Taskade
Also known as: Taskade Genesis, Taskade Workspace DNA
AI-native workspace and no-code builder with autonomous Plan & Execute agents and multi-agent teams.
Taskade is an AI-native unified workspace that combines real-time collaboration, AI agents, workflow automation, and no-code app generation in a single tool, positioning itself as an operating system for team productivity. It began in 2017 as a collaborative document and project editor and has progressively layered AI on top without removing the underlying productivity features.
The platform is organized around what Taskade calls Workspace DNA, a self-reinforcing loop of four primitives: Projects (memory and data), Agents (intelligence), Automations (execution), and the app interface. Memory feeds the agents, the agents trigger automations, and automations write new state back into memory, so a workspace compounds in capability as it is used.
Taskade Genesis, launched publicly in October 2025, is the no-code builder that turns a natural-language prompt into a running application, not static code, with a central orchestrator called EVE coordinating agent activity and the app lifecycle. Custom AI agents can be trained on files, data, and web links, deployed as multi-agent teams, and connected to more than 100 external tools, with a public API and an MCP server.
Founded by CEO John Xie, CTO Stan Chang, and CPO Dionis Loire and headquartered in San Francisco, Taskade is a Y Combinator (S19) company that raised a $5M seed round from Grishin Robotics, Y Combinator, and angels including Immad Akhund and Mark Pincus. It serves more than a million users, including teams at Nike, Netflix, Tesla, Airbnb, and 3M, and is sold self serve, with a free plan and Pro at $10 a month or $60 a year.
Vendor details
Canonical URL
https://www.taskade.com
Category
Agent builder
Subcategory
AI-native workspace with prompt-to-app generation, persistent-memory agents and an official MCP server
Funding status
Independent. Y Combinator company, cited by the vendor as S19 in some materials and W19 in others, headquartered in San Francisco and founded 2017 by John Xie, Stan Chang and Dionis Loire. Raised a $5M seed from Grishin Robotics, Y Combinator and angels including Immad Akhund and Mark Pincus. The vendor cites more than a million users, 150,000 apps generated, and named customers including 3M, Nike, Tesla, Netflix, Airbnb, Disney and Adobe.
Company status
independent
Use cases & customers
Primary use cases
Deployment options
Integrations
Agents carry 22 or more built-in tools, cited elsewhere by the vendor as 34, plus custom tool definitions, and automations connect more than 100 native integrations with branching, looping and filtering, spanning messaging, email, CRM and payments through Slack, Gmail, HubSpot, Salesforce and Stripe, extended further through Zapier and n8n, for which the vendor publishes a public source-of-truth repository of its actions and triggers. Documented agent actions include creating tasks, sending emails, posting to Slack and updating calendars. The developer surface covers REST API v1, an Action API v2, an SDK, webhooks, OAuth 2.0 and Personal API Tokens, with OIDC sign-in for Genesis apps. An official Model Context Protocol server exposes 50-plus tools across workspaces, projects, tasks, agents, knowledge bases, templates and automations, with a hosted OAuth endpoint requiring no installation, and ships alongside an OpenAPI-to-MCP code generator. Automation triggers include schedules, task events, deadlines, incoming email and content feeds such as YouTube and RSS.
In practice
You keep rebuilding the same client-portal-plus-intake-form setup across three disconnected tools. In Taskade you describe it once and Genesis assembles a running workspace around it, with the data, agents, and automations already wired together.
Your team's project notes, tasks, and the AI meant to help all live in separate apps that don't talk. Taskade keeps them in one workspace where the project is the memory, agents act on it, and automations write results back.
