Composio vs LiteLLM
Composio (Composio) and LiteLLM (BerriAI) side by side on public data, as of Oct 9, 2026.
LiteLLM has 13.5x the weekly package downloads of Composio (23.1M against 1.7M). LiteLLM has 2.0x the GitHub stars of Composio (60.4K against 30.5K).
Side-by-side numbers
| Metric | Composio | LiteLLM |
|---|---|---|
| Gid Score | 55 | 73 |
| Overall rank | #34 | #8 |
| Downloads, last 7 days | 1.7M | 23.1M |
| Downloads, 7-day change | up 8.4% | up 1.8% |
| Downloads, 30-day change | up 33.7% | — |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 30.5K | 60.4K |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 2 | 37 |
| Latest stable release | 0.13.0 · 10d ago | 1.104.2 · yesterday |
| Stable releases, 90 days | ||
| Terminal-Bench (best run) | — | — |
| Price | Free + $29/mo | Free (OSS) |
| License | MIT | MIT (enterprise features under a separate licence) |
| First released | — | — |
| Interfaces | Python SDK, TypeScript SDK, MCP server | Python library, Proxy server, REST API |
| Models |
Trends
Composio
Connects AI agents to 1,000+ apps and APIs with managed authentication, tool search and a sandboxed workbench, so agents can take actions in tools like GitHub, Slack and Gmail.
Pricing: Hobby is free. Pro is $29 a month with $29 of usage included; Enterprise is custom.
Latest release 0.13.0:
- cdabe06: Allow the Google and Cloudflare providers' executeToolCall and the OpenAI Responses provider's handleResponse to execute through a supplied Tool Router session, matching the other…
LiteLLM
An AI gateway and Python SDK that calls 100+ model APIs through one OpenAI-style interface, with spend tracking, budgets, rate limits, fallbacks, guardrails and logging.
Pricing: The SDK and proxy are open source and free. An enterprise edition with SSO, audit logs and support is sold separately.
Latest release 1.104.2:
- The cosign claims were validated
- The signatures were verified against the specified public key
- feat(decisions): backport /v1/systemone, OpenAI-format /v1/decisions and the OpenAI Decisions provider to stable/1.104.x for v1.104.2 (#44236, #45184,