Back to vendors
R

Retool

Also known as: Retool Agents, Retool Workflows, Retool AI

Visit site
Entry priceTeam is $10 per builder and $5 per internal user a month, and Business is $50 and $15. A free tier covers up to 5 users, and Enterprise is custom. Agent hours beyond the included 20 a month are billed hourly by model.Full pricing detail

Internal tools platform extended into agent orchestration: agents pick their own tools, delegate to sub agents, link MCP servers, and inherit platform RBAC, with self hosting and built in evals.

Retool is an internal tools platform that has extended its low code builder and workflow engine into a full agent orchestration system. Retool Agents are configured with instructions, given tools, and left to decide which tools to call, in what order, and when the task is complete. They can delegate to sub agents and escalate. Retool separates AI workflows, which run LLMs inside a predefined process, from agents, which are given a goal and choose their own path.

Agents inherit the same governance the rest of the platform enforces, so agent specific tools are bound by existing role based access control and data level permissions rather than sitting outside them, and a person can be required to approve a tool call before it runs. Customers can choose among multiple hosted models with routing. Enterprise customers can bring their own LLM key, and a custom AI provider integration accepts any OpenAI compatible endpoint, including self hosted or private model deployments. Evaluations for tuning agent performance come built in, and Retool Vectors gives agents a managed vector store over the customer's documents and web pages.

Retool runs as multi tenant cloud on AWS, as a self hosted Docker image inside a customer virtual private cloud, or as a Retool managed self hosted instance running in a customer owned AWS account. When Retool is self hosted, no Retool systems store customer data and no Retool personnel have logical access to it. Only usage information and orchestration metadata go back to Retool.

Retool does not describe memory kept across runs. It names one agent template, the Competition Scanner, and the rest appear only inside the product. Tools that need approval cannot be called over A2A. Single sign on and several governance features sit on higher tiers, and agents are billed by the hour separately from the AI credit pool, so agent cost grows with runtime rather than with seats.

Vendor details

Canonical URL

https://retool.com

Category

Agent builder

Subcategory

Agent orchestration on an internal tools platform

Funding status

Private and well capitalized. Named production customers reported at Fortune 500 scale including Amazon, Brex and Coinbase. Funding rounds are not stated on Retool's own pages.

Company status

independent

Use cases & customers

Primary use cases

autonomous internal operations agentscustomer support ticket triage with sub agent delegationmulti step workflow automation over internal systemsinternal tool and admin panel buildingcustomer facing portals

Target customers

enterprisemid-marketdevelopersoperations teamsproduct managers

Deployment options

Retool Cloud on AWSself-hosted Docker in customer VPCRetool-managed self-hosted in customer-owned AWS VPCon-premise

Integrations

Over 100 native connectors spanning Postgres, MySQL, MongoDB, Snowflake, Salesforce, Stripe and REST or GraphQL endpoints. Agents can be given any saved query or workflow as a tool, plus purpose built agent tools governed by the same platform permissions. Agents can link MCP servers or delegate to other agents. Extensible with JavaScript, Python and SQL, and a Secrets Manager with programmatic rotation via API.

In practice

A support team builds an agent that triages inbound tickets, delegates specialized questions to sub agents, and escalates only the cases it cannot close, with every step watchable in real time.

An operations team turns existing saved queries and APIs into governed agent tools so an agent can process chargeback disputes end to end without new integration work.

A regulated enterprise runs the whole platform self hosted inside its own AWS account so that no customer data reaches Retool systems while still using hosted or private models of its choice.

Agentic Index coverage score

12.0 / 14 capabilities · 86%

Integrations & Tool Calling Full

Agents act through core tools built by Retool (email, calendar, Google Docs and Slides, files, web search), custom tools, any saved query or workflow, other agents and connected MCP servers, over Retool's 100+ connectors. There are 38 core tools in all, covering calendar events and open time slots, files and folders, vector search, reading a web page and running JavaScript or Python. An agent can connect up to 20 remote MCP servers and import tools from other agents.

