Replit Agent 3
Agent / Orchestration · In-browser autonomous app generation with built-in deploy, DB, and test agents
At a glance
| Setup effort | Zero |
| Released | 2025 |
| Open source | No |
| Interface | Web |
| Model choice | Fixed |
| Guardrails | Sandboxed |
| Cost | Paid (Replit Core) |
| Autonomy | Autonomous |
| Capabilities | Multi-step planning, Tool use, Long-running tasks, Auto-testing, Auto-deploy, Browser preview, Shell |
What Replit Agent 3 does
Multi-step planning, Tool use, Long-running tasks, Auto-testing, Auto-deploy, Browser preview, Shell
Best for
In-browser autonomous app generation with built-in deploy, DB, and test agents
Works well with
LLM Provider / Model
Integration
Context / RAG
Conflicts & caveats
- Replit Agent 3 uses its own model selection internally — your selected Claude Sonnet 4.6 will be ignored.
- ⚠️ Replit Agent 3 with on-demand context "Continue codebase indexing" may act on stale code — prefer real-time context (Cursor @codebase, Greptile, GitHub Copilot indexing, Augment Context, CocoIndex, turbopuffer).
Build a full stack around Replit Agent 3 — Flowpicker shows compatibility warnings before you commit.
Open the stack planner →