Back to vendors
R

Replit Agent

Also known as: Repls

Visit site
Entry priceCore at $20 a month ($18 a month billed annually), Pro at $100 a month ($90 billed annually) and Enterprise at custom pricing. A free Starter plan appears in Replit's docs but not on the pricing page.Full pricing detail

AI app builder and runtime for the full stack, where an agent builds the app, sets up the database, tests its own work in a real browser and deploys it. Built for builders, students and startups.

Replit is a development platform that runs in the browser and bundles everything needed to build, run, and deploy software into a single tab, with no local installation or infrastructure to manage. The company's goal is to make programming as accessible as using a word processor. It pairs a full cloud IDE, supporting more than fifty languages, with its own database, authentication, hosting, and monitoring, so a project can go from a blank editor to a live URL without touching a terminal or configuring a server.

Its headline feature is the Replit Agent, now in its fourth generation. You describe an application in plain English, and the agent scaffolds the file structure, writes the code, installs dependencies, sets up the database schema, configures environment variables, and deploys the result to a live URL, all inside the browser. The Agent is a project builder that takes an idea all the way to a running app. It can work with most of the languages Replit supports and defaults to common web and backend stacks.

Agent 4 leans into autonomy and scale. Parallel agents can run tasks together with progress kept visible, and requests submitted in any order are sequenced and executed in a sensible order. A reflection loop built into the Agent has it test its own application in a browser, generate a report, and fix the issues it finds before handing it back. The Agent can also build other agents and workflows that you trigger from tools like Slack or email.

Because everything runs on Replit's cloud, deployment is a click away, with autoscaling, static, scheduled, and always on options. Projects connect to over a hundred integrations, including OpenAI, Stripe, and Google Workspace, and can import from Bolt, Lovable, GitHub, and Figma. For teams, Replit adds real time collaboration, SSO, SOC 2 Type II compliance, and admin controls. Engineers and people who do not write code both use it to go from an idea to a working, shareable prototype.

Vendor details

Canonical URL

https://replit.com

Category

Coding agent

Subcategory

Browser-based build, test and publish platform where the runtime, agent and hosting are one product

Company status

independent

Use cases & customers

Primary use cases

Going from a prompt to a tested, published application without leaving the browser, with the runtime, agent and hosting as one productScheduling recurring work through Routines that run Replit itself and return results into the same ConversationBuilding several features at once with parallel Agent tasks reviewed and applied back to a protected main versionBuilding applications backed by BigQuery, Databricks, Snowflake or Microsoft Fabric through warehouse connectorsStandardising how an organization builds with Enterprise custom templates, design systems, SSO, SCIM and audit logs with SIEM integration

Target customers

developersbuildersstartups

Deployment options

SaaScloud

Integrations

Connectors activate automatically from the customer's prompt, with no wiring in advance. Connector management across Core, Pro and Enterprise provides centralized admin controls, scoped access and audit tracking. Dedicated warehouse connectors cover BigQuery, Databricks, Snowflake and Microsoft Fabric so Agent builds applications backed by the customer's own data platform. Integrations reach HubSpot, Slack, Gmail, calendar, Linear, GitHub, Ashby, Notion, Google Drive, Shopify, Stripe, Clerk and RevenueCat. Model Context Protocol works in both directions. Agent connects outward to listed or custom MCP servers from a directory, and Replit publishes its own MCP Server that compatible MCP clients can connect to. Agent Skills package reusable instructions with supporting material. Import paths bring in projects, code and designs from other builders, GitHub, Figma and Claude. Publishing covers autoscale, scheduled, static and reserved always on deployments. Apps also reach the iOS and Android stores end to end through App Store Connect and Play Console.

In practice

You have an app idea but no local dev environment and no patience for setup. Replit's Agent scaffolds the code, sets up the database, and deploys it to a live URL in the browser, often in minutes.

You're an operations lead who needs an internal dashboard but engineering has no capacity. You describe it to Replit Agent in plain English and get a working, deployed tool without writing code or touching infrastructure.

Your generated app has bugs you'd rather not hunt down yourself. Replit's Agent tests the running app in a browser, generates a report, and fixes the issues it finds before handing the build back to you.

Agentic Index coverage score

13.5 / 14 capabilities · 96%

Integrations & Tool Calling Full

Connectors are integrations that Agent activates automatically based on the customer's prompts, and connector management across Core, Pro and Enterprise adds centralized admin controls, scoped access and audit tracking. Dedicated warehouse connectors cover BigQuery, Databricks, Snowflake and Microsoft Fabric. Use cases and build guides reach HubSpot, Slack, Gmail, calendar, Linear, GitHub, Ashby, Notion, Google Drive, Shopify, Stripe, Clerk and RevenueCat. External tools are also reachable through MCP servers listed in a directory, or custom MCP servers for anything unlisted.

