Back to vendors
C

Composio

Visit site
Entry priceHobby free (100K tool calls/mo) · Pro $29/mo + usage · Enterprise customFull pricing detail

Action layer for AI agents, with more than 1,500 toolkits behind managed OAuth for each user, approvals before chosen tools run, a Firewall against prompt injection, triggers, a code sandbox and a cloud browser, and a log of every tool call.

Composio is the action layer for AI agents. It holds the connections to other software so an agent can do things in a user's own accounts instead of only talking about them. The unit of work is a session, created for one of the customer's users, which scopes who the agent acts for, which toolkits and tools it can see, how it authenticates, and the state it accumulates during the run.

More than 1,500 toolkits are available, and Composio manages the OAuth redirects, token exchange and refresh behind them. When a tool needs an account that is not connected, the agent can pause, send the user a connect link and retry once the user has authorized, and the connection then persists for later sessions. Tools execute on the server with the credential injected, so tokens never reach the model.

Tool search finds the tools for a task and returns skills, playbooks of steps and known pitfalls drawn from real usage. Instant tools let an agent call paid services such as search and enrichment from a Composio balance, with no provider accounts to open. Triggers deliver events from connected apps to the customer's webhook, a persistent sandbox runs code for work too big for single calls, and a Browser Tool gives the agent a cloud browser for sites with no API.

Control over what the agent does has grown. A session can require the user's approval before chosen tools run, such as anything that creates, updates or deletes, a feature added in October 2026 and still marked experimental. Firewall blocks tool calls or results that match checks written in plain language and stops prompt injection in tool results. Every tool execution and trigger event is logged with arguments and responses, retained from 7 days to a year and exportable to a SIEM, with zero data retention available.

Composio is SOC 2 Type II attested and ISO 27001:2022 certified. It disclosed a security incident in May 2026, in which an attacker reached internal systems and customer credentials, and its September update describes the remediation, including APIs that no longer return tokens, envelope encryption and independently re-verified fixes. It runs in Composio Cloud, in a private VPC, self hosted, or with credential keys in the customer's own KMS, and it does not run the agent. Pricing is published, from a free Hobby plan of 100,000 tool calls a month to Pro at $29 a month plus metered usage.

From our comparison video

Arcade vs Composio: 6 Questions for Teams Whose Agents Act for Users

Our 6 minute video puts Composio side by side with Arcade. It covers what each one does and how each is priced, then when to choose which.

Recorded in October 2026. The profile here is live and updates as research is verified.

Vendor details

Canonical URL

https://composio.dev

Category

Agent infrastructure

Company status

independent

Use cases & customers

Target customers

AI developersplatform teams

Deployment options

SaaSAPI

Integrations

Composio offers more than 1,500 toolkits across apps such as Slack, GitHub, Gmail, Notion, Jira, Linear, HubSpot and Salesforce, exposed to an agent through a session with managed OAuth per end user, tool search and multi-execute meta tools. It also ships Python and TypeScript SDKs with provider adapters for the major agent frameworks, sessions over MCP and single-toolkit MCP servers, a CLI and agent plugins for Claude Code and Codex, triggers delivered to the customer's webhook, and a Logs API for streaming tool execution records to a SIEM.

In practice

Your agent needs to act in Slack, GitHub and Gmail for each of your users, and the OAuth and token refresh work is eating your roadmap. Composio manages authentication for each user and exposes those apps as tools the agent can call right away.

You want Claude Code or Cursor to do real work across your apps, not just answer questions. Composio exposes its sessions over MCP and ships an agent skill for coding agents, so the client reaches tools from more than 1,500 toolkits with authentication handled.

You are putting an agent into production and worry it could send, post or delete something it shouldn't. A Composio session limits which tools the agent sees, asks the user to approve chosen tools before they run, and Firewall blocks calls and results that break your rules, with every call logged.

