Minded
Also known as: Minded Recorder, minded.com
An AI coworker that works from Slack, Teams, Gmail and Chrome, learns a task from one walkthrough, runs it with browser automation and integrations, and waits for approval before any action other than a read. It is built on Minded's agent development platform with flows, knowledge bases and on premises deployment.
Minded sells an AI agent that finds and completes work across finance, sales, marketing, HR, operations and support. It lives in Slack, Teams, Gmail and Chrome, connects to business systems by OAuth with per tool scopes, and learns new tasks when a person walks through them once in the browser, saving each as a skill it can run again, on demand, on a schedule or on its own. Reads run freely inside granted scopes. Every other action waits for approval, with the exact change shown, and every run, tool call and approval is logged.
Underneath is Minded's agent development platform: a visual flow editor with GitHub sync, the MindedJS TypeScript SDK, webhook and cron triggers, Playwright based RPA tools for web apps without APIs, knowledge bases queried through a RAG API, PII masking, SAML single sign on and on premises deployment of the Operator in the customer's cloud. Minded holds SOC 2 Type II. It prices by finished work in credits, from a $9.99 Starter to Pro and Business plans.
Vendor details
Canonical URL
https://www.minded.com
Category
Agent builder
Funding status
Not stated on the pages read
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Minded connects by OAuth with per tool scopes to QuickBooks, Salesforce, Stripe, Google Drive, Slack, Zendesk and other systems. The agent works from Slack, Teams, Gmail and a Chrome extension. Developers extend it with custom tools, Playwright RPA tools, the MindedJS SDK and the Agent, Analytics and Knowledge APIs.
In practice
A finance team shows Minded how to reconcile invoices by walking through the task once in the browser, and the agent then repeats it in QuickBooks on a cron schedule, asking for approval before it changes any record.
A support lead connects Zendesk and Slack, and when a webhook fires on a new refund request the agent prepares the refund, shows the exact change in Slack, and waits for the lead to allow it once, for the task or always.
A company with strict data rules deploys the Operator in its own VPC, so customer PII and compute stay in its cloud while Minded's control plane handles orchestration and monitoring, and the security team exports the activity log for its own audits.
Sources & related URLs
Agentic Index coverage score
12.0 / 14 capabilities · 86%
| Integrations & Tool Calling | Full |
|---|---|
|
Every plan includes Minded's integrations, connected by OAuth with per tool scopes the tool owner picks, and the agent reads and writes in systems such as QuickBooks, Salesforce, Stripe, Google Drive, Slack and Zendesk; developers add custom tools to flows. Sourceminded.com/securityread 2026-09-27 |
|
| Workflow Orchestration | Full |
|
Flows orchestrate nodes, edges, tools and memory in a visual editor with two way GitHub sync, playbooks guide agent behavior, and the SDK runs parallel LLM requests; the agent plans a task once and runs each step across the tools it needs. Sourcedocs.minded.com/low-code-editor/flowsread 2026-09-27 |
|
| Knowledge Grounding & RAG | Full |
|
Knowledge bases hold the customer's uploaded documents with metadata, kept per environment (development, staging, production) and queried at run time through a Knowledge Base RAG API and a Knowledge API, so new knowledge is added by upload. Sourcedocs.minded.com/platform/knowledge-basesread 2026-09-27 |
|
| Human Oversight & Guardrails | Full |
|
Reads run inside the scopes granted, and every other action stops and waits for approval. The request names the tool, account and exact change, the user allows it once, for the task or always, and flagged output goes to a reviewer whose verdict is recorded on the run. Sourceminded.com/securityread 2026-09-27 |
|
| Security, Identity & Governance | Full |
|
Tool owners grant per tool scopes that never widen on their own, SAML single sign on is an enterprise feature, Business plans add shared workspaces and team roles, and data is isolated per workspace with least privilege service accounts. Minded says it holds SOC 2 Type II and publishes no trust portal. Sourceminded.com/securityread 2026-09-27 |
|
| Observability & Auditability | Full |
|
Every run, tool call and approval is logged in plain language, each session opens into its full trace down to the approval that let it through, the activity log exports, and the SDK adds logging, events, debugging and an Analytics API. Sourceminded.com/securityread 2026-09-27 |
|
| Memory & State Persistence | Partial |
|
