> ## Documentation Index
> Fetch the complete documentation index at: https://futureagi.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Introducing Agent Compass

<iframe className="w-full aspect-video rounded-xl" src="https://www.youtube.com/embed/p-bFSq3AEkI?si=GyW3p4VMRSDZUgOP" title="YouTube video player" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerPolicy="strict-origin-when-cross-origin" allowFullScreen />

import { Card, CardGroup } from 'nextra-theme-docs'

**Agent Compass** is an intelligent error analysis system that points AI agent development teams in the right direction. It is capable of automatically identifying issues, group similar ones, learning from mistakes, and providing actionable guidance. Developers can leverage this system to course-correct by identifying what's going wrong and how to fix it.

<img src="https://mintcdn.com/futureagi/5B_nmxyNsAFUDMA3/product/agent-compass/agent_compass_trace.png?fit=max&auto=format&n=5B_nmxyNsAFUDMA3&q=85&s=a6198018eb96daefd244d4c55ca1b497" alt="Agent compass overview" width="1263" height="549" data-path="product/agent-compass/agent_compass_trace.png" />

## What does agent compass do?

* **Error Detection & Direction**: Automatically identifies and categorizes errors in agent execution, points out possible root causes and immediate fixes
* **Learning-Based Recommendations**: Uses episodic memory from past agent runs and semantic memory from error patterns to recommend better solutions in future
* **Comprehensive Issue Tracking**: Stores analysis results, error patterns, and improvement insights to track development progress over time
* **Pattern-Based Guidance**: Automatically detects recurring problems in agent behavior and provides confidence-scored recommendations for resolution
* **Development Intelligence**: Delivers detailed statistics and real-time insights that helps you understand where your agents are failing and how to improve

## Supported Integrations

The following integrations are currently supported

## LLM Models

<CardGroup cols={2}>
  <Card title="OpenAI" href="/future-agi/integrations/openai" />

  <Card title="OpenAI Agents SDK" href="/future-agi/integrations/openai_agents" />

  <Card title="Vertex AI (Gemini)" href="/future-agi/integrations/vertexai" />

  <Card title="AWS Bedrock" href="/future-agi/integrations/bedrock" />

  <Card title="Mistral AI" href="/future-agi/integrations/mistralai" />

  <Card title="Anthropic" href="/future-agi/integrations/anthropic" />

  <Card title="Groq" href="/future-agi/integrations/groq" />

  <Card title="Together AI" href="/future-agi/integrations/togetherai" />

  <Card title="Google ADK" href="/future-agi/integrations/google_adk" />

  <Card title="Google GenAI" href="/future-agi/integrations/google_genai" />

  <Card title="Portkey ADK" href="/future-agi/integrations/portkey" />
</CardGroup>

## Orchestration Frameworks

<CardGroup cols={2}>
  <Card title="LlamaIndex" href="/future-agi/integrations/llamaindex" />

  <Card title="LlamaIndex Workflows" href="/future-agi/integrations/llamaindex-workflows" />

  <Card title="Langchain" href="/future-agi/integrations/langchain" />

  <Card title="LangGraph" href="/future-agi/integrations/langgraph" />

  <Card title="LiteLLM" href="/future-agi/integrations/litellm" />

  <Card title="CrewAI" href="/future-agi/integrations/crewai" />

  <Card title="Haystack" href="/future-agi/integrations/haystack" />

  <Card title="Autogen" href="/future-agi/integrations/autogen" />

  <Card title="PromptFlow" href="/future-agi/integrations/promptflow" />

  <Card title="Vercel" href="/future-agi/integrations/vercel" />

  <Card title="Pipecat" href="/future-agi/integrations/pipecat" />
</CardGroup>

## Other

<CardGroup cols={2}>
  <Card title="DSPY" href="/future-agi/integrations/dspy" />

  <Card title="Guardrails AI" href="/future-agi/integrations/guardrails" />

  <Card title="Hugging Face smolagents" href="/future-agi/integrations/smol_agents" />

  <Card title="Ollama" href="/future-agi/integrations/ollama" />

  <Card title="Instructor" href="/future-agi/integrations/instructor" />

  <Card title="MCP" href="/integrations/mcp" />
</CardGroup>

## Configuring agent compass

You need absolutely **zero** configuration for using Agent Compass in your observe projects. Once you start sending traces to FutureAGI, the compass picks traces according to the [sampling rate](/future-agi/products/agent-compass/quickstart#sampling-rate) and generates meaningful insights

The next section exhibits a walkthrough on setting up an observe project using the [Google ADK integration](/future-agi/integrations/google_adk) to get insights from Agent Compass