Custom tools cost nothing to create and have no run limits, and any tool's output is capped at 1 MB. Retool's app building agent can also call tools on outside MCP servers connected as resources, while an app is built and when it runs, and people using the app can trigger only the MCP tools they have permission for; this is in public beta on cloud for all plans.

SourceRetool, docs.retool.com Agents Tools and changelog MCP in app builderread 2026-10-05

Workflow Orchestration Full

Agents choose which tools to call and in what order, invoke other agents as tools and talk to external agents over A2A, and agentic workflows combine Retool Workflows with agent steps. Each agent pairs a model and its tools with an orchestration layer that handles state, reasoning and planning.

It works in a ReAct loop, alternating between thinking and acting, with no fixed stopping point. A workflow calls an agent through an Invoke Agent block, and an agent used as a tool can run for up to eight hours. One business process can mix code that makes fixed decisions, model calls that make open ones, and people who weigh in.

SourceRetool, docs.retool.com Agents overview, Agentic workflows and Toolsread 2026-10-05

Knowledge Grounding & RAG Full

Retool Vectors is a managed vector database for Retool AI. Retool extracts text from documents, splits it into chunks and computes embeddings with OpenAI's embeddings API, and it crawls URLs into new embeddings within published limits of three concurrent crawls, 25 URLs and a 15 second timeout. When an AI action references a Vector, the most relevant content goes into the model request. Agents have core tools that list Vectors, run a semantic search, fetch the chunks of a document or URL, and list the documents and URLs stored.

SourceRetool, docs.retool.com Retool Vectors quickstart and Agents Toolsread 2026-10-05

Human Oversight & Guardrails Full

Agent tools run under Retool's role based access control and data level permissions, and anyone can watch an agent step by step as it works. Tools that need approval cannot be used over A2A, which does not support that waiting state. Retool lists consent before tool execution among its agent controls, and its launch post says approval of actions before they run "can be configured for every tool call."

In Retool's examples, an agent waits for a person's go ahead before it creates tickets or sends calendar invitations. The tool settings cover timeouts and typed parameters, and Retool does not show where the approval is switched on. Agents act on behalf of users, so they never use a tool or data source without permission.

SourceRetool, docs.retool.com Agent to agent and Agents overview, and retool.com blog on agent developmentread 2026-10-05

Security, Identity & Governance Full

Retool offers role based access control through administrator permissions, enforced two factor authentication and detailed admin audit logs on Business and Enterprise, and holds SOC 2 Type 2, with audit reports available through the Trust Center at trust.retool.com. Admins can sign out any user remotely, and every sign in is logged with its device type and IP address. Data is encrypted in transit and at rest, a vulnerability disclosure program takes reports from researchers, and outside security firms audit the platform regularly. The pricing page puts SSO and SCIM on Enterprise.

SourceRetool, docs.retool.com security practices and retool.com/pricingread 2026-10-05

Observability & Auditability Full

Each agent run shows token usage, estimated cost, total runtime and tool calls above a replay of the run with tool chips for each step, and any running agent can be watched step by step; admin audit logs sit on Business and Enterprise. Each run also lists its run ID, status, timestamp and duration.

Dashboards cover all agents or a single one, filter by time from the past 15 minutes to the past month, and stream events live. An agent graph shows in real time which resources an agent is touching. Thought logs show an agent's reasoning, with token, latency and cost figures for each run and in total.

SourceRetool, docs.retool.com Monitor agents and retool.com blog on agent developmentread 2026-10-05

Memory & State Persistence Partial

An agent keeps the context of its chat and its run as it calls tools, within one session. The orchestration layer manages memory and state during a run. Retool does not describe memory kept from one run to the next.

SourceRetool, docs.retool.com Agents overview and FAQread 2026-10-05

Deployment & Data Residency Full

Retool runs as multitenant cloud on AWS or as 'Self-hosted services in your VPC/VPN', and Agents run on both cloud and self hosted instances, including email triggers through Mailgun on self hosted. Self hosting comes with the Enterprise plan. When self hosted, no Retool system stores customer data and no Retool staff can reach it, and only usage information and orchestration metadata go back to Retool. The cloud service is built to keep running through the loss of a server or a whole data center, and self hosted instances can switch A2A off with a feature flag.

