2026–2026
kstenerud / yoloai

yoloai

Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.

4Distinct people
52Mentions
0Explicit recommenders
255GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 7:57:46 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by week52 dated mentions

Observed mentions: 2026-02-25 20:23:05 UTC to 2026-08-20 10:59:24 UTC. Weeks start Monday, UTC.

024682026-02-23 00:00:00 UTC to 2026-03-02 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 commentsFeb 232026-03-02 00:00:00 UTC to 2026-03-09 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-03-09 00:00:00 UTC to 2026-03-16 00:00:00 UTC (exclusive): 6 mentions; 1 submissions, 5 comments2026-03-16 00:00:00 UTC to 2026-03-23 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2026-03-23 00:00:00 UTC to 2026-03-30 00:00:00 UTC (exclusive): 6 mentions; 0 submissions, 6 comments2026-03-30 00:00:00 UTC to 2026-04-06 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2026-04-06 00:00:00 UTC to 2026-04-13 00:00:00 UTC (exclusive): 3 mentions; 0 submissions, 3 comments2026-04-13 00:00:00 UTC to 2026-04-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-04-20 00:00:00 UTC to 2026-04-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-04-27 00:00:00 UTC to 2026-05-04 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-04 00:00:00 UTC to 2026-05-11 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-11 00:00:00 UTC to 2026-05-18 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-18 00:00:00 UTC to 2026-05-25 00:00:00 UTC (exclusive): 4 mentions; 0 submissions, 4 commentsMay 182026-05-25 00:00:00 UTC to 2026-06-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-06-01 00:00:00 UTC to 2026-06-08 00:00:00 UTC (exclusive): 3 mentions; 0 submissions, 3 comments2026-06-08 00:00:00 UTC to 2026-06-15 00:00:00 UTC (exclusive): 4 mentions; 0 submissions, 4 comments2026-06-15 00:00:00 UTC to 2026-06-22 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-22 00:00:00 UTC to 2026-06-29 00:00:00 UTC (exclusive): 3 mentions; 0 submissions, 3 comments2026-06-29 00:00:00 UTC to 2026-07-06 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-07-06 00:00:00 UTC to 2026-07-13 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-07-13 00:00:00 UTC to 2026-07-20 00:00:00 UTC (exclusive): 8 mentions; 0 submissions, 8 comments2026-07-20 00:00:00 UTC to 2026-07-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-07-27 00:00:00 UTC to 2026-08-03 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-08-03 00:00:00 UTC to 2026-08-10 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-08-10 00:00:00 UTC to 2026-08-17 00:00:00 UTC (exclusive): 3 mentions; 0 submissions, 3 comments2026-08-17 00:00:00 UTC to 2026-08-24 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsAug 17

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Feb 232026-02-23 00:00:00 UTC2026-03-02 00:00:00 UTC202
Mar 22026-03-02 00:00:00 UTC2026-03-09 00:00:00 UTC101
Mar 92026-03-09 00:00:00 UTC2026-03-16 00:00:00 UTC615
Mar 162026-03-16 00:00:00 UTC2026-03-23 00:00:00 UTC202
Mar 232026-03-23 00:00:00 UTC2026-03-30 00:00:00 UTC606
Mar 302026-03-30 00:00:00 UTC2026-04-06 00:00:00 UTC202
Apr 62026-04-06 00:00:00 UTC2026-04-13 00:00:00 UTC303
Apr 132026-04-13 00:00:00 UTC2026-04-20 00:00:00 UTC000
Apr 202026-04-20 00:00:00 UTC2026-04-27 00:00:00 UTC000
Apr 272026-04-27 00:00:00 UTC2026-05-04 00:00:00 UTC000
May 42026-05-04 00:00:00 UTC2026-05-11 00:00:00 UTC000
May 112026-05-11 00:00:00 UTC2026-05-18 00:00:00 UTC000
May 182026-05-18 00:00:00 UTC2026-05-25 00:00:00 UTC404
May 252026-05-25 00:00:00 UTC2026-06-01 00:00:00 UTC101
Jun 12026-06-01 00:00:00 UTC2026-06-08 00:00:00 UTC303
Jun 82026-06-08 00:00:00 UTC2026-06-15 00:00:00 UTC404
Jun 152026-06-15 00:00:00 UTC2026-06-22 00:00:00 UTC000
Jun 222026-06-22 00:00:00 UTC2026-06-29 00:00:00 UTC303
Jun 292026-06-29 00:00:00 UTC2026-07-06 00:00:00 UTC101
Jul 62026-07-06 00:00:00 UTC2026-07-13 00:00:00 UTC101
Jul 132026-07-13 00:00:00 UTC2026-07-20 00:00:00 UTC808
Jul 202026-07-20 00:00:00 UTC2026-07-27 00:00:00 UTC000
Jul 272026-07-27 00:00:00 UTC2026-08-03 00:00:00 UTC000
Aug 32026-08-03 00:00:00 UTC2026-08-10 00:00:00 UTC101
Aug 102026-08-10 00:00:00 UTC2026-08-17 00:00:00 UTC303
Aug 172026-08-17 00:00:00 UTC2026-08-24 00:00:00 UTC101

