{"slug":"replit-agent","name":"Replit Agent","vendor":"Replit","tagline":"Replit's cloud agent that plans, builds, tests and deploys apps from natural-language prompts","url":"https://agentboards.org/agent/replit-agent","website":"https://replit.com/ai","docs":"https://docs.replit.com/replitai/agent","repo":null,"category":"web-app","execution":["cloud"],"license":"proprietary","open_source":false,"pricing":{"model":"mixed","summary":"Free Starter tier; Core $20/mo and Pro $100/mo include monthly credits, Agent work beyond the free allowance is billed per checkpoint with effort-based pricing","from_usd":20,"free_tier":true,"byok":false},"models":{"backbone":["Claude","GPT","Gemini"],"bring_your_own_model":true,"local_models":false},"protocols":{"mcp_client":true,"mcp_server":true},"capabilities":{"terminal_exec":true,"browser":true,"multi_file_edit":true,"git_ops":true,"docker_sandbox":true,"multi_agent":true,"headless_ci":false},"context_window":null,"platforms":["web"],"install":[],"benchmarks":[],"tags":["web-app","cloud-ide","vibe-coding","mcp","browser-testing"],"github_stars":null,"metrics":{"stars":null,"pushed_at":null,"archived":null,"open_issues":null,"latest_version":null,"latest_version_at":null,"latest_version_url":null,"version_source":null,"checked_at":"2026-09-08T05:06:15.401Z"},"sources":{"pricing":"https://replit.com/pricing","models":"https://docs.replit.com/chat/model-selector","protocols":"https://docs.replit.com/platforms/mcp-server","capabilities":"https://docs.replit.com/features/agent/app-testing"},"verified_at":"2026-09-02","adoption":{"score":null,"signals":{"hn_mentions_1y":5},"measured_at":"2026-09-21"},"scores":{"panel":5.6,"adoption":null,"spread":4,"facts":6.7,"board":5.8,"dimensions":{"reliability":5.3,"usefulness":6,"cost":4.7,"longevity":6.5},"per_persona":{"amigo":6.3,"critico":5.5,"profesor":5.8,"inversora":7.5,"jefa":5.3,"hacker":3.5},"community":null},"rank":132,"category_rank":7,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"Four points between La Inversora's moat and El Hacker's closed box, and they are describing the same hosting arrangement from opposite ends.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Use Replit Agent to go from idea to hosted app in an afternoon, not as your team's main coding agent, because the checkpoint meter and vendor-chosen model are not built for that.","scores":{"reliability":6,"usefulness":7,"cost":5,"longevity":7},"evidence":["https://docs.replit.com/billing/ai-billing","https://replit.com/pricing"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"Replit bills Agent work per checkpoint at an effort-based price the pricing page does not state, and plan mode charges even when it produces no code.","scores":{"reliability":5,"usefulness":6,"cost":4,"longevity":7},"evidence":["https://docs.replit.com/billing/ai-billing","https://docs.replit.com/features/agent/app-testing"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"Replit Agent's browser-based self-testing is a genuine verification loop; its models, its context strategy and its cost per edit are undocumented, and no benchmark is offered.","scores":{"reliability":6,"usefulness":6,"cost":5,"longevity":6},"evidence":["https://docs.replit.com/features/agent/app-testing","https://docs.replit.com/billing/ai-billing"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"Replit has consumer distribution and a hosting business that turns every generated app into a switching cost, and its shift to effort-based pricing is the tell that margins are being managed.","scores":{"reliability":7,"usefulness":8,"cost":7,"longevity":8},"evidence":["https://replit.com/pricing","https://docs.replit.com/billing/ai-billing"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"Enterprise has SSO and single-tenant environments, but an unpublished effort-based meter and code that lives in Replit's cloud limit this to prototyping teams; approved with conditions.","scores":{"reliability":5,"usefulness":5,"cost":4,"longevity":7},"evidence":["https://replit.com/pricing","https://docs.replit.com/billing/ai-billing"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"A closed cloud workspace with a model I cannot choose and a meter I cannot read; the Git export and the MCP client are the only doors, and they open outward.","scores":{"reliability":3,"usefulness":4,"cost":3,"longevity":4},"evidence":["https://docs.replit.com/learn/model-context-protocol","https://docs.replit.com/billing/ai-billing"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"Bills per checkpoint with effort-based pricing, so the harder the bug, the more you pay to watch it try.","scores":null,"evidence":[]}]}