Agentic Index coverage score

9.5 / 14 capabilities · 68%

Integrations & Tool Calling Full

Each session gives an agent tools from more than 1,500 toolkits, scoped to one of the customer's users, and Composio manages the OAuth redirects, token exchange and refresh behind them. The agent can pause in the middle of a chat, send the user a Connect Link and retry the tool once the account is connected, and the connection persists for later sessions.

Tools run on the server with the credential injected, never handed to the model. Tool search finds the right tools for a task, custom tools and MCP servers sit alongside the catalog, and Instant tools let an agent call paid third party services such as search and enrichment from a Composio balance without the user opening provider accounts.

Sourcedocs.composio.dev/docs/how-composio-worksread 2026-10-24

Workflow Orchestration Partial

The sandbox is a persistent Python environment where the agent writes code that calls tools programmatically, with helpers for tool execution, LLM calls, file uploads, direct API calls and web search, error correction on generated code, and state that persists across calls, and a MULTI_EXECUTE meta tool runs several tool calls together. There is no workflow definition, versioned flow, or sequencing and branching that combine deterministic workflow nodes with autonomous agent steps.

Sourcedocs.composio.dev/docs/sandbox/remoteread 2026-10-24

Knowledge Grounding & RAG Not documented

There is no retrieval structure Composio maintains over the customer's own documents. Its search finds the right tools for a task, and its sandbox can extract text from files an agent is working on.

Sourcedocs.composio.dev/docs/how-composio-worksread 2026-10-24

Human Oversight & Guardrails Full

A session can require the user's approval before chosen tools run. The customer picks them by tag, such as tools that create, update or delete something, and can set different rules for each toolkit or tool. When the agent calls one of those tools, Composio does not run it. It asks the user to approve the call, runs the tool once the user answers, and passes a decline or cancel back unchanged, and an MCP client that cannot ask can be set to deny or allow by default.

Approvals arrived in October 2026 and are still marked experimental. Firewall adds checks written in plain language that block a tool call before it runs or a result before the agent sees it, with a built in check for prompt injection in tool results. The customer also chooses which toolkits and tools a session exposes, and scoped API keys keep session management apart from tool execution.

Sourcedocs.composio.dev/docs/approvalsread 2026-10-24

Security, Identity & Governance Full

Composio is SOC 2 Type II attested and ISO 27001:2022 certified, with the SOC 2 report and sub processor list in its Trust Center at trust.composio.dev. Access controls include organization and project isolation, scoped project API keys that keep session management apart from tool execution with an IP allowlist for each key, MFA an organization admin can enforce, and signed webhook deliveries.

Credentials stay out of the model's context, APIs no longer return connected account tokens or custom OAuth client secrets, OAuth credentials use envelope encryption, and API keys are stored only as hashes. Composio disclosed a security incident in May 2026, in which an attacker reached internal systems and customer credentials, and its September update lists that remediation, a rebuilt tool building service and independent assessors who re-verified the fixes. Enterprise adds SAML or OIDC SSO with SCIM provisioning and customer managed keys.

Sourcecomposio.dev/blog/composio-may-2026-security-incidentread 2026-10-24

Observability & Auditability Full

Every tool execution and trigger event is logged with the toolkit and action, status, connection and auth config IDs, the supplied user ID, timing and source, and by default the request arguments and response data, kept for up to a year. Enterprise sets its own retention, from 7 days to a year, and zero data retention keeps only metadata. A Logs API and both SDKs search records by user, tool and status, and records export as CSV or into a SIEM or observability platform.

Sourcedocs.composio.dev/docs/poc-to-prod/stream-logs-to-a-siemread 2026-10-24

Memory & State Persistence Partial

A Composio session scopes execution state for the run, covering logs, tool memory, MCP state and sandbox files, with sandbox variables and runtime state persisting across calls and cleared after roughly 12 hours of inactivity, and sessions can be reused, updated and deleted. The scope (the session and its user) and the lifetime are stated. This is state carried through one task, and there is no memory layer the agent draws on across runs.

