Specialist AI Agents for Every Task
Relevance AI is a low/no-code platform for building AI agents and multi-agent "Workforces" that autonomously complete tasks across sales, customer success, operations, and support, positioned as decoupling growth from headcount via an AI workforce.
Published by the vendor themselves — not community forks.
Agent skill framework compatible with Codex, Claude Code, Cursor, and GitHub Copilot
Claude Code plugin for Relevance AI
| Plan | Price | Included | Notable |
|---|---|---|---|
| Pro | $19/month billed annually (or $29/month billed monthly) | 30,000 Actions/year, $240 Vendor Credits/year 2 Build Users | Unlimited Workforces, Scheduling, Chat mode |
| Team | $234/month billed annually (or $349/month billed monthly) | 84,000 Actions/year, $840 Vendor Credits/year 5 Build Users, 45 End Users, 5 shared projects | Calling & meeting agents |
| Enterprise | Contact sales | Custom Actions and Vendor Credits Unlimited users & projects | Enterprise app triggers, Agent evaluations, A/B testing & analytics |
Checked 2026-08-03 against their pricing page. Vendors change pricing without notice.
Relevance AI is a low/no-code AI agent platform: individual "Agents" complete tasks autonomously, and multiple agents can be composed into "Workforces" for more complex workflows, with a visual canvas, RAG-based Knowledge layer, and a Tools builder for integrations.
Vendor marketing targets go-to-market, customer success, and operations leaders moving from AI-assisted work to autonomous agent workflows, spanning solo GTM operators (Pro plan, 2 build users) up to org-wide enterprise deployments with SSO/RBAC/audit logs.
Pricing is metered on both "Actions" and "Vendor Credits" with separate annual allotments (e.g. Pro: 30,000 Actions/year and $240 Vendor Credits/year), which makes monthly cost hard to predict for spiky or high-volume workloads without buying top-ups ($80 per 1,000 extra Actions, $20 per 10,000 extra Vendor Credits). The Free plan caps out at 1 user, 1 project, and 200 Actions/month, so it only supports a single-operator trial, not team evaluation. Calling and meeting agents are gated behind the Team plan ($234/mo annual) and above, so a small team wanting only that specific capability pays for the mid-tier plan's full seat/user bundle to get it.
General automation runtimes used to wire GTM tools together, from node-graph builders to agent frameworks.
Category: Workflow and agent orchestration. Membership is decided by 3 stated tests, not by category tags — see them and the full comparison.
Appears in comparison shortlists
No. Relevance AI states that Free is retired for both new signups and existing accounts. Organizations previously on Free must upgrade to Pro or Team to resume use.
We could not locate a documented base URL or a published OpenAPI specification.
Yes. The MCP server grants an authenticated AI client (Claude Desktop, Cursor, VS Code, ChatGPT, or the vendor's own Claude Code plugin) full access to a project's agents and tools - create agents, build tools, set up Workforces, trigger and execute them.
Pro costs $19/month billed annually or $29/month billed monthly, with 30,000 Actions/year and $240 Vendor Credits/year. Team costs $234/month billed annually or $349/month billed monthly, with 84,000 Actions/year and $840 Vendor Credits/year. Enterprise is custom-priced. Free is retired. Extra Actions cost $80 per 1,000 and extra Vendor Credits cost $20 per 10,000.
Multi-agent teams that collaborate on complex workflows, configured on a visual canvas with escalation and approval steps, as distinct from single autonomous Agents.
Yes.
The Enterprise plan adds SSO, RBAC, audit logs, enterprise app triggers, and a dedicated account manager, per the vendor's pricing documentation.
This page tells you whether Relevance AI fits. Cheetah builds and runs the system it goes into — enrichment, sequencing, CRM and the joins between them.
Book a call →The directory stays free. There is nothing gated behind this.
Tell us what you want to improve. Fedor reviews the workflow and replies by email when there is a useful fit.