Categories › AI & Agents › Multi-agent, orchestration & workflows
Low on memory? Your bot sends heavy jobs to cloud sandboxes on your own provider keys. Flat fee.
Remote server: your requests and data go to compute.cloudforbots.com. Claude Code: claude mcp add --transport http compute-connector https://compute.cloudforbots.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
check_memory — Before a heavy job, send how much memory the machine your agent runs on has free (free -m, os.freemem()) and what you are about to run. Get run_job — Pro: run a shell command in a fresh cloud sandbox on your own provider account (vercel (Vercel Sandbox, default), e2b, daytona, modal, workesave_provider_key — Pro, owner only: save one provider key, sealed with AES-256-GCM before it reaches the database. Providers: vercel (Vercel Sandbox, default),list_providers — Every provider this connects to, how each one runs, and (with your key) the provider keys you saved: name, provider, fingerprint, default, ldelete_provider_key — Pro, owner only: delete a saved provider key by name. Jobs on that key stop working at once.provider_setup — Step-by-step setup for one provider: where to get the key, what to pass to save_provider_key, links to its docs and price page, and for Modaweekly_report — Plain-English summary of the last 7 days: memory checks, low-memory warnings, jobs that would have been offloaded (free) or ran (Pro) by prousage_and_upgrade — Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.