Labs / Time machine / Composio
Composio
The subprocessor list as we last read it, on Nov 20, 2026.
Dates are when we read the list (UTC), not when Composio changed it. Between two readings we don't know what it said.
tall: list changed · medium: document changed · short: read, no change · x: check failed · dotted: change dates only. Tap a tick or use the date box.
We record change dates, not every check, before Oct 11, 2026.
We have published no changes to this vendor's list; our first reading was Oct 3, 2026.
Read Nov 20, 2026 · 8 companies named as a subprocessor · stored document
| Name | Purpose | Location | First read |
|---|---|---|---|
| Amazon Web Services | Cloud infrastructure; Hosts and processes customer request data across AWS cloud infrastructure, including ECS Fargate, Lambda, RDS, S3, Secrets Manager, KMS, and related networking/security services. | us-east-1 N Virginia | |
| ClickHouse | Stores trigger logs, delivery callbacks, tool/metering usage logs. | Stores logs and activity | |
| Cloudflare | Workers to delivers trigger payloads to customer webhooks; file upload relay downloads third-party files and writes them to R2 storage. | DNS and Workers | |
| E2B | Provides isolated cloud sandboxes for executing customer-requested Python/bash workflows and processing temporary files/artifacts during Tool Router Workbench sessions. | Workbench Sessions | |
| OpenAI AI | Processes prompts, reranking inputs, and embeddings where OpenAI models are selected or routed. We've *Disabled* sharing data for improving models and training on our data. | LLM inferences | |
| OpenRouter AI | Provides an API gateway for accessing third-party AI models and managing usage. When Composio sends prompts through OpenRouter, OpenRouter routes those requests to the selected model provider, which may also process the content. All requests are sent with `zdr: true` | AI model access and inference routing | |
| Pusher | Realtime trigger delivery to SDK/CLI channels; receives trigger event payloads. | Real time Trigger delivery | |
| Vercel | Backend processes all API requests via Vercel hosted service. Additionally, Vercel AI routes selected AI SDK model calls to configured model providers for workbench/runtime flows. We've enabled ZDR on Vercel. | Serves APIs, Vercel AI for LLM routing |
Built from the changes we published; changes we recorded without an alert (parser fixes, entries approved after review) don't appear. Where we later improved how we read a list, an earlier list may look different from the vendor's page at the time.
Gaps in our readings
- to · 1 day · newer reading being checked
All readings (43)
History starts Oct 3, 2026. Dates are UTC. Data CC BY 4.0. Shown as stored when this page was built.