You want an assistant that knows your accounting method or where your project docs actually live, not a generic chatbot. You can train a custom Taskade agent on your own files, data, and links and give it a defined role.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
10.0 / 14 capabilities · 71%
| Integrations & Tool Calling | Full |
|---|---|
|
Agents carry 22 or more built-in tools plus custom tool definitions, with 34 tools cited in later material, and Automations connect more than 100 native integrations with branching, looping and filtering. Named integrations include Slack, Gmail, HubSpot, Salesforce and Stripe, with further reach through Zapier and n8n. For those, Taskade maintains a public source-of-truth repository of Taskade actions and triggers built on its public API. Agent actions include creating tasks, sending emails, posting to Slack and updating calendars. The official MCP server exposes a further 50-plus tools for workspaces, projects, tasks, agents, knowledge bases, templates and automations. Sourcegithub.com/taskade/mcp, github.com/taskade organization repositories, github.com/taskade/taskade READMEread 2026-08-31 |
|
| Workflow Orchestration | Full |
|
AI Agents v2 has multi-agent teams alongside custom tools, persistent memory, slash commands and human-in-the-loop controls. Agents deploy as multi-agent teams, with a central orchestrator coordinating agent activity and the app lifecycle. Automations are no-code workflow automation with branching, looping and filtering across more than 100 integrations. In Workspace DNA, memory feeds agents, agents trigger automations, and execution writes new state back. Automations and agents are addressable objects in the MCP server tool surface. Sourcegithub.com/taskade/taskade README, github.com/taskade/mcp, taskade.com AI agents pageread 2026-08-31 |
|
| Knowledge Grounding & RAG | Full |
|
Agent Knowledge trains agents on uploaded PDFs, CSVs and documents, URLs and YouTube, or connected projects as live, auto-updating sources. A Knowledge Management page covers bulk import and auto-categorization, and REST API v1 endpoints add and remove projects and media from an agent's knowledge. Each agent keeps its own maintained set of knowledge sources that update automatically. Long-Term Memory is a separate feature. Sourcedocs.taskade.com documentation index, Agent Knowledge and Knowledge Management entries and Agents API referenceread 2026-09-29 |
|
| Human Oversight & Guardrails | Full |
|
Human in the Loop is an approve or reject gate before agents interact with external platforms. The builder turns it on in the agent's Tools tab and selects which tools need approval. When the agent wants to use one of those tools, it proposes the action, the user sees a confirmation prompt, and the agent goes ahead only on Approve and stops on Reject. Recommended uses are sending emails, posting to social media and creating CRM records. So the approval step sits in the run path. Tools can also be enabled, disabled or removed per agent. Sourcedocs.taskade.com Tools for AI Agents pageread 2026-09-29 |
|
| Security, Identity & Governance | Partial |
|
Access controls are OAuth 2.0 and Personal API Token authentication for programmatic access, OIDC sign-in for Genesis apps, single sign-on on higher tiers, team workspaces with administrative controls, and role assignment within workspaces. A toggle controls whether an agent is publicly reachable by shareable link or embedded. There is no security certification, trust center, SCIM provisioning or audit log. Sourcehelp.taskade.com developer API article, github.com/taskade/taskade README, github.com/taskade/mcp, taskade.com product pagesread 2026-08-31 |
|
| Observability & Auditability | Partial |
|
Agent conversations are auto-saved and kept for later review, and automations are durable, with execution resuming after failures. Higher tiers include advanced analytics. There is no agent execution trace, tool-call record, cross-agent run history, change audit log or cost attribution. In the Workspace DNA design, automation execution writes new state back into projects, so attribution of each run matters, and Taskade does not describe it. Sourcegithub.com/taskade/taskade README, github.com/taskade/mcp, help.taskade.com developer API articleread 2026-08-31 |
|
| Memory & State Persistence | Full |
|
Long-Term Memory is held as a dedicated Memory Project that the agent writes and reads. EVE's workspace memory persists across sessions, is scoped to one workspace and grows automatically as the user interacts, and per-agent memory persists across conversations with that agent. The user can browse the memory project, remove entries, correct facts, add context and version it, with edits taking effect in the next conversation, and the memory is addressable through the Action API v2. The agent writes this memory, it has a set scope, and users can purge, review and edit it. The memory project is separate from business projects, so deleting it does not delete business records. Sourcedocs.taskade.com Long-Term Memory pageread 2026-09-29 |
|
| Deployment & Data Residency | Not documented |
|
Taskade is a cloud workspace with native desktop and mobile applications and self-serve pricing starting at a low monthly rate. There is no self-hosting, on-premises deployment, virtual private cloud option, customer-managed encryption keys or customer-selectable region. Genesis apps can be published to a customer's own domain with OIDC sign-in, which controls the published application's address, not where Taskade processes or stores data. Sourcegithub.com/taskade/docs, github.com/taskade/taskade README, help.taskade.com developer API articleread 2026-08-31 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Users are pointed to clone a ready-made app for free from the community gallery or Taskade's official kits and customize it in Taskade Genesis, instead of starting from a blank prompt. Taskade maintains a clone-ready App Kits Gallery, and a Workspace DNA template for building Genesis apps has its own repository. The template library holds 700-plus templates covering project management, engineering and marketing, and Taskade cites 150,000-plus apps generated. Templates are an addressable object type in the MCP server tool surface, with a set flow for creating a project from a template. Sourcegithub.com/taskade/docs, github.com/taskade organization repositories, github.com/taskade/mcpread 2026-08-31 |
