✓It Still Works
  • Home
  • Search
  • Discover
  • Catalogue
  • Categories
  • What changed
  • Developer repos
  • How we check
  • Developer utilities
  • Games and play
  • Everyday tools
  • Music and audio
  • Images and photos
  • Save and convert media
  • Writing and publishing
  • Draw and diagram
  • Coding and upskilling
  • 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

roll a workspace back when an agent run goes wrong

Not what you meant?

  • check on a coding agent from your phone while away from the desk
  • run agents with your real dev environment rather than a hosted sandbox
  • keep agent work on hardware you control
  • run several coding agents on isolated worktrees

Tools(5)

roll a workspace back when an agent run goes wrong · fire a webhook when a long agent run completes · run several coding agents at once without them colliding · run a personal AI agent on your own machine rather than someone else's

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

  1. A Claude Code plugin that coordinates 19 agents and 39 skills across several models

    Why this one

    • roll a workspace back when an agent run goes wrong
    • coordinate more than one model on a single coding task
    • add approval gates before an agent makes a change you cannot undo

    On the record

    • Free
    • No signup
    • First check

    Last checked 3 days ago

    Open↗
  2. Desktop notifications when Claude Code or Codex needs you

    Why this one

    • fire a webhook when a long agent run completes
    • stop checking whether the agent has finished yet
    • get a sound or desktop alert when Claude Code needs an answer

    On the record

    • Free
    • No signup
    • First check

    Last checked 3 days ago

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

    Why this one

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

    On the record

    • Free
    • No signup
    • First check

    Last checked 3 days ago

    Open↗
  4. A self-hosted AI agent with persistent memory that writes its own skills

    Why this one

    • run a personal AI agent on your own machine rather than someone else's
    • reach the same agent from Telegram or Slack instead of a web app

    On the record

    • Free tier
    • Needs an account
    • First check

    Last checked 3 days ago

    Open↗
  5. One workspace for whichever coding agent you are using this month

    Why this one

    • review changes from several parallel agent runs in one place
    • switch between coding agents without rebuilding your workflow
    • keep each agent's changes isolated until you have looked at them

    On the record

    • Free tier
    • Your own API key
    • First check

    Last checked 3 days ago

    Open↗