✓It Still Works
  • Home
  • Search
  • Discover
  • Catalogue
  • Categories
  • What changed
  • Developer repos
  • How we check
  • Coding and upskilling
  • Developer utilities
  • Draw and diagram
  • Everyday tools
  • Games and play
  • Images and photos
  • Music and audio
  • Save and convert media
  • Testin category
  • Writing and publishing
  • Cloudflare (4)
  • Vercel (3)
  • GitHub Pages (2)
  • Google Cloud (2)
  • nginx (self-hosted) (2)
  • Google (1)
  • Netlify (1)
712 checks loggedEvery listing, every sweepSign in
Theme
✓It Still Works
Sign in

Every listing is checked on a schedule. No numbers we cannot measure.

How we checkGraveyardSubmit something
  • Discover
  • Catalogue
  • Changes
  • Repos

I understood

sandbox an agent whose blast radius you are unsure of

Not what you meant?

  • try a coding agent inside a WebContainer
  • see what your coding agent is doing without switching windows
  • know an agent finished while you are working in something else
  • keep an eye on several agent clients from one place on macOS

Tools(5)

sandbox an agent whose blast radius you are unsure of · see which of your agent nodes are actually online · sandbox an agent in Docker before letting it touch anything · sandbox Claude Code away from your working tree

5 listings shown. Every result was live at its last check.

  1. A common layer over Claude Code, Codex and the agents you write yourself

    Why this one

    • sandbox an agent whose blast radius you are unsure of
    • put spend caps and policies around agents you already run
    • work on the same live agent session with someone else

    On the record

    • Free
    • Your own API key

    Last checked 2 days ago

    Open↗
  2. 你的 AI Agent 桌面工作台

    Why this one

    • see which of your agent nodes are actually online
    • use Claude, Codex and Grok from one desktop app instead of three
    • hand a task to whichever model suits it without switching tools

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗
  3. Run coding agents in parallel from a TUI or web dashboard

    Why this one

    • sandbox an agent in Docker before letting it touch anything
    • run several coding agents at once without them colliding
    • give each agent its own branch through a git worktree

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗
  4. run coding agents in a sandbox, review the branch

    Why this one

    • sandbox Claude Code away from your working tree
    • review an agent's branch after it stops

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗
  5. Agents handle tasks, message each other, and review each other's code

    Why this one

    • let agents pass work between themselves instead of routing it yourself
    • have one agent review another's code before you see it
    • track what a group of agents is doing on a kanban board

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