Snapshot 35863
Normalized text
Scripts and page chrome removed; this is what change detection compares.
Skip to navigationSkip to main content Composio Composio.dev is your AI-powered conductor, orchestrating seamless SaaS integrations with agents as instruments and MCP as the score. From Slack to Salesforce, every service plays in sync—no more messy solos of auth or APIs. Let AI agents handle the backend while your app hits every note, fast and flawlessly. [email protected] Privacy PolicyOpens in new tab Subprocessors Amazon Web Services • Cloud infrastructure us-east-1 N Virginia Hosts and processes customer request data across AWS cloud infrastructure, including ECS Fargate, Lambda, RDS, S3, Secrets Manager, KMS, and related networking/security services. Cloudflare • DNS and Workers Workers to delivers trigger payloads to customer webhooks; file upload relay downloads third-party files and writes them to R2 storage. Vercel • Serves APIs, Vercel AI for LLM routing 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. OpenAI • LLM inferences 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. E2B • Workbench Sessions Provides isolated cloud sandboxes for executing customer-requested Python/bash workflows and processing temporary files/artifacts during Tool Router Workbench sessions. Pusher • Real time Trigger delivery Realtime trigger delivery to SDK/CLI channels; receives trigger event payloads. ClickHouse • Stores logs and activity Stores trigger logs, delivery callbacks, tool/metering usage logs. OpenRouter • AI model access and inference routing 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 1-8 of 8 results Showresults per page All subprocessors Amazon Web Services Hosts and processes customer request data across AWS cloud infrastructure, including ECS Fargate, Lambda, RDS, S3, Secrets Manager, KMS, and related networking/security services. Cloud infrastructure us-east-1 N Virginia aws.amazon.com 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 https://www.cloudflare.com 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 vercel.com OpenAI 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 https://openai.com E2B Provides isolated cloud sandboxes for executing customer-requested Python/bash workflows and processing temporary files/artifacts during Tool Router Workbench sessions. Workbench Sessions e2b.dev Pusher Realtime trigger delivery to SDK/CLI channels; receives trigger event payloads. Real time Trigger delivery pusher.com ClickHouse Stores trigger logs, delivery callbacks, tool/metering usage logs. Stores logs and activity clickhouse.com OpenRouter 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 openrouter.ai