79 integrations · all systems nominal

Trace, evaluate, optimise,
and simulate any AI stack

Future AGI ships open-source traceAI instrumentation for every framework, model provider, vector database, and voice stack you'd use in production. One .instrument() call and every LLM call, tool use, retrieval, and chain step becomes an OpenTelemetry span — with attached evaluators, optimisers, and simulations on the same trace.

Total
79

integrations

Python
69

packages

TypeScript
62

packages

Java
23

packages

▸ Most popular

Featured integrations

The frameworks most teams instrument first.

▸ LLM Providers

LLM Providers

Frontier and open-weight model APIs you can call directly.

OpenAI logo
Py TS Java

OpenAI

GPT-4o, GPT-5, o-series, and the OpenAI Responses API.

trace evaluate optimize simulate
Anthropic logo
Py TS Java

Anthropic

Claude Opus, Sonnet, and Haiku via the Anthropic Messages API.

trace evaluate optimize simulate
Google GenAI logo
Py TS Java

Google GenAI

Gemini 2.x via the Google GenAI SDK (Vertex + AI Studio).

trace evaluate optimize simulate
Cohere logo
Py TS Java

Cohere

Command, Embed, and Rerank via the Cohere API.

trace evaluate optimize
Mistral logo
Py TS

Mistral

Mistral Large, Codestral, and open-weight Mistral / Mixtral.

trace evaluate optimize
Groq logo
Py TS

Groq

LPU inference for Llama, Mixtral, and Qwen at sub-second latency.

trace evaluate optimize
Together AI logo
Py TS

Together AI

Hosted open-weight LLMs with serverless and dedicated endpoints.

trace evaluate optimize
Fireworks AI logo
Py TS

Fireworks AI

FireFunction, Llama, and Mixtral with function-calling.

trace evaluate optimize
DeepSeek logo
Py TS

DeepSeek

DeepSeek V3 and R1 reasoning models via the OpenAI-compatible API.

trace evaluate optimize
xAI Grok logo
Py TS

xAI Grok

Grok 2/3 models via the xAI OpenAI-compatible API.

trace evaluate optimize
Cerebras logo
Py TS

Cerebras

Wafer-scale inference for Llama and Qwen models.

trace evaluate optimize
Ollama logo
Py TS Java

Ollama

Local Llama, Mistral, and Qwen via the Ollama runtime.

trace evaluate
Hugging Face logo
Py TS

Hugging Face

Hugging Face Inference and Inference Endpoints across thousands of models.

trace evaluate
vLLM logo
Py TS

vLLM

High-throughput open-source LLM serving with PagedAttention.

trace evaluate
Perplexity logo
Py TS

Perplexity

Perplexity Sonar online + offline models with citations.

trace evaluate
DeepInfra logo
Py TS

DeepInfra

Serverless inference for Llama, Mistral, and Qwen at GPU prices.

trace evaluate
Anyscale logo
Py TS

Anyscale

Anyscale Endpoints for hosted open-source models.

trace evaluate
Hyperbolic logo
Py TS

Hyperbolic

Decentralized GPU inference for Llama, Qwen, and DeepSeek.

trace evaluate
Novita AI logo
Py TS

Novita AI

Serverless inference for Llama, Mistral, and Qwen models.

trace evaluate
Nebius AI Studio logo
Py TS

Nebius AI Studio

European GPU inference platform for open-source LLMs.

trace evaluate
SambaNova logo
Py TS

SambaNova

Reconfigurable Dataflow Units for high-throughput Llama inference.

trace evaluate
Lambda Inference logo
Py TS

Lambda Inference

Lambda's serverless inference API for open-weight LLMs.

trace evaluate
GitHub Models logo
Py TS

GitHub Models

Free-tier model playground from GitHub for prototyping.

trace evaluate
Moonshot AI (Kimi) logo
Py TS

Moonshot AI (Kimi)

Moonshot Kimi K1.5 / K2 long-context reasoning models.

trace evaluate
ZhipuAI / Z.AI logo
Py TS

ZhipuAI / Z.AI

GLM-4 frontier models from Zhipu / Z.AI.

trace evaluate
MiniMax logo
Py TS

MiniMax

MiniMax abab and Hailuo models for chat and reasoning.

trace evaluate
Voyage AI logo
Py TS

Voyage AI

Domain-specific embeddings and reranker from Voyage AI.

trace evaluate
Jina AI logo
Py TS

Jina AI

Jina embeddings, reranker, and reader API.

trace evaluate

▸ Agent Frameworks

Agent Frameworks

Multi-step orchestration libraries for tool-using agents.

LangChain logo
Py TS

LangChain

Chains, agents, and LCEL pipelines with auto-traced spans for every step.

trace evaluate optimize simulate
LangChain4j logo
Java

LangChain4j

Java-native chains, agents, and RAG with LangChain4j.

trace evaluate
DSPy logo
Py

DSPy

Declarative LLM programs with optimisable signatures and modules.

trace evaluate optimize
CrewAI logo
Py

CrewAI

Role-based multi-agent crews with task plans and tool use.

trace evaluate simulate
AutoGen logo
Py

AutoGen

Microsoft's multi-agent conversation framework.

trace evaluate simulate
Agno logo
Py

Agno

Lightweight Python agent framework with built-in memory and tools.

trace evaluate
smolagents logo
Py

smolagents

Hugging Face's tiny agent framework with code agents and tool calling.

trace evaluate
Pydantic AI logo
Py

Pydantic AI

Type-safe agents with Pydantic models for inputs, outputs, and tools.

trace evaluate
OpenAI Agents SDK logo
Py TS

OpenAI Agents SDK

OpenAI's official agent runtime with handoffs, guardrails, and tracing.

trace evaluate optimize simulate
Google ADK logo
Py TS

Google ADK

Google Agent Development Kit for Vertex-hosted multi-agent systems.

trace evaluate simulate
Claude Agent SDK logo
Py

Claude Agent SDK

Anthropic's Agent SDK for Claude with code execution and computer use.

trace evaluate
Strands Agents logo
Py TS

Strands Agents

AWS Strands SDK for Bedrock-backed agents and workflows.

trace evaluate
BeeAI logo
Py TS

BeeAI

IBM BeeAI framework for tool-using agents with streaming and memory.

trace evaluate
Instructor logo
Py TS

Instructor

Structured outputs from LLMs using Pydantic and Zod schemas.

trace evaluate
Mastra logo
TS

Mastra

TypeScript-first agent framework with workflows, memory, and RAG.

trace evaluate
Vercel AI SDK logo
TS

Vercel AI SDK

Vercel AI SDK for streaming chat, generation, and tools in Next.js.

trace evaluate
Spring AI logo
Java

Spring AI

Spring framework integration for chat models, embeddings, and RAG in Java.

trace evaluate
Spring Boot Starter logo
Java

Spring Boot Starter

Auto-configuration starter for tracing Spring Boot AI apps in seconds.

trace
Semantic Kernel logo
Java

Semantic Kernel

Microsoft's SDK for plugins, planners, and Skill orchestration.

trace evaluate
LangGraph logo
Py TS

LangGraph

Stateful multi-actor orchestration on top of LangChain.

trace evaluate optimize simulate

▸ Guardrails & Safety

Guardrails & Safety

Input/output validation libraries that wrap LLM calls.

▸ Mission control

Don't see your stack?

traceAI is OpenTelemetry-native, so any OTel exporter works today. For first-class support, vote on an open GitHub issue or open a new one — most integrations land in under a week.