Sourcedocs.replit.com chat/connectors, replitai/managing-connectors, connectors/warehouses, use-cases section, build/add-integrations and build/connect-via-mcp pagesread 2026-08-31

Workflow Orchestration Full

Agent breaks work into tasks that can be reviewed, run in the background and applied back to the main version, and several features can be built at once through parallel tasks, with guidance on delegating safely and slicing work small.

Plan and Build modes are separate phases, Conversations and Projects are separate surfaces and a Conversation can be turned into a Project, and Routines schedule recurring runs that return to a thread. Projects hold multiple artifacts, and teammates can each start their own Agent thread on a shared project. Agents and automations built on Replit run on its cloud with Slack, Telegram and scheduled triggers.

Sourcedocs.replit.com task-system, build-in-parallel, plan-vs-build-mode, conversations-and-projects, projects-and-artifacts, invite-teammates and chat/routines pagesread 2026-08-31

Knowledge Grounding & RAG Partial

Replit grounds Agent through per-request context and file uploads, Custom Instructions followed across Projects, Enterprise design systems held as a DESIGN.md, Agent Skills with supporting material, and project memory retrieved when relevant. Replit does not describe a searchable index it keeps over the customer's documents.

Design systems and Skills act as templates, Custom Instructions guide how Agent works, and the BigQuery, Databricks, Snowflake and Microsoft Fabric warehouse connectors supply data to the apps Agent builds. Grounding in the customer's own material comes from the context supplied with each request.

Sourcedocs.replit.com Memories page, 31 August read of chat/add-context, custom-instructions and connectors/warehouses, re-gradedread 2026-09-29

Human Oversight & Guardrails Full

Replit ships two gates in the run path. Agent proposes tasks with detailed plans that the user accepts or revises before they start, and each finished background task runs in an isolated copy and does not change the main version until the user reviews its work log, test results and live preview and chooses "Apply changes" or "Dismiss". Agent creates tasks automatically when it helps, and Replit does not say every edit in the main thread passes the same gate. Spend controls include usage limits, per user workspace spend limits and a budget for each Routine run.

Sourcedocs.replit.com Task system pageread 2026-09-29

Security, Identity & Governance Full

Replit states SOC 2 Type II compliance and publishes an information security overview of its security practices, data protection and compliance standards.

Controls include SAML single sign on configured from workspace settings with an in product wizard that provisions the connection from pasted identity provider values, SCIM provisioning with synced group mapping to workspaces and roles, roles across Admin, Member, Guest and Viewer with custom groups on Enterprise only, separate account and workspace admin roles, audit logs with SIEM integration, Enterprise privacy and source control settings across the organization, per user workspace spend limits, and connector management with centralized admin controls, scoped access and audit tracking. A security checklist covers securing generated applications separately.

Sourcedocs.replit.com teams/information-security, teams/saml, teams/scim, teams/groups-and-permissions, teams/account-and-workspace-admins, teams/audit-logs, teams/enterprise-privacy-settings and replitai/managing-connectors pagesread 2026-08-31

Observability & Auditability Full

Enterprise audit logs track and monitor security relevant actions across an organization, with SIEM integration. An Enterprise analytics dashboard reports activity, resource usage, published apps and costs. Connector management on Core, Pro and Enterprise provides centralized admin controls, scoped access and audit tracking. For each piece of work, the task system surfaces Agent's work as reviewable tasks that run in the background, Routines keep run history and status, and checkpoints record project state. Published apps are monitored separately after launch.

Sourcedocs.replit.com teams audit-logs, billing/teams-billing/analytics-dashboard, replitai/managing-connectors, task-system, chat/routines and build/publish-your-app pagesread 2026-08-31

Memory & State Persistence Full

Agent writes Memories while the user works and keeps them useful over time, with user memory scoped to one builder and workspace, project memory staying with one Project and retrieved when relevant, and custom memory following its own access and visibility settings. In Settings, Customization, Memory the user opts in, can turn Memory off, controls sharing with collaborators (off by default) and can view and update the Memory file, which is where memories are reviewed and cleared. Custom Instructions and Skills are kept separate from memory.

Sourcedocs.replit.com Memories pageread 2026-09-29

Deployment & Data Residency Full

Enterprise administrators choose a deployment geography for published apps: North America, South America, the EU, Asia or Australia. Bring Your Own Cloud entered private preview for Enterprise in October 2026, alongside private deployments. Publishing covers autoscale, scheduled, static and reserved deployments, plus iOS and Android store publishing.

Sourcedocs.replit.com/teams/privacy-and-deployment-settings and updates/2026/10/16; docs.replit.com/teams/privacy-and-deployment-settings.mdread 2026-10-25

Prebuilt Agents, Templates & Packs Full

Enterprise custom templates standardize how an organization builds with Agent, alongside Enterprise design systems that configure Agent with the organization's component library, brand assets, design tokens and visual standards.

A quickstart covers building and publishing from a template, and Replit Design lets builders remix a featured template into a project and offers a library panel with starter templates, inspiration curated by Mobbin and reuse of the customer's own creations. Agent Skills package specialized knowledge that can be attached, installed in a project, or used to start one. Replit's public gallery shows templates with view and use counts.

Sourcedocs.replit.com teams/custom-templates, teams/custom-design-system, build/build-and-publish-from-template, design/start-from-a-template, design/library-panel and build/use-agent-skills pages, replit.com galleryread 2026-08-31

Triggers & Channel Coverage Full

Routines schedule recurring work from within a Conversation, using connected tools, creating projects or tasks in connected services and sending messages, with results returned to the same Conversation.

Routines run at intervals of one hour or more, with five active Routines per user on Core and ten on Pro, run only in Power or Max mode, carry a budget for each run that is checked after each step, and wait when due rather than queueing twice. Routines cannot schedule publishing. A Routines sidebar lists schedules, active status and run history with run-now and delete actions. Channels include Conversations, the prompt box, Voice Mode, the mobile app and Slack context.

Sourcedocs.replit.com chat/routines, home/routines, chat/conversations, chat/voice-mode and home/understand-your-workspace pagesread 2026-08-31

Model Flexibility & Routing Full

Intelligent model routing lets Replit pick an appropriate model for each task, with manual selection available when the customer wants that control. A model selector lets the customer choose an available model and set its Effort, though manual selection depends on the customer's mode and plan. In Replit Design the model behind the design surface can be switched to explore different directions, since each model brings its own sensibility and frontend strengths. Agent Modes across Free, Power and Max govern capability and spend, and Routines run only in Power or Max.

Sourcedocs.replit.com chat/auto-mode, chat/model-selector, chat/agent-modes and design/explore-with-different-models pagesread 2026-08-31

APIs, SDKs & MCP Extensibility Full

The Replit MCP Server at https://mcp.replit.com/server/mcp runs over Streamable HTTP with OAuth through protected-resource discovery, and its tools, including create_app_from_prompt, search_apps, resolve_app_by_name, list_apps and ask_question, create, find, inspect, update and publish Replit Apps from any MCP client. Native connections from ChatGPT, Claude and Slack run on the same server. Outbound MCP connections to external servers are a separate path, letting Agent use other tools.

Sourcedocs.replit.com Replit MCP Server and Connect through MCP pagesread 2026-09-29

Testing, Debugging & Optimization Full

Agent tests the application it built in a real browser, generates a report and fixes the issues it finds before handing the work back. That testing is Replit's own, separate from any test suite the customer already has. Further checks sit in the release path, with mobile testing on a real device through Expo Go and through TestFlight and Play Console internal testing tracks, a task system that lets work be reviewed before it is applied to the main version, and checkpoints that record state for rollback.

Sourcedocs.replit.com learn/build-with-agent, task-system, build/mobile-preview-testing and learn/security-checklist pagesread 2026-08-31

Browser & Computer Use Full

App Testing has Agent test the apps it builds in a real browser, navigating and clicking through flows the way a user would and recording a video replay of the run. It covers Full Stack JavaScript and Streamlit apps in the higher effort modes. A Browserbase connector adds managed headless browsers for fetching and automating outside sites.

Sourcedocs.replit.com/features/agent/app-testingread 2026-10-25

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Product updates

·Agent capabilityPartially Verified

Replit Agent can now research and compare products, then prepare a merchant checkout through a browser subagent and complete the purchase with Link, Stripe's digital wallet. The user approves the merchant, total and any recurring terms in the Link flow; connecting the wallet alone does not authorize spending, and changed terms trigger a new approval. It is available to Core and Pro users in the US. The same update lets Replit Agent create Google Ads Performance Max campaigns from a user's app or site, and adds Performance Agent, which scans source code and deployment logs for latency and data layer problems.

Bears on: Browser/computer use

View source
·Agent capabilityVerified

Troubleshooting now happens inside the build conversation: when a user asks about contacting Support, Replit Agent checks for active incidents, consults the documentation and looks into known issues and platform limits. On the Pro plan, Agent can also file the support ticket itself, with debugging details from the user's environment attached.

Bears on: Agent capability

View source
·Agent capabilityVerified

Enterprise teams can now describe a change and have a Replit Cloud Agent find the relevant code, make the change and test it in the running app. The agent then opens a GitHub pull request or GitLab merge request with screenshots and video. Work runs in isolated cloud sandboxes built from a shared development environment the team sets up once, and follows the team's contribution guidelines.

Bears on: Agent capability

View source
View all 12 Replit Agent updates →Tracked since Jun 2026 · Verified from public vendor sources

Pricing

Core at $20 a month ($18 a month billed annually), Pro at $100 a month ($90 billed annually) and Enterprise at custom pricing. A free Starter plan appears in Replit's docs but not on the pricing page.

A plan subscription with monthly credits. Agent work, compute, deployments and storage draw from those credits, and usage is billed pay as you go once they run out.

Free tier

Included quota

Core includes $20 of monthly credits toward more powerful models, with Agent, compute, deployments and storage drawing from the credit pool, up to 5 collaborators, unlimited workspaces and autonomous long builds. Pro is $100 a month flat for up to 15 builders, with $100 toward the most powerful models, tiered credit options, one month rollover, private deployments and RBAC. Agent effort modes trade cost against capability.

What is public

Replit publishes its plan structure. A free Starter plan with limited Agent and one published app appears in the docs. Core is $20 a month ($18 billed annually) with $20 of monthly credits, Pro is $100 a month for up to 15 builders with tiered credits and one month rollover, and Enterprise is custom. Agent usage is effort based and billed from credits, then pay as you go.

Billing mechanics

Subscription plus usage. The plan fee includes a monthly credit allotment, and Agent work bills effort based checkpoints against those credits, then pay as you go past the allotment. Agent effort controls (Lite through Turbo) adjust the cost per request. Always on deployments, databases and storage draw from the same credit pool.

Cost watchouts

Effort based Agent pricing means complex requests bill variable checkpoint amounts. Every Agent interaction is billable, even text only answers, and failed or errored operations still charge. Once included credits are exhausted, billing continues pay as you go with no default spending cap, and spend limits and alerts are left for the customer to set. Core credits expire each cycle with no rollover, and Pro credits roll over one month. Third party model calls (Claude, GPT) bill at provider rates from the customer's credits.

Variable cost rationale

Agent work is metered by effort. Each request bills a variable checkpoint amount from the plan's monthly credits, scaled by the effort mode, and every Agent interaction counts, including text only answers and failed operations. Always on deployments, databases and storage draw from the same credits, so hosting adds cost even when nobody is building. Once the credits run out, billing continues pay as you go. There is no default spending cap, so the limits are the spend controls the customer sets and the effort mode, which trades cost against capability from Lite through Turbo. Core credits expire each cycle, and Pro credits roll over for one month.

Additional watchouts

Always on deployments keep consuming credits while the app is inactive, and Agent work bills by effort, so the subscription is only the entry price. Total cost follows Agent use plus hosting.

Sales call required

No, self serve available

Free / trial

Free Starter plan with limited daily Agent credits and one published app that goes down after 30 days, named in the docs but not on the pricing page. No trial.

Lowest paid plan

Core at $20 per month, or $18 per month billed annually, with $20 of credits toward the most powerful models

Commercial notes

A full stack build and run platform. Agent handles scaffolding, database setup, testing and deployment, and the platform hosts the result. Replit is also available directly inside Claude, to design in Claude and build in Replit.

Key ambiguities

Effort based checkpoint costs vary and are not published per operation, so the cost of building an app is hard to predict, and Enterprise pricing is not published. Agent work is billed by effort rather than fixed checkpoints, and Pro replaced the Teams plan.

Support SLA / resale

Pro includes Premium Support.

Missing data

Per checkpoint effort rates, Pro credit tier ladder details, and Enterprise pricing are unpublished.

Agentic Index verified 2026-10-25

Alternatives to Replit Agent

The closest documented capability profiles to Replit Agent among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • OpenHands13.5 / 14Matches Replit Agent across all 14 documented capabilities
  • Base4413.0 / 14A lighter documented profile than Replit AgentReplit Agent vs Base44 →
  • OpenAI Codex13.0 / 14A lighter documented profile than Replit Agent
  • Qoder14.0 / 14Fuller documented coverage on Knowledge Grounding & RAG
  • Qwen Code13.0 / 14A lighter documented profile than Replit Agent
  • Anthropic Claude Code12.5 / 14A lighter documented profile than Replit Agent

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.