Sourcedocs.composio.dev/docs/security/data-retentionread 2026-10-24

Deployment & Data Residency Full

Customers choose among four deployment options, each with its own credential boundary. Besides Composio Cloud there is a private VPC deployment inside the customer's network boundary, a self hosted deployment in the customer's environment with Helm support, and a deployment with customer managed keys, where a proxy in the customer's cloud holds credential plaintext under keys in its own KMS (AWS KMS, Google Cloud KMS or HashiCorp Vault Transit).

Sourcedocs.composio.dev/docs/security/token-custodyread 2026-10-24

Prebuilt Agents, Templates & Packs Not documented

There is no agent or workflow a customer adopts whole. Composio ships toolkits and meta tools that let an agent find and run actions, plus example applications. Its skills are execution playbooks for single tasks, such as sending a Slack message, derived from real usage and returned with tool search as ordered steps and known pitfalls. Nothing is installed or chosen, so they guide the customer's own agent rather than arriving as ready made workflows, templates or agents for particular roles.

Sourcedocs.composio.dev/docs/skillsread 2026-10-24

Triggers & Channel Coverage Full

Triggers react to events in connected apps and deliver them to the customer's webhook as structured payloads. A trigger can be activated for a user, events arrive through an SDK subscription or in production, and trigger instances can be listed, enabled, disabled and deleted. A worked example runs an agent when an email arrives.

Sourcedocs.composio.dev/docs/triggersread 2026-10-24

Model Flexibility & Routing Full

The agent and its model stay entirely the customer's. Composio never proxies the customer's LLM or runs an agent on its behalf, and its provider adapters serve tools to whatever framework and model the customer runs, so the model is the customer's choice throughout.

Sourcedocs.composio.dev/docs/sandbox/remoteread 2026-10-24

APIs, SDKs & MCP Extensibility Full

Developers get Python and TypeScript SDKs, a CLI, a current REST API (v3.1) with a published reference, provider adapters for the major agent frameworks, sessions exposed over MCP, single-toolkit MCP servers and an agent skill for wiring Composio into a coding agent.

Sourcedocs.composio.dev/llms.txtread 2026-10-24

Testing, Debugging & Optimization Not documented

There is no evaluation harness, scored test cases, quality gate or optimization loop after deployment for the customer's agent. Composio's guidance covers building, authenticating and running tools, with advice on production readiness and rate limits, but no gate or debugging path for agent behavior.

Sourcedocs.composio.dev/llms.txtread 2026-10-24

Browser & Computer Use Partial

Composio's Browser Tool gives an agent a cloud browser for sites with no API. The agent hands it a task in plain language, and a browser agent navigates, clicks, fills forms, handles multi step logins and returns the data or any files it produced.

A live link lets the user watch the browser as it works, a session can be reused so logins and cookies carry over to the next task, and a stuck task can be stopped. The agent sets the task rather than steering each step, and there is no desktop or remote computer session. Separately, the sandbox runs code, which is code execution rather than computer use.

Sourcedocs.composio.dev/toolkits/browser_toolread 2026-10-24

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

·Human approval / guardrailsVerified

Composio Firewall checks every action an agent takes through Composio against the user's intent and the limits set by the developer and user, before the action runs. It also screens tool results before they reach the agent and blocks any that carry malicious instructions. It is live for all Composio developers.

Bears on: Human approval / guardrails

View source
·Agent capabilityVerified

Composio Instant gives agents a wallet for calling more than 100 paid third party tools, including Apollo, People Data Labs, Exa, Parallel and ZeroBounce, without the user creating provider accounts or API keys, with a charge per call. New accounts start with $2 of wallet credit and Pro includes $29 a month, the user's own connected account is used first, and failed calls are not charged.

Bears on: Pricing / packaging

View source
·Security / enterpriseVerified

A per project option to skip data logging is now Zero Data Retention, an organization add on at Composio that an admin can switch on for every project at once. With it on, tool calls run without storing request arguments, responses or error text, and logs keep only metadata such as IDs, timing and status.

