repowiserepowise
Sign in
composiohq/composio
OverviewDocsArchitectureKnowledge GraphFilesCode HealthSecurityRefactoring

People & History

CommitsContributorsDecisions
Chat
Stats
repowiserepowise
ExplorePricingDocs
Sign in
repowisecomposiohq/composio
CO
CO

composiohq / composio

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

TypeScript★ 30,366
Use in your agentAsk this codebase

github.com/composiohq/composio·Indexed at a1e7a6f·2d ago·Up to date with upstream

About this codebase

Composio gives AI agents 1000+ pre-authenticated toolkits by turning your inputs (a user session, authentication context, connected accounts, and an agent’s intent) into a runnable tool surface through a pipeline that includes session creation, toolkit selection, authentication + execution routing, and docs/runtime compatibility checks—ending in agent-ready tool calls and a published toolkit documentation experience. The repo is used by developers building production agents (via the TypeScript and Python SDKs), by teams integrating into their agent framework through Providers, and by operators using the `composio` CLI and sandboxed session workflows to connect accounts, restrict toolkits, and trigger executions.

Written by gpt-5.4-nano from the index

2,969 files and 13,189 symbols in 10 modules, led by TypeScript (1,390 files) and Python (234).

Start reading

  • Knowledge graph2,969 files and how they depend on each other.→
  • Agent Command SetDocumentationDocumentation for ts/packages/cli/src/commands/agent, written by gpt-5.4-nano.→
  • Build/sync Algolia index via first-party script (section-sized records) and avoid Algolia CrawlerDecisionProposed decision, from a pull request.→

Code health

7.7out of 10Good

This codebase scores 7.7 out of 10 for code health, which we rate good. It also scores maintainability 8.2 and static performance 9.9 out of 10. The three are scored separately and never blended into one number. Risk is concentrated, as it usually is: 286 of 2,969 files are git hotspots, and they average 6.6 — which is where the fixes pay off most.

Full health report →

Do next

1 thing worth doing in the week to Sep 30, the last indexed commit, 1 of them now.

Now

  • Critical

    Clean up what this week's commits left: 11 serious findings in 8 files

    7 commits in the last 7 days added or worsened them, and they are still open. Start with ts/packages/json-schema-to-zod/src/utils/unicode-pattern.ts, which has 2 critical.

    serious findings
    11
    critical
    2
    files
    8
    Medium effort

Improve what Repowise can see

  • Add a test coverage report

    Without one, Repowise cannot tell tested code from untested code, so every test-related action says “unknown”.

    line coverage
    Unknown, no report
    Small effort
All actions in the Overview →

Use composiohq/composio in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

https://api.repowise.dev/mcp/composiohq/composio

One command, run anywhere. Adds the server to your local Claude Code config.

Docs
bash
claude mcp add --transport http repowise https://api.repowise.dev/mcp/composiohq/composio \
  --header "Authorization: Bearer rw_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
The snippet shows a placeholder key. Generate one to get a copyable secret.
Sign in and create an API key to connect.Sign in

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is composio put together?")
  • get_why("why is composio structured this way?")

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.

Go deeper

  • OverviewEverything the index found, what changed this week, commits and decisions.→
  • DocumentationModule-by-module documentation, 1,830 pages, 68 written by a model.→
  • ArchitectureDependency graph, layers and third-party dependencies.→
  • Code healthEvery file's score, the findings behind it, tests and refactoring plans.→
  • CommitsEach commit's effect on code health, with agent provenance.→
  • ContributorsWho owns what, and where one person holds most of the knowledge.→
  • DecisionsArchitectural decisions mined from commits and pull requests.→
  • Ask this codebaseSign inGrounded answers over the indexed code.→

For maintainers

Add a badge to your README

Both badges are public, cached, and update on their own after every index. Nothing to install.

Repowise badge

Links to this page. Adding it also re-indexes the repo every week.

Repowise badge: explore code
[![repowise](https://api.repowise.dev/badge/wiki/composiohq/composio.svg)](https://repowise.dev/repo/composiohq/composio)

Code health badge

Average health across every file, straight from the latest index.

Code health badge showing the average health score out of 10
[![Code health](https://api.repowise.dev/badge/health/composiohq/composio.svg)](https://repowise.dev/repo/composiohq/composio)

How composiohq/composio works

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action. This page is a map of the composiohq/composio repository, written primarily in TypeScript, rebuilt from the source each time it is indexed. Repowise parses every symbol, computes a dependency graph, scores per-file code health from complexity, duplication, test coverage and churn, mines git history for hotspots and ownership, and lifts the architectural decisions into documentation you can read here or query through MCP.

The codebase has 2,969 files and 13,189 symbols in 10 modules, led by TypeScript, Python and JavaScript. Code health is 7.7 out of 10, rated good.

Use the links above to open each view, or connect this repository to your agent for grounded answers inside Claude, Cursor, Codex or VS Code.