Activepieces
Open source, MIT licensed automation platform where every one of 700 plus integrations is also an MCP server, combining a visual flow builder, AI agents and tables with cloud or fully self hosted deployment.
Activepieces is an open source automation platform built around artificial intelligence and the Model Context Protocol. Teams use a no-code visual builder to assemble workflows from reusable building blocks the platform calls pieces, each one an integration such as Gmail, Slack, or a database, connected into flows that start from a trigger like an incoming email or a schedule and run a series of actions, with branching and data transformations along the way.
The pieces themselves are written in TypeScript and published as open source packages, and roughly 60 percent of them come from the community, so the code behind every integration can be inspected. Activepieces adds AI on top of this foundation. Native steps call language models, an AI assistant helps build flows, and AI agents can sense their environment, plan a sequence of steps and act by using pieces as tools, so a workflow can make decisions instead of following only fixed rules.
Every integration in Activepieces is automatically exposed as an MCP server, which turns its whole library into tools that external AI assistants like Claude, Cursor, or other MCP compatible clients can call directly. An AI agent can send an email, update a CRM, or edit a spreadsheet through Activepieces without a custom workflow for each case.
Because it is open source under the permissive MIT license, Activepieces can be self hosted entirely within an organization's own network, including air gapped environments. It is also offered as a managed cloud with EU and US data regions. Flows can include approval and delay steps and leave audit trails, and enterprise editions add governance features like single sign on, user provisioning, and role based access. Non technical builders work in the visual builder, while developers can write their own pieces in TypeScript or embed automation in their own product with the JavaScript SDK.
Vendor details
Canonical URL
https://www.activepieces.com
Category
Agent builder
Funding status
Independent. Y Combinator backed, founded 2022. Open source core under the MIT license with more than 700 integration pieces, roughly 60 percent community contributed, and over 300,000 builders reported. Customers named on the site include MoneyGram, Alan, PostHog, Red Bull, Rakuten, Contentful, Roblox, DocuSign and Pipedrive.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
More than 700 open source TypeScript integration pieces spanning CRM, communication, databases, project management, ecommerce, HR and AI providers, each usable as a workflow step or as an agent tool, with anything else reachable through the HTTP piece or a webhook. Every piece is automatically exposed as an MCP server callable from Claude, ChatGPT, Cursor, GitHub Copilot, Windsurf and Gemini. Activepieces bills this as the largest open source MCP toolkit. An AI provider gateway connects Azure OpenAI, Amazon Bedrock, OpenRouter or LiteLLM, and an embeddable JavaScript SDK ships automation inside the customer's own product.
In practice
You want to move off automation that charges per task and keep your data in house. Activepieces is open source and can be self hosted, even in an air gapped network, and you can inspect and extend every integration it runs.
You want your AI assistant to actually do things in your apps. Activepieces exposes every integration as an MCP server, so Claude or Cursor can send email, update your CRM, or edit sheets through it directly.
Your workflow needs to make judgment calls, not just follow fixed rules. Activepieces lets you drop AI agents into a flow that sense, plan, and act using your connected pieces, with approval steps to keep humans in control.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
11.5 / 14 capabilities · 82%
| Integrations & Tool Calling | Full |
|---|---|
|
Activepieces has more than 700 integrations covering CRM, communication, databases, project management, ecommerce, HR and AI providers. Each is a typed TypeScript piece that works as a workflow step or as an agent tool, and anything else can be reached through the HTTP piece or a webhook. Roughly 60 percent are contributed by the community, and all are open source npm packages. Sourceactivepieces.com/pieces and github.com/activepiecesread 2026-08-30 |
|
| Workflow Orchestration | Full |
|
A visual builder composes multi step flows with branching, loops, conditions, code steps and data transformations. AI agents inside those flows can sense, plan and act using pieces as tools. Agents, flows and tables come with every plan, including the free one, and multi agent orchestration is supported at scale. Sourceactivepieces.com/pricing and product/ai-agent-builder; activepieces.com/product/ai-agent-builderread 2026-08-30 |
|
| Knowledge Grounding & RAG | Full |
|
Each agent has a Knowledge Base section where the builder uploads PDF, DOCX, TXT or CSV documents or points at a project table, and the agent looks answers up instead of guessing. Retrieval runs on Postgres with the pgvector extension, which is installed on Cloud and in the standard self-hosted images, and table sources stay current as flows update them. Sourceactivepieces.com/docs/agents/knowledge and /docs/tables/with-agentsread 2026-09-29 |
|
| Human Oversight & Guardrails | Full |
|
Flows can include steps that require approval before continuing or delay execution for a period, alongside chat and form input interfaces. Sensitive connections require approval before a user may use them, and flows are fully versioned so changes can be reviewed and rolled back. Sourcegithub.com/activepieces and activepieces.com/product/governance-and-managementread 2026-08-30 |