Memory is a schema validated data store that persists throughout an agent session and is shared by every node in a flow, and Minded does not describe memory kept across sessions. Sourcedocs.minded.com/sdk/memoryread 2026-09-27 |
|
| Deployment & Data Residency | Full |
|
The Operator can be deployed on premises in the customer's own cloud, so the agentic plane (compute and data such as PII) runs in the customer's VPC while Minded's control plane handles orchestration and monitoring. Sourcedocs.minded.com/platform/on-premread 2026-09-27 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
Customers build skills themselves, by walking through a task once or in the editor, with an example order refund flow to start from. Pages for finance, sales, marketing, HR, operations and support describe use cases, but Minded offers no catalog of prebuilt agents or skills. Sourcedocs.minded.com/examples/order-refund-flowread 2026-09-27 |
|
| Triggers & Channel Coverage | Full |
|
Agent flows start from webhook triggers or cron schedule triggers with a timezone, Pro plans run scheduled and recurring tasks, and the agent works from Slack, Teams, Gmail and Chrome. Sourcedocs.minded.com/low-code-editor/triggersread 2026-09-27 |
|
| Model Flexibility & Routing | Partial |
|
An agent's project configuration sets its model, from OpenAI through ChatOpenAI or the customer's own Azure OpenAI deployment through AzureChatOpenAI, one model family on two routes. The hosted product says it runs each step on the smallest model that does the job, without naming the provider. Sourcedocs.minded.com/getting-started/project-configurationread 2026-09-27 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
The MindedJS TypeScript SDK has a published API reference on Minded's GitHub, and Minded also offers an Agent API plus REST Analytics and Knowledge APIs for the platform's own agents and knowledge bases. Sourcedocs.minded.com/api/overviewread 2026-09-27 |
|
| Testing, Debugging & Optimization | Partial |
|
Minded lays out a method for collecting end to end eval cases and rerunning the agent until they pass, with an expert sign off before going live, plus SDK debugging tools. Teams run this practice by hand, and the product has no evaluation harness, scored test runs or release gate. Sourcedocs.minded.com/resources/your-first-evalread 2026-09-27 |
|
| Browser & Computer Use | Full |
|
RPA tools drive a browser with Playwright to click, fill and submit forms and navigate web apps that have no API, with automatic screenshots, action logging and browser session management, and the browser extension records a task the user walks through once so Minded can repeat it as a skill. Sourcedocs.minded.com/low-code-editor/rpa-toolsread 2026-09-27 |
|
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
Pricing
Starter is $9.99 to start, with 5,000 credits. Pro runs from $20 a month for 2,000 credits, with $50 for 5,000 as the headline tier, and Business from $1,500 a month.
A monthly credit subscription, with credits spent per finished task.
What is public
Minded publishes Starter, every Pro and Business credit step and price, credits per task by complexity, and plan features.
Variable cost rationale
Finished work is metered in credits at $0.01 each, and a task costs about 10 to 3,500 credits by complexity, so spend grows with the number and difficulty of tasks. The monthly credit step sets the bill. Pro runs from 2,000 to 200,000 credits a month and Business from 150,000, extra credits are topped up by choice, and unused credits roll over while subscribed.
Overage / add-ons
Credits top up anytime and roll over while subscribed.
Sales call required
No, self serve available
Free / trial
No free plan or trial
Lowest paid plan
Starter at $9.99 to start, with 5,000 credits
Cancellation / refund
Pro and Business bill monthly and cancel anytime.
Support SLA / resale
Business includes priority support.
Related vendors
- Lindy — Lindy is an AI teammate that lives in Slack, answers from your tools…
- Activepieces — Open source, MIT licensed automation platform where every one of 700…
- Agenta — Agenta is an open source workspace where teams build AI agents by…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code platform for building and running AI agents, with a…
- Aigensei — Enterprise agentic workflow platform that runs business processes…
Alternatives to Minded
The closest documented capability profiles to Minded among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Newgen12.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Flowable13.0 / 14Fuller documented coverage on Model Flexibility & Routing and Testing, Debugging & Optimization
- GPTBots13.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs and Model Flexibility & Routing
- Superblocks11.0 / 14A lighter documented profile than Minded
- Activepieces11.5 / 14Fuller documented coverage on Model Flexibility & Routing
- Bizagi11.5 / 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