SourceRetool, docs.retool.com security practices and Agent to agent, and retool.com/pricingread 2026-10-05

Prebuilt Agents, Templates & Packs Partial

Retool Agents 'offers several pre-defined templates' for specific use cases, but Retool names only one publicly, the Competition Scanner; the rest appear only inside the product. Competition Scanner comes loaded with mock competitor data from Retool Database and needs custom tools. The core tools are building blocks for agents, not agents in their own right.

SourceRetool, docs.retool.com Create from template and Agents Toolsread 2026-10-05

Triggers & Channel Coverage Full

Agents start on their own when an email arrives at their unique agent address or when an outside agent calls them over the A2A trigger. People can also start them from the built in chat, from an Agent Chat component inside an app, or from an Invoke Agent block in a workflow. Chat threads can be shared with teammates.

SourceRetool, docs.retool.com Agents overview and Triggersread 2026-10-05

Model Flexibility & Routing Full

Builders 'choose your favorite LLM' and 'Choose from multiple AI models to balance performance and cost', on Retool managed keys for certain providers or their own key with a model provider. With Retool managed keys, the provider handles data under its agreement with Retool. With the customer's own key, the customer's agreement with that provider applies. Agent hours are priced by model, with more capable models costing more, and paid plans include up to 20 free agent hours a month.

SourceRetool, docs.retool.com Agents FAQ and retool.com/pricingread 2026-10-05

APIs, SDKs & MCP Extensibility Full

Agents built in Retool are callable from outside over A2A, with an A2A trigger and an A2A endpoints reference, and the platform extends through custom tools, JavaScript, Python and SQL. Each agent has its own API key, sent in an X-Api-Key header and rotated as needed, and the endpoints accept HTTP with REST or JSON-RPC. Outside agents can send a message, poll for task updates, stream them over Server Sent Events or cancel a task. In the other direction, custom tools and resource queries can call outside agents over REST.

SourceRetool, docs.retool.com Agent to agent and A2A endpoints referenceread 2026-10-05

Testing, Debugging & Optimization Full

Evals test agents systematically: builders create datasets and test cases, run evals and compare runs side by side, and 'fine-tune with built-in evals'. Each test case holds an input and the expected output. Tool choice cases check that the agent picks the right tool with the right parameters, and final answer cases grade the reply. Programmatic reviewers check exact matches, valid JSON or XML, schema matches, contained strings or Levenshtein distance, and LLM judges score tone, factuality or closed questions, each on a scale from 0 to 1. Two runs can be compared at a time.

SourceRetool, docs.retool.com Agents Evalsread 2026-10-05

Browser & Computer Use Not documented

Agents act through core tools, custom tools, queries, workflows, other agents and MCP servers; the web search core tool is a search, and Retool offers no browser, desktop or computer control. A second web tool reads a page's content, and the code tool runs JavaScript or Python, but none of the tools clicks through a site or works a screen.

SourceRetool, docs.retool.com Agents Toolsread 2026-10-05

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

·Security / enterpriseVerified

Enterprise admins can now add private npm registries to Retool, and builders can then ask the app builder agent to install packages from them, such as a design system hosted on the company's own servers. A registry can be the default for all packages or take whole npm scopes, and can sit behind a bearer token or basic auth. Teams that run their own registry can also set rules on what it allows, for example a minimum package age.

Bears on: Human approval / guardrails

View source
·MCP / tool calling / APIPartially Verified

Retool 4.74 adds tools to the Retool MCP server for disabling and enabling users and for adding and removing permission group members, alongside a tool to list user spaces and space filtering on the audit log tool.

Bears on: Security / enterprise

View source
·MCP / tool calling / APIVerified

Retool's app building agent can now use external MCP servers connected as resources, calling their tools while an app is being built or when it runs. People using a published app can only trigger the MCP tools they have permission for. It is live on cloud for all plans as a public beta.

Bears on: MCP / tool calling / API

View source
View all 3 Retool updates →Tracked since Sep 2026 · Verified from public vendor sources

Pricing

Team is $10 per builder and $5 per internal user a month, and Business is $50 and $15. A free tier covers up to 5 users, and Enterprise is custom. Agent hours beyond the included 20 a month are billed hourly by model.