|
| Triggers & Channel Coverage | Full |
|
Automations are a trigger-and-action engine that runs work around the clock across more than 100 integrations, with AI agents running the workflows. Triggers span schedules and Slack, Gmail, Google Sheets, HubSpot and GitHub events, and inbound webhooks can also trigger automations. A recent update expanded the trigger catalog and fixed HTTP webhook triggers. Autonomous agents run without per-request prompting. Scheduled and event triggers wake agents without a user. Sourcedocs.taskade.com documentation index, Automations, Comprehensive Integrations, Webhooks and Autonomous Agents entriesread 2026-09-29 |
|
| Model Flexibility & Routing | Full |
|
The TSK-1 model picker lets the customer set an agent or automation to Auto, pin one of four capability tiers (Instant, Standard, Thinking, Reasoning), or, on Max and Enterprise, pin a custom model such as a specific Claude or GPT version, which bypasses TSK-1 routing entirely. More than eleven frontier models are integrated, and switching an agent from Claude to Gemini keeps its memory. Customers choose across model makers, though custom models are limited to the Max and Enterprise plans. Sourcedocs.taskade.com TSK-1 Model Tiers and Long-Term Memory pagesread 2026-09-29 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Taskade offers REST API v1, an Action API v2, an SDK and webhooks for programmatic access, with authentication by Personal API Token or OAuth 2.0 and OIDC sign-in for Genesis apps. An official Model Context Protocol server has its own repository under Taskade's GitHub organization and exposes 50-plus tools covering workspaces, projects, tasks, agents, knowledge bases, templates and automations. There is also an OpenAPI-to-MCP code generator, and a hosted MCP endpoint on Taskade's domain connects by OAuth without local installation. Agents can be published with a shareable link or embedded. The documentation is a public repository that accepts pull requests. Sourcegithub.com/taskade/mcp, github.com/taskade/docs, help.taskade.com developer API article, taskade.com MCP guidanceread 2026-08-31 |
|
| Testing, Debugging & Optimization | Not documented |
|
There is no testing, evaluation, scoring, benchmarking or regression capability, and no self-checking or verification gate on agent output before use. Automations have durable execution and resume after failures, which is reliability, not a measure of output quality. The MCP tool surface covers workspaces, projects, tasks, agents, knowledge bases, templates and automations, with no evaluation or test object type. Sourcegithub.com/taskade/taskade README, github.com/taskade/mcp, github.com/taskade/docs, help.taskade.com developer API articleread 2026-08-31 |
|
| Browser & Computer Use | Not documented |
|
Agents have 22 to 34 built-in tools, more than 100 native integrations, custom tool definitions and web browsing to gather information. Every action path runs through connectors, the REST and Action APIs, or the MCP server, which are programmatic interfaces. Web browsing for research is retrieval over fetched content, not operation of software that lacks an interface. There is no browser control, session automation, form filling or cloud-computer capability. Sourcegithub.com/taskade/taskade README, github.com/taskade/mcp, help.taskade.com developer API articleread 2026-08-31 |
|
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 chats in Taskade now keep working after the user closes the tab or reloads, and the agent finishes its reply. Reopening the chat picks the reply up live where it left off, a second tab can follow the same reply as it streams, and Stop halts the agent from any tab.
Bears on: Workflow orchestration
View sourceWith Taskade v6.278.0, a tool added to a public agent stays off for visitors until the owner turns it on in Tool Permissions, while agents published before the release keep the tools they had. When Taskade EVE builds or publishes an agent, it turns on the tools that agent needs, and workspace members who can only view an agent no longer see its instructions.
Bears on: Security / enterprise
View sourceTaskade enabled the deployment of custom, white-labeled AI agents that feature generated avatars, custom personas, and distinct URLs. Users can publish these branded agents via a public Taskade link, a custom domain using a CNAME record, or as an embedded website widget without writing any code.
Bears on: Deployment / data residency
View sourcePricing
Free plan. Pro is $10 a month, or $60 a year ($5 a month billed annually).
Free / trial
Free plan for 2 users with 11,000 one time AI credits (1,000 on verifying and 10,000 on the first app build)
Lowest paid plan
Pro at $10 a month, or $60 a year billed annually, for up to 10 users
Support SLA / resale
Business adds priority support over the standard support on Free and Pro. Enterprise adds dedicated support and a custom SLA.
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 Taskade
The closest documented capability profiles to Taskade among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- MindPal9.5 / 14Adds documented Testing, Debugging & Optimization
- Chipp12.0 / 14Adds documented Testing, Debugging & Optimization
- Langflow12.0 / 14Adds documented Deployment & Data Residency and Testing, Debugging & Optimization
- Elastic11.5 / 14Adds documented Deployment & Data Residency
- Lindy10.5 / 14Adds documented Browser & Computer UseTaskade vs Lindy →
- Teneo9.5 / 14Adds documented Testing, Debugging & Optimization
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded