Starter
Free
Limited daily credits
Replit's AI coding agent, fully integrated into the Replit browser and mobile IDE. Agent 4 (March 2026) can vibe-code a production-ready startup from a single prompt — scaffolding the app, installing dependencies, wiring a database, deploying to a live URL, and iterating on feedback. Parallel agents (up to 10 on Pro), a Security Agent, and native iOS/Android apps make it the most complete browser-first AI development platform.
+Pros
- Agent 4 parallel execution lets multiple agents work simultaneously on different parts of a project (auth, database, frontend, backend), dramatically reducing build time.
- Infinite Canvas for visual design exploration with UI variant generation, hover/active state editing, responsive overrides, and multi-select — all changes apply directly to production code.
- Full-stack platform with built-in authentication, database, hosting, monitoring, and 100+ integrations (OpenAI, Stripe, Google Workspace, Databricks) — no separate tools needed.
- Multi-artifact support lets you build web apps, mobile apps, landing pages, slide decks, animated videos, and data visualizations all in the same project with shared context.
- Team collaboration via task-based kanban workflow — members submit requests in any order, Agent 4 intelligently sequences them, merges results, and handles dependency resolution.
- Enterprise-grade security with Security Agent (automated codebase review), Auto-Protect (automatic CVE patching), Security Center 2.0, Private Publishing, and SSO/SAML.
−Cons
- Credit-based pricing can be limiting for heavy users — Starter has limited free daily credits, Core ($20/mo) gives $25 monthly credits, Pro ($95/mo) gives $100 credits, which can deplete quickly on complex builds.
- Probabilistic output quality — Replit states the Agent 'may occasionally make mistakes' as it's powered by LLMs, meaning generated code can contain bugs, hallucinations, or security issues requiring manual review.
- Platform lock-in risk — while code can be exported, the tight integration with Replit's hosting, database, auth, and monitoring means migrating an app off the platform requires significant rework.
- Parallel agent execution (Agent 4's flagship feature) is primarily gated behind Pro and Enterprise plans — free and Core users get limited or no parallel agent access.
Pricing
Core
$25/mo
2 parallel agents, $20/mo annual
Pro
$100/mo
10 parallel agents, $95/mo annual
Enterprise
Custom
SSO, SAML, private publishing
Replit Agent is the AI coding agent built into the Replit cloud IDE — the platform that turned browser-based development into a mainstream choice for millions of developers worldwide. By early 2026, Replit had reached 50 million users and closed a $400M Series D at a $3B+ valuation, cementing its position as one of the most adopted AI development platforms on the market.
Agent 4, launched in March 2026, is the most capable iteration yet — designed for production-ready 'vibe coding' from a single prompt. Unlike previous versions, Agent 4 handles the full development lifecycle autonomously: scaffolding, dependency management, database provisioning, frontend and backend wiring, automated testing, error-fixing, and one-click deployment to a public URL. The March 2026 launch was accompanied by a demo of Agent 4 building a complete startup application from scratch in minutes.
The platform expanded beyond the browser in January 2026 with native iOS and Android apps, allowing developers to manage, prompt, and review agent work from mobile. Core and Pro plans support parallel agents (2 and 10 respectively), enabling multiple tasks to run simultaneously across projects. A Security Agent and Auto-Protect feature — launched in April 2026 — continuously scans for vulnerabilities and automatically patches common issues, positioning Replit as a platform for production-grade security, not just prototyping.
Key Features
• Agent 4: full-lifecycle autonomous coding agent from prompt to deployed app
• Parallel agents: 2 (Core) or 10 (Pro) simultaneous agents across projects
• Browser IDE: full Node.js/Python/Java/Go environment, no local setup required
• Native mobile: iOS and Android apps for managing and prompting agents on the go
• Security Agent & Auto-Protect: automated vulnerability scanning and patching
• App Monitoring: real-time performance and error tracking for deployed apps
• Connectors: integrations with external APIs, databases, and services via @ syntax
• Autonomy Level settings: control how much the agent acts vs. asks for confirmation
• Replit Animation: motion-style video generation from prompts
• One-click deploy: instant public URL with built-in hosting and database
• Google Cloud AI Tooling Partner of the Year 2026
• 50M+ users, $400M Series D, $3B+ valuation (March 2026)
Version History
Major release: parallel agent execution, infinite canvas design mode, multi-artifact projects (web, mobile, slides, video), task-based team collaboration with kanban workflow, app monitoring integration.
Native mobile app support — build and publish iOS/Android apps from natural language prompts directly on Replit without Xcode or Android Studio.
Introduced instant, precise agent control for quick targeted code changes without the full autonomous pipeline — free for a limited time for all users.
Native data warehouse connectors for Snowflake, Databricks, and BigQuery — allowing Agent to build data apps directly connected to enterprise data sources.
Launched visual design creation with Gemini 3 model — create interactive mockups and static sites in under two minutes from natural language prompts.
Signature Snippet
On Replit (web or mobile): prompt Agent 4 — 'Build a SaaS task manager with user auth, a Postgres database, REST API, and a React dashboard.' Agent 4 scaffolds the project, installs dependencies, creates the DB schema, writes the API and frontend, runs tests, fixes errors autonomously, and gives you a live URL — ready to share or continue iterating.More in this Space
Prime Agent (Prime Intellect)
Prime Agent is an open-source (MIT) self-improving coding and research harness by Prime Intellect, built on a Recursive Language Model that runs inside a persistent IPython REPL and a Continual Harness that refines its own state via /refine. It took the same frontier weights from 30.2% to 95.5% on ARC-AGI-3 RHAE Best@1, powered daemon-backed sessions, and ships no hosted offering.
OpenCodeReview (ocr)
OpenCodeReview (ocr) is Alibaba's open-source AI code-review CLI. It reads git diffs and drives an LLM agent through a hybrid architecture where deterministic pipelines handle file selection, rule matching, and comment positioning while the agent does the reasoning. Built on two years of internal use at Alibaba scale, it ships a multi-language ruleset and consumes roughly 1/9 of the tokens of general-purpose agents.
Delta (by Zed)
Multiplayer environment from Zed for coding with agents. Threads unify the agent conversation, the code edits, and human review in one shareable artifact, replacing the branch/PR loop. Built on DeltaDB, a CRDT-based version control layer that records every edit between commits alongside the prompts and reasoning that produced them.