Hugging Face on Future AGI
LLM Providers
Hugging Face Inference and Inference Endpoints across thousands of models.
What you get
Everything traced, scored, and improvable
One install instruments Hugging Face on OpenTelemetry. Future AGI then layers evaluators, optimisers, and simulations on top of the same trace tree — no second SDK, no double instrumentation.
Trace
Auto-instrumented spans
Every Hugging Face call becomes a span — inputs, outputs, latency, tokens, cost, model name, tool args, retrieval results, and chain steps captured automatically.
Evaluate
70+ evaluators on every span
Attach Groundedness, Context Relevance, Prompt Injection, Toxicity, and 70+ more — purpose-built scorers powered by the Turing eval models, not generic LLM-as-judge.
Optimize
Closed-loop improvement
Pipe failed traces into agent-opt: GEPA, PromptWizard, ProTeGi, and Bayesian search rewrite your prompts with proof of measured gains.
Simulate
Adversarial scenarios at scale
Generate hundreds of personas and run them through your Hugging Face agent before launch — text and voice, scripted or persona-driven.
Quickstart · <3 min
Instrument Hugging Face in three steps
-
Step 1
Install the traceAI package
One package per language, ships from PyPI, npm, and Maven Central.
-
Step 2
Register the trace provider
Set
FI_API_KEYandFI_SECRET_KEY, then callHuggingFaceInstrumentor().instrument(). -
Step 3
Run your existing Hugging Face app
No code changes. Traces appear in the Future AGI dashboard within seconds.
Install
pip install traceAI-huggingfaceInstrument
from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType
from traceai_huggingface import HuggingFaceInstrumentor
trace_provider = register(
project_type=ProjectType.OBSERVE,
project_name="HUGGINGFACE_APP",
)
HuggingFaceInstrumentor().instrument(tracer_provider=trace_provider)
# Your existing Hugging Face code runs unchanged from here.
# Every call is now an OpenTelemetry span in Future AGI.Pick a recipe
What do you want to do with Hugging Face?
Each recipe is a copy-paste page with the exact code, the gotchas, and a working example you can clone.
Recipes for Hugging Face
Adjacent integrations
Other llm providers
OpenAI
GPT-4o, GPT-5, o-series, and the OpenAI Responses API.
Anthropic
Claude Opus, Sonnet, and Haiku via the Anthropic Messages API.
Google GenAI
Gemini 2.x via the Google GenAI SDK (Vertex + AI Studio).
Cohere
Command, Embed, and Rerank via the Cohere API.