|
| Security, Identity & Governance | Full |
|
Single sign on uses SAML 2.0 with Okta, Microsoft Entra ID, Google Workspace, Auth0 and OneLogin, alongside SCIM provisioning and advanced role based access control. Audit logs carry full actor, resource and timestamp context, sensitive connections require approval before use, and credentials are centralized. Private pieces, per team control over which integrations are visible, secret managers and event streaming to a customer SIEM complete the controls. Sourceactivepieces.com/product/governance-and-management and pricingread 2026-08-30 |
|
| Observability & Auditability | Full |
|
Audit logs record every flow run, user action and system event with resource type, detailed description, actor and timestamp, and can be filtered by action, performer, project and date range. Events stream to a customer SIEM, team analytics are available, and per step run logs show inputs, outputs and errors. Flows are fully versioned. Sourceactivepieces.com/product/governance-and-management and pricingread 2026-08-30 |
|
| Memory & State Persistence | Partial |
|
Tables store data inside Activepieces for flows and agents to read and write, so state can persist between runs without an external database, and flows are versioned. Tables are general storage, and agents have no memory of their own with a set scope, lifetime or review path. Sourceactivepieces.com/docs/tables/overview and /docs/agents/createread 2026-09-29 |
|
| Deployment & Data Residency | Full |
|
Every plan runs on the managed cloud or on the customer's own servers. The MIT licensed Community Edition can be self hosted with Docker, Docker Compose, Kubernetes or Helm on any cloud, including air gapped networks, and the managed cloud offers EU and US data regions plus dedicated workers on Ultimate. Sourceactivepieces.com/pricing, product/deployment-options and open-source; activepieces.com/product/deployment-optionsread 2026-08-30 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
A Template Library in the Explore tab offers ready-made flows across Sales, Marketing, Customer Service, Finance, HR, Engineering, Operations and AI Agents. Templates are searchable by name and show the apps used and the estimated time and cost saved, and admins can manage templates for their platform. Only the categories are named, with no individual template or ready agent listed. Sourceactivepieces.com/docs/flows/template-library and /docs/admin-guide/guides/templatesread 2026-09-29 |
|
| Triggers & Channel Coverage | Full |
|
Flows can start from app events across more than 700 integrations, from scheduled runs, and from webhooks and HTTP for anything with an API. Built in human input triggers include a chat interface and a form interface, and on every plan external AI clients such as Claude, ChatGPT, Cursor, GitHub Copilot and Gemini can invoke flows through MCP. Sourceactivepieces.com/pricing and github.com/activepiecesread 2026-08-30 |
|
| Model Flexibility & Routing | Full |
|
In the AI Providers settings, customers connect their own AI gateway or cloud provider, such as Azure OpenAI, Amazon Bedrock, OpenRouter or LiteLLM, with centralized billing and usage. From the Plus plan customers can bring their own AI keys, and they choose between fast, smart and frontier model tiers priced at 2, 10 and 20 credits. Sourceactivepieces.com/product/governance-and-management and pricingread 2026-08-30 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Every one of the 700 plus pieces is automatically exposed as an MCP server that Claude, ChatGPT, Cursor, GitHub Copilot, Windsurf and Gemini can call, and Activepieces bills this as the largest open source MCP toolkit. MCPs and API access come with every plan, including the free one. The piece framework is open source TypeScript published to npm with hot reloading, and an embeddable JavaScript SDK is available for SaaS integration. Sourceactivepieces.com/pricing and github.com/activepiecesread 2026-08-30 |
|
| Testing, Debugging & Optimization | Partial |
|
Individual steps can be run in a test mode with sample data before a flow is published, and run logs show inputs, outputs and errors per step. Failed steps retry automatically, and versioning with Git Sync and releases on Ultimate lets changes be shipped and rolled back. Activepieces has no agent evaluation, scoring or regression testing product. Sourceactivepieces.com/docs and pricingread 2026-08-30 |
|
| Browser & Computer Use | Not documented |
|
All action goes through typed integration pieces, HTTP requests and webhooks against documented APIs. Activepieces has no browser automation or screen control and cannot operate software that lacks a programmatic interface. Sourceactivepieces.comread 2026-08-30 |
|
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
Activepieces 0.92.0 adds agent creation from a natural language description and an AI Router that chooses a workflow route from a question. The release also adds a Deno code sandbox, an MCP activity feed recording client calls, and OpenID Connect support for restricting connector access by email domain.
Bears on: Agent capability
View sourceActivepieces release 0.85.4 added AI-ready metadata across hundreds of pieces, tagged non-agent actions with audience='human', and updated builder docs to require AI metadata on new actions and triggers.
Bears on: MCP / tool calling / API
View sourceActivepieces release 0.85.4 shipped broader runtime visibility improvements, including evlog-wide events replacing OpenTelemetry + pino, date ranges for queue health metrics, and worker/sandbox state and RAM visibility.
