✓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

let agents pass work between themselves instead of routing it yourself

Not what you meant?

  • keep an agent working on the same product across separate sessions
  • turn a recurring support complaint into a fix the agent picks up
  • give a coding agent the context it keeps losing between tasks
  • use Claude, Codex and Grok from one desktop app instead of three

Tools(5)

let agents pass work between themselves instead of routing it yourself · route work across several agents · reach the same agent from Telegram or Slack instead of a web app · stop an agent from signing off on its own work

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

  1. 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
    • First check

    Last checked 3 days ago

    Open↗
  2. Multi-agent orchestration with skill routing and verified task results

    Why this one

    • route work across several agents
    • run agent tasks in parallel and check the result

    On the record

    • Free
    • No signup
    • First check

    Last checked 3 days ago

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

    Why this one

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

    On the record

    • Free tier
    • Needs an account
    • First check

    Last checked 3 days ago

    Open↗
  4. A supervised agentic build loop that cannot approve its own work

    Why this one

    • stop an agent from signing off on its own work
    • put a spec through implementation and review without babysitting it
    • get an independent check on a change before it lands

    On the record

    • Free
    • No signup
    • First check

    Last checked 3 days ago

    Open↗
  5. A common layer over Claude Code, Codex and the agents you write yourself

    Why this one

    • work on the same live agent session with someone else
    • put spend caps and policies around agents you already run
    • swap the harness underneath without rewriting your agents

    On the record

    • Free
    • Your own API key
    • First check

    Last checked 3 days ago

    Open↗