SDKs

Future AGI is a set of packages that evaluate LLM outputs, trace calls across your stack, optimize prompts, and load-test voice agents. Install what you need, skip what you don’t.

Language Support

Quickstart

pip install ai-evaluation

export FI_API_KEY="your-api-key"
export FI_SECRET_KEY="your-secret-key"

from fi.evals import evaluate

# Local metric — no API key needed
result = evaluate("contains", output="Hello world", keyword="Hello")
print(result.score)    # 1.0
print(result.passed)   # True

# Cloud metric — needs FI_API_KEY and FI_SECRET_KEY
result = evaluate("toxicity", output="Hello world", model="turing_flash")
print(result.score)    # 1.0
print(result.passed)   # True

pip install fi-instrumentation-otel traceai-openai

npm install @future-agi/ai-evaluation

export FI_API_KEY="your-api-key"
export FI_SECRET_KEY="your-secret-key"

import { Evaluator, Tone } from "@future-agi/ai-evaluation";

const evaluator = new Evaluator();

const result = await evaluator.evaluate({
  evalTemplates: [new Tone()],
  inputs: [{
    query: "Write a professional email",
    response: "Dear Sir/Madam, I hope this message finds you well..."
  }],
  modelName: "turing_flash"
});

console.log(result);

npm install @traceai/fi-core @traceai/openai

<!-- Maven — add the JitPack repository -->
<repository>
    <id>jitpack.io</id>
    <url>https://jitpack.io</url>
</repository>

<dependency>
    <groupId>com.github.future-agi.traceAI</groupId>
    <artifactId>traceai-java-openai</artifactId>
    <version>LATEST</version>
</dependency>

dotnet add package fi-instrumentation-otel

pip install ai-evaluation

Packages

Python

Six packages, each installable independently:

futureagi                    ← standalone base layer
  └── ai-evaluation          ← installs futureagi automatically
        └── agent-opt        ← installs ai-evaluation automatically

fi-instrumentation-otel      ← standalone tracing layer
  ├── traceai-*              ← each installs fi-instrumentation-otel
  └── agent-simulate         ← installs fi-instrumentation-otel

TypeScript

Java and C#

Tracing only. Java has 25+ instrumentors (Maven via JitPack, group ID com.github.future-agi.traceAI). C# has a single NuGet package (fi-instrumentation-otel). See the Tracing reference for details.

Evaluations — ai-evaluation

76+ local metrics for things like tone, hallucination, bias, and factual accuracy. Also includes guardrails (toxicity, PII, prompt injection) that run in under 10ms.

Available in Python and TypeScript.

Tracing — fi-instrumentation-otel + traceai-*

Install the core library plus one instrumentor per framework. LLM calls, retrieval steps, and agent actions get traced and sent to your Future AGI dashboard.

Available in Python, TypeScript, Java, and C#.

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType

trace_provider = register(
    project_name="my-project",
    project_type=ProjectType.OBSERVE,
)

from traceai_openai import OpenAIInstrumentor
OpenAIInstrumentor().instrument(tracer_provider=trace_provider)

# All OpenAI calls are now traced
# Traces appear in your Future AGI dashboard under "my-project"

Core SDK — futureagi

Datasets, prompt versioning, and knowledge bases. If you installed ai-evaluation, you already have this.

Available in Python and TypeScript.

Prompt Optimization — agent-opt

Six optimization algorithms: Random Search, Bayesian, ProTeGi, Meta-Prompt, PromptWizard, and GEPA. Each uses eval metrics to score prompt variants and find the best one.

Python only.

pip install agent-opt

Simulation Testing — agent-simulate

Run simulated conversations against your voice AI agents using configurable personas. Captures audio, transcripts, and eval scores.

Python only.

pip install agent-simulate

Next Steps