$ buildwith info composio

Composio

#8 in Agent Ops · Freemium

sources differ by section

Composio gives AI agents pre-authenticated toolkits, per-user sessions, authentication, triggers and a sandbox so they can act in real software. The SDKs (Python and TypeScript) are MIT-licensed on GitHub; the hosted platform is a paid service with a free Hobby tier.

for Developers building agents on OpenAI Agents, Claude Agent SDK, Vercel AI SDK, LangChain and other frameworks who need their agents to use users' own accounts in third-party apps.

use this if your agent needs authenticated access to real apps (Gmail, Slack, GitHub and many more) without you building OAuth and integrations yourself.

open composio.dev ↗

Features

$ features --list

  • ›1,000+ toolkits per the README (the pricing page says 1,500+)
  • ›Managed OAuth: consent, token storage, refresh and scopes per connected account
  • ›Triggers that deliver app events to your webhook
  • ›Custom tools and your own MCP servers alongside the catalog
  • ›Python SDK and TypeScript SDK (@composio/core) with adapters for OpenAI Agents, Claude Agent SDK, Vercel AI SDK and LangChain
  • ›Sandboxed workbench and proxy execute for endpoints not yet wrapped as tools
  • ›Instant Tools: some paid APIs run on Composio's accounts, billed from your balance at 0% markup

Pricing

$ pricing --tiers

Hobby (SDK)

$0

No card. 100,000 tool calls and 50,000 trigger events a month (up to 20,000 calls and 10,000 events on Composio-managed apps), unlimited connected accounts on your own apps, 3 team members, and $2 of one-time credit. Hard-capped: usage pauses at the limit instead of billing.

Pro (SDK)

$29/month

Includes $29 of monthly usage credit (no rollover), unlimited team members, 10,000 requests per minute (2,000 on Hobby), and spend caps. Past the free amounts: $0.0003 per tool call and $0.003 per trigger event. Firewall, BAA, IP allowlist and zero data retention are paid add-ons.

Standard (team app)

$18/seat/month

Separate plan on the main pricing page for teams connecting apps to Claude, Codex, Cursor and similar clients: $18 of credit and 10,000 tool calls per seat each month, pooled, plus SSO, Firewall and zero data retention. The free version of that plan allows up to 3 members.

Enterprise

Custom

Committed volume, SSO/SCIM, customer-managed keys, advanced white-labeling, MSA/DPA/BAA, dedicated support and SLA. Enterprise on the team-app plan adds bring-your-own-cloud.

Why this rank

$ diff --rank 8

Ranked #8 in agent ops. Composio is not an agent itself but the tool and auth layer many agents use: OpenHuman and OpenMausBot both connect apps through it, and so does Rakazo. Its adoption (31,024 stars on 2026-11-11) sits just below Buzz, and its free tier is generous, but it depends on a hosted paid service, so it ranks below the agent runtimes and workspaces above it.

Score breakdown

$ scores --rubric

Measured so far · how we rank

Adoption

20% weight

90verified

How widely builders already use it for this kind of work. — 31,160 GitHub stars on 2026-11-18. Agent Ops adoption scale: 20 × log10(stars), rounded, capped at 100 (1k stars = 60, 10k = 80, 100k+ = 100); here 20 × log10(31,160) = 89.9. Stars are a proxy for builder adoption, not a usage count. · verified 2026-11-18

Strengths

$ strengths

  • ›31,024 GitHub stars and 4,937 forks on 2026-11-11; the SDK repo was pushed the day of checking.
  • ›The SDK Hobby plan is hard-capped with no card, so usage pauses at the limit instead of billing.
  • ›Works with most agent frameworks and over MCP, so it complements the agents ranked above it.

Limitations

$ limits

  • ›Only the SDKs are open source; the toolkits, auth and execution run on Composio's hosted service.
  • ›Composio-managed OAuth apps get lower allowances (20k of the 100k free calls) and extra per-call charges; scaling means registering your own OAuth apps.
  • ›Usage-based add-ons (direct execution, proxy, sandbox, compliance) make costs harder to predict past the free tier.
  • ›New pricing applied to signups from 2026-08-15, so older guides may quote different numbers.

Sources

$ sources --verified

$ buildwith alternatives composio

  • #1 Hermes AgentFree / OSS

    use this if you want an always-on, model-agnostic agent that learns skills over time and lives in your terminal and chat apps.

  • #2 HerdrFree / OSS

    use this if you want your coding agents to keep running after you close the laptop and to reattach from any terminal.

  • #3 OpenClawFree / OSS

    use this if you want a hugely popular open-source personal agent that actually does things on any OS and platform.

  • #4 PaperclipFree / OSS

    use this if you want to run a team of agents (Claude, Codex, Cursor, Hermes and more) toward one goal, with roles, budgets and tickets.

  • #5 DeepSeek HarnessFree / OSS

    use this if you want an open-source, plugin-first agent harness you can run as a local web UI or desktop app and point at DeepSeek, Claude, OpenAI, Kimi or your own gateway.

  • #6 OpenHumanFree / OSS

    use this if you want a fast, lightweight open-source agent harness with built-in memory that can run many agents on a small server.

  • #7 BuzzFree / OSS

    use this if your team wants humans and agents working in the same rooms with every message, workflow step and approval in one auditable log.

  • #9 OpenMausBotFree / OSS

    use this if you want a chat-app roster of bots running on the Claude, Codex or Grok CLIs and subscriptions you already have, each with its own computer.

  • #10 RakazoFree / OSS

    use this if you want persistent, self-hosted AI teammates with their own browser and shell, on your own model keys and machines.

  • #11 OpenBotFreemium

    use this if you want a self-hostable workspace where AI coworkers get their own computers, under company sign-in, tool permissions, approvals and audit.

  • #12 HarnessFreemium

    use this if you run Claude Code, Codex, Cursor and others across several machines and want one place to watch and steer them.

sponsor this spot →