Bears on: Security / enterprise

View source
View all 4 Composio updates →Tracked since Jun 2026 · Verified from public vendor sources

Pricing

Hobby free (100K tool calls/mo) · Pro $29/mo + usage · Enterprise custom

Monthly platform fee on Pro plus usage: tool calls, delivered trigger events and any add-ons a call uses

Free tier

Included quota

Hobby and Pro both include 100,000 tool calls, 50,000 trigger events and 1 million sandbox LLM tokens a month free, with unlimited connected accounts on the customer's own OAuth app. Composio-managed shared apps count up to 20,000 of those tool calls and 10,000 trigger events. Pro adds a $29 monthly usage credit and unlimited team members.

What is public

Composio publishes a full rate card: plan allowances, per tool call and per trigger event rates, every add-on rate, the rates for its shared OAuth apps, per tool prices for Instant tools, and a feature comparison across Hobby, Pro and Enterprise. Enterprise itself is quoted.

Billing mechanics

Hobby stops at the included limits, so no charge is incurred unexpectedly. Pro adds a $29 monthly platform fee carrying $29 of usage credit, then meters tool calls and delivered trigger events, with per meter spend caps; add-ons charge per call when a call uses them. Instant tools bill provider charges from the Composio balance at no markup. Enterprise is quoted on committed volume with annual invoicing.

Cost watchouts

Several add-ons apply on Pro whenever a call uses them: running a tool outside a session, proxy execute, sandbox execution and shared connections each add a small per call charge past their free amounts, and Firewall costs $0.50 per million tokens evaluated. Security and compliance options (IP allowlist, a HIPAA BAA, zero data retention, advanced white labeling) are add-ons on Pro and included on Enterprise. Composio-managed shared OAuth apps carry lower allowances and higher rates, so production volume needs the customer's own OAuth app. The $29 usage credit expires each month.

Variable cost rationale

Two flat units, the tool call at $0.0003 and the delivered trigger event at $0.003, keep the bill linear with usage, and the Hobby plan pauses at its limits rather than billing over them. A heavy month rises with the add-ons a call happens to use (sandbox, proxy, direct execution, Firewall) and the security options switched on, and Pro has per meter spend caps to set a ceiling.

Additional watchouts

On Pro, the $29 of usage credit does not roll over, usage beyond the free amounts is metered per tool call and per trigger event, and add-ons such as sandbox execution, proxy execute and Firewall add small charges on the calls that use them.

Overage / add-ons

Past the free amounts on Pro: $0.0003 per tool call and $0.003 per delivered trigger event, plus any add-on that applies to a call. Connected accounts are unlimited and free with the customer's own app, and meta tools such as tool search are not billed. Hobby stops at its caps.

Sales call required

Mixed (some tiers require a call)

Free / trial

Hobby plan: 100,000 tool calls, 50,000 trigger events and 3 team members a month, hard capped, no card

Lowest paid plan

Pro, $29 a month including $29 of usage credit, then $0.0003 per tool call and $0.003 per trigger event

Commercial notes

Composio sells to developers building agents and to enterprises rolling agents out across a company, and also offers Composio For You, which connects assistants such as Claude, ChatGPT and Cursor to a person's own apps. It states SOC 2 Type II attestation and ISO 27001:2022 certification.

Key ambiguities

Enterprise pricing is custom. Customers who signed up before 15 August 2026 stay on their earlier pricing through 31 December 2026. Sandbox LLM tokens are billed only when Composio runs a model for the customer in the sandbox.

Missing data

Enterprise pricing is not published.

Agentic Index verified 2026-10-24

Alternatives to Composio

The closest documented capability profiles to Composio among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • OpenRouter10.5 / 14Adds documented Testing, Debugging & Optimization
  • TrueFoundry9.5 / 14Adds documented Testing, Debugging & Optimization
  • Deepgram7.5 / 14A lighter documented profile than Composio
  • Braintrust10.0 / 14Adds documented Prebuilt Agents, Templates & Packs and Testing, Debugging & Optimization
  • Helicone8.0 / 14Adds documented Testing, Debugging & Optimization
  • LangWatch10.0 / 14Adds documented Prebuilt Agents, Templates & Packs and 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

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.