What Hacker News says

6 sources
kstenerud·Mar 12, 2026Submission

Show HN: YoloAI: Sandboxed agent, no permission fatigue, diff/apply workflow

The problem: tools like Claude Code ask you to approve every file edit, every shell command. After hundreds of prompts you stop reading and just hit "yes", or even worse you reach for `--dangerously-skip-permissions` and hope for the best. Neither option is great. yoloAI runs your AI coding agents (Claude Code, Codex, Gemini, Aider, OpenCode) inside disposable containers so that they can operate without permission prompts. Your files are never touched because the agent works on an isolated copy. When it's done, `yoloai diff` shows exactly what changed, and `yoloai apply` patches your real project. Workflow: yoloai new fix-bug ./my-project --prompt "fix the failing tests" # agent works freely inside the sandbox yoloai diff fix-bug # see what changed yoloai apply fix-bug # patch your real project (either workdir changes
Read the rest
or new git commits) yoloai destroy fix-bug # toss the container This isn't just some Docker wrapper script. yoloAI handles the full lifecycle: copying your project into the sandbox, setting up git baselines, injecting credentials, managing agent state across sessions, and giving you a clean diff/apply workflow to review changes before they land. Your originals are protected until you explicitly choose what to keep. Single Go binary. Works on Linux (Docker), macOS (Docker Desktop, Tart VMs, or native Seatbelt sandboxing). Profiles with user-supplied Dockerfiles for reproducible environments. Network isolation with domain allowlists. Five agents supported out of the box. Early access: The core workflow is solid, rough edges remain. MIT licensed. https://github.com/kstenerud/yoloai I built this because I was tired of babysitting Claude Code through permission prompts. Now I can't live without it. Happy to answer questions about the design, the tradeoffs, or the sandboxing approach.
1 points · Open discussion
I took a more paranoid approach to sandboxing agents. They can do whatever they want inside their container, and then I choose which of their changes to apply outside as commits: ┌─ YOLO shell ──────────────────────┬─ Outer shell ─────────────────────┐ │ │ │ │ yoloai new myproject . -a │ │ │ │ │ │ # Tell the agent what to do, │ │ │ # have it commit when done. │ │ │ │ yoloai diff myproject │ │ │ yoloai apply myproject │ │ │ # Rev
Read the rest
iew and accept the commits. │ │ │ │ │ # ... next task, next commit ... │ │ │ │ yoloai apply myproject │ │ │ │ │ │ # When you have a good set of │ │ │ # commits, push: │ │ │ git push │ │ │ │ │ │ # Done? Tear it down: │ │ │ yoloai destroy myproject │ └───────────────────────────────────┴───────────────────────────────────┘ Works with Docker, Seatbelt, and Tart backends (I've even had it build an iOS app inside a seatbelt container). https://github.com/kstenerud/yoloai
In Agent Safehouse – macOS-native sandboxing for local agents
yoloAI: Fearless YOLO sandbox for your agent. Run your agents contained (container or VM, Linux or Mac), with all restrictions removed. Workflow: ┌─ YOLO shell ──────────────────────┬─ Outer shell ─────────────────────┐ │ │ │ │ yoloai new myproject . -a │ │ │ │ │ │ # Tell the agent what to do, │ │ │ # have it commit when done. │ │ │ │ yoloai diff myproject │ │ │ yoloai apply myproject │ │ │ # Review and accept the commits. │
Read the rest
│ │ │ │ # ... next task, next commit ... │ │ │ │ yoloai apply myproject │ │ │ │ │ │ # When you have a good set of │ │ │ # commits, push: │ │ │ git push │ │ │ │ │ │ # Done? Tear it down: │ │ │ yoloai destroy myproject │ └───────────────────────────────────┴───────────────────────────────────┘ Sandboxes: Docker (Linux, Mac), Seatbelt (Mac), Tart (Mac) Everything's contained in a single go binary. Just build and run. https://github.com/kstenerud/yoloai
In Ask HN: What Are You Working On? (March 2026)

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.