# WildEdge > Inference observability for on-device and cloud AI. Collect telemetry from your app (Python, iOS / macOS, Android SDKs) or LLM gateway (LiteLLM, OpenRouter, Bifrost), then investigate it in WildEdge or with your AI agent over MCP. ## Table of Contents - [Changelog](https://docs.wildedge.dev/changelog.md): What has changed recently - [Connect ChatGPT or Claude](https://docs.wildedge.dev/mcp_web.md): Connect ChatGPT, Claude, or another OAuth-capable web agent to WildEdge through remote MCP. - [Connect Codex, Claude Code, or Gemini CLI](https://docs.wildedge.dev/mcp.md): Connect Claude Code, Codex, or Gemini CLI to create projects, investigate telemetry, and manage your team. - [Connect your AI agent](https://docs.wildedge.dev/connect-agent.md): Connect Codex, Claude Code, Gemini CLI, ChatGPT, or Claude to WildEdge through the remote MCP server, and point it at these docs. - [How WildEdge works](https://docs.wildedge.dev/concepts.md): The building blocks of WildEdge, from projects, keys, events, runs, and attachments to SQL charts, dashboards, datasets, and training export. - [Integration coverage](https://docs.wildedge.dev/integration-coverage.md): Automatic telemetry, manual tracking, captured content, and delivery behavior by collection path. - [Investigate events and traces](https://docs.wildedge.dev/investigate.md): Start from recent events, find a suspicious inference, and inspect the context that explains it, in WildEdge or with your AI agent. - [Quickstart: cloud API](https://docs.wildedge.dev/quickstart/cloud.md): Send your first inference event to WildEdge from an OpenAI call in about 2 minutes. Works with any OpenAI-compatible provider. - [Quickstart: on-device model](https://docs.wildedge.dev/quickstart/on-device.md): Send your first inference event to WildEdge from Python in about 5 minutes. Runs a small local model on CPU, no model API key needed. - [Set up app and gateway telemetry](https://docs.wildedge.dev/setup/sdk-and-gateway.md): Record on-device inference with an SDK and cloud calls through your LLM gateway without counting the same call twice. - [Set up app telemetry](https://docs.wildedge.dev/setup/sdk.md): Record inference calls in your application with the Python, iOS / macOS, or Android SDK, then confirm your first event arrives. - [Set up Bifrost](https://docs.wildedge.dev/gateways/bifrost.md): Send model calls from Bifrost to WildEdge with its otel plugin. - [Set up gateway telemetry](https://docs.wildedge.dev/llm-gateways.md): Send model calls from an LLM gateway to WildEdge over OpenTelemetry, from LiteLLM, OpenRouter or Bifrost. - [Set up LiteLLM](https://docs.wildedge.dev/gateways/litellm.md): Send model calls from the LiteLLM proxy to WildEdge over OpenTelemetry. - [Set up OpenRouter](https://docs.wildedge.dev/gateways/openrouter.md): Send model calls from OpenRouter to WildEdge with Broadcast. - [Telemetry reference](https://docs.wildedge.dev/telemetry.md): Accepted telemetry events, payload fields, types, units, and optional content. - [Troubleshooting guide](https://docs.wildedge.dev/what-we-collect.md): Choose telemetry for investigating failures, latency, cost, device issues, and model changes.