Bears on: Observability / auditability
View sourcePricing
Plus is $20 a month (10,000 credits, up to 5 users) and Team $200 a month (50,000 credits, 25 users), with annual billing saving two months. Free forever includes 1,000 credits a month, and the MIT Community Edition self hosts free. Ultimate and Enterprise Control are custom.
Credit based. One credit covers a flow run regardless of step count, one covers each agentic action, and an AI step takes 2, 10 or 20 credits depending on model tier, or 1 with the customer's own AI key. The plan sets seat count and feature access.
Included quota
Free carries 1,000 credits a month on a daily reset, for up to 5 users, with unlimited flows, agents, tables, MCPs and API access. Plus is $16 a month billed yearly, with 10,000 credits a month, 5 users and bring your own AI keys. Team is $166 a month billed yearly, with 50,000 credits a month, 25 users then $25 each, unlimited projects, SSO, standard roles, global connections and email support. Ultimate has custom credits pooled yearly, SCIM, custom RBAC, audit logs, secret managers, event streaming, private pieces, branding, Git Sync and releases, and dedicated workers. Embed starts at $36k a year.
What is public
The public plans are Free ($0, 1,000 credits a month, up to 5 users), Plus ($20 a month, 10,000 credits, up to 5 users), Team ($200 a month, 50,000 credits, 25 users), Ultimate (custom, credits sized yearly, unlimited users), Embed (from $36k a year) and Enterprise Control (custom, self hosted or air gapped, with SSO and SCIM, custom RBAC and audit logs). Extra credits are $0.007 on Plus and Team, and yearly billing saves two months.
Billing mechanics
Each plan carries a credit allowance, with extra credits at $0.007 on Plus and Team and volume rates on Ultimate. Bringing your own AI key lowers AI step cost. The self hosted Community Edition has no credit caps.
Cost watchouts
Governance is paywalled. SSO and standard roles start at Team, while SCIM, custom RBAC, audit logs, secret managers, event streaming and private pieces are Ultimate only, and the self hosted Community Edition excludes Agents and Chat, Projects, API access and the whole team and admin layer. Team includes 25 users then $25 per user per month. AI steps cost 2 to 20 credits depending on model tier unless the customer brings its own key. Self hosting shifts infrastructure, upgrades and uptime to the customer.
Variable cost rationale
Credits are the meter. One credit covers a whole flow run however many steps it has, and each agentic action costs one credit, so ordinary automation volume stays cheap and predictable. AI steps cost 2, 10 or 20 credits depending on model tier, and they are what makes the bill grow. Beyond Team's 25 included users, each extra user is $25 a month. Each plan carries a credit allowance. Extra credits cost $0.007 each on Plus and Team, Free runs wait for the daily reset, and Ultimate pools credits across the year. Bringing your own AI key cuts every AI step to 1 credit, and the self hosted Community Edition has no credit caps.
Additional watchouts
Enterprise governance sits in the top tier only. Pricing has changed twice, and older structures still circulate in other sources.
Overage / add-ons
Past the plan allowance, extra credits cost $0.007 each on Plus and Team. On Free, runs wait until the credits reset the next day. Ultimate pools credits across the year. The self hosted Community Edition has no caps.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free forever with 1,000 credits a month for up to 5 users and no card, and the MIT licensed Community Edition self hosts free
Lowest paid plan
Plus at $20 a month, or $16 a month billed yearly
Commercial notes
Activepieces was founded in 2022 by Mohammad AbuAboud and Ashraf Samhouri and is backed by Y Combinator. It is MIT licensed, with an AI agent layer and native Model Context Protocol support ("largest open-source MCP toolkit"), and its open source project has 22,000+ GitHub stars.
Key ambiguities
Pricing has changed twice. The task based tiers and the later $5 per active flow model are both superseded by the current credit model. Many third party sources still publish the older structures.
Cancellation / refund
Free, Plus and Team are self serve. Upgrades and added seats take effect at once and are prorated, and downgrades apply at the end of the billing period.
Support SLA / resale
Community support on Free and Plus, email support on Team and dedicated support on Ultimate. Embed puts a white label builder inside a customer's own product.
Missing data
Nothing material is missing. The full rate card, credit costs per action type and the plan feature matrix are all published.
Related vendors
- Lindy — Lindy is an AI teammate that lives in Slack, answers from your tools…
- 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…
- Airia — Enterprise platform that unifies agent orchestration, security, and…
Alternatives to Activepieces
The closest documented capability profiles to Activepieces among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Budibase11.5 / 14Matches Activepieces across all 14 documented capabilities
- Cohere North11.0 / 14A lighter documented profile than Activepieces
- Dify12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Joget11.0 / 14A lighter documented profile than Activepieces
- LuMay12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Retool12.0 / 14Fuller documented coverage on 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