Three user classes (builders, internal users and external users), each billed per user a month, plus agent hours and AI credits.

Free tierTrial available

Included quota

Free includes up to 5 users, unlimited apps, 500 workflow runs, 250 AI credits and up to 20 agent hours a month. Team includes 5,000 workflow runs and 1,000 AI credits a month, Business 5,000 runs and 3,000 credits, and Enterprise 10,000 credits with custom runs and agent hours. Every plan below Enterprise includes up to 20 agent hours a month.

What is public

Retool publishes every plan's seat prices for builders and internal users, the external user tiers, the workflow run and AI credit allowances, the workflow overage block and the 20 included agent hours. The hourly agent rate by model is not published.

Billing mechanics

Users are classified for billing each cycle by activity. Builders create or edit apps, workflows and agents and carry the highest rate. Internal users only view and use published apps and are billed at a reduced rate, and Business plan admins can use permission groups to hold users at that lower rate. External users are volume tiered and only available on Business and Enterprise. Agents bill hourly and separately from the AI credit pool. Team and self serve Business pay by credit card. ACH and wire are available only to contracted Business and Enterprise customers.

Cost watchouts

Agent hours are the largest exposure. Free agent hours are capped at roughly 20 per month and agent execution pauses once they are exhausted, so an agent workload can stop rather than degrade. Paid agent rates vary by model capability, so switching an agent to a stronger model changes the run rate. Workflow run overages are billed in blocks on Team and Business. Single sign on and several governance features sit behind higher tiers, which can force a jump to custom Enterprise pricing the moment a security review requires SSO. Self hosting shifts cost into infrastructure, upgrades and maintenance time.

Variable cost rationale

Three meters sit on top of the seats. Agent runtime is billed by the hour beyond the included 20 hours a month, at rates that vary by model. AI prompting draws on a monthly credit allowance (250 on Free, 1,000 on Team, 3,000 on Business and 10,000 on Enterprise), and workflow runs beyond the plan allowance are billed in blocks of 5,000 at $75 a month. Agent hours grow with how long autonomous work takes, not with headcount, and moving an agent to a stronger model raises its hourly rate. On the free tier, agent execution pauses when the hours run out, so nothing more is billed. No cap on paid agent hours is published, and agent time is billed separately from the AI credit pool. Seats are flat per user, and Business admins can use permission groups to keep users at the lower internal user rate.

Additional watchouts

Seat count does not predict Retool agent cost. Agent spend is a function of how long agents run and which model they run on, and it is ring fenced from the AI credit pool.

Overage / add-ons

Workflow runs beyond the included allowance are billed in blocks on Team and Business, at $75 per 5,000 runs a month. Agent hours beyond the included allowance are billed hourly at model dependent rates. On the free tier, agent execution pauses instead of billing.

Sales call required

Mixed (some tiers require a call)

Free / trial

Free plan for up to 5 users with 500 workflow runs, 250 AI credits and 20 agent hours a month, and a free trial of Team and Business

Lowest paid plan

Team at $10 per builder and $5 per internal user a month ($8 and $4 billed annually)

Commercial notes

Annual billing is about 20 percent below monthly, at $8 per builder and $4 per internal user a month on Team and $40 and $12 on Business.

Key ambiguities

The hourly agent rate varies by model and is not published, so agent cost at volume depends on model choice and runtime. Seat prices are geo priced and show in EUR in some regions, so the USD figures may differ by region.

Cancellation / refund

Team and Business bill monthly or annually, with annual billing about 20 percent cheaper. Enterprise is a custom contract.

Support SLA / resale

Enterprise includes full technical support.

Missing data

An hourly agent rate card by model, and USD seat rates for every region.

Agentic Index verified 2026-09-30

Alternatives to Retool

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

  • Activepieces11.5 / 14A lighter documented profile than Retool
  • Budibase11.5 / 14A lighter documented profile than Retool
  • Mendix12.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
  • OutSystems12.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
  • AgentX12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
  • Airia12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs

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

Head to head

Contact us

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