hosted-agentslisted

# Hosted Agent Infrastructure Hosted agents run in remote sandboxed environments rather than on local machines. When designed well, they provide unlimited concurrency, consistent execution environments, and multiplayer collaboration. The critical insight is that session speed should be limited only by model provider time-to-first-token, with all infrastructure setup completed before the user starts their session. ## When to Use - Building background coding agents that run independently of user devices - Designing sandboxed execution environments for agent workloads - Implementing multiplayer agent sessions with shared state - Creating multi-client agent interfaces (Slack, Web, Chrome extensions) - Scaling agent infrastructure beyond local machine constraints - Building systems where agents spawn sub-agents for parallel work ## When NOT to Use - Coordinating multiple agents with handoffs or supervisor patterns (use multi-agent-patterns) - Persisting agent state or memory across sessions (use memory-systems) - Designing individual tools or tool interfaces for agents (use tool-design) - Running agents locally on a user's machine (not a hosting problem) ## Decision Tree ``` What are you building? │ ├─ Agent runs remotely in sandboxed environment │ ├─ Need pre-built environment images? → Image Registry Pattern │ ├─ Need instant session start? → Warm Pool + Predictive Warm-Up │ └─ Need multiple users in same session? → Multiplayer Support │ ├─ Agent needs to spawn sub-age