Maniac: Continually optimizing models from your LLM telemetry and evals.

Maniac is an enterprise AI platform that makes it easy to replace existing LLM API calls with fine-tuned, task-specific models. Drop in Maniac with one line of code to:

• Capture and structure production LLM traffic
• Automatically fine-tune and evaluate Small Language Models (SLMs) on your tasks
• Replace over-generalized LLM calls with higher performance, lower latency models built for just what you need
• Focus engineering time where it matters most: building and refining high-quality model evaluations—not managing infrastructure, hyperparameters, or bespoke fine-tuning pipelines

All with virtually no changes to your existing codebase.

Getting started

1

Sign up for Maniac

Head over to https://app.maniac.ai/auth/register

2

Grab your API key

From Project Settings or on the Containers page.

3

Set the environment variable

export MANIAC_API_KEY=your-api-key

---

Dropping Maniac into your Codebase

For an agentic setup, copy this prompt and give it to your preferred coding agent:

Fetch and follow https://raw.githubusercontent.com/ManiacIncorporated/sb-monorepo/main/docs/gitbook/agent-setup.md to instrument this repo for Maniac telemetry.

Install the library

Python

pip install maniac

TypeScript

npm install maniac-js

Initialize client

Python

from maniac import Maniac

maniac = Maniac(api_key="your-maniac-api-key")

TypeScript

import Maniac from "maniac-js";

const maniac = new Maniac();

Create a container

Containers log inference and automatically build datasets for fine-tuning and evaluation. initial_model sets the model used in that container until a Maniac model is deployed in its place.

Python

container = maniac.containers.create(
  label = "my-container",
  default_system_prompt = "You are a helpful math tutor.",
  initial_model = "openai/gpt-5.2"
)

TypeScript

const container = await maniac.containers.create({
  label: "my-container",
  initial_model: "openai/gpt-5.2",
});

Log Completions

Now that you've made a container, let's add some data to it. Note that the inputs and outputs of items are both required to be in openai chat completions format. The output field is not required.

Python

response = maniac.chat.completions.register(
    container = "my-container",
    items = [{
        "input": {
            "messages": [{"role": "user", "content": "Hello!"}]
        },
        "output": {
            "choices": [{
                "message": [{"role": "assistant", "content": "Hello! How can I help?"}]
            }]
        }
    }]
)

TypeScript

await maniac.chat.completions.register({
  container: "my-container",
  items: [{
    input: {
      messages: [{ role: "user", content: "Hello!" }],
    },
    output: {
      choices: [{
        message: { role: "assistant", content: "Hello! How can I help?" },
      }],
    },
  }],
});

---

Optimizing your model

The inference logs in your container now serve as training data for a new SLM—fully yours, lower latency, most cost effective, and optimized specifically for your task.

1

Create an Eval

Evaluations define the optimization target. They can be implemented as arbitrary code or defined using judge prompts.

From the Evals tab inside a container, Add Eval.

Judge Eval

Code Eval

2

Optimization happens automatically

Once your telemetry hooks and evals are in place, Maniac automatically optimizes a model for your task — no manual configuration required.

---

Deploy.

Optimized models can be be deployed into a container from the Models tab. Once deployed, you can chat with your generated models, and inference requests are now routed through the Maniac model instead of the initial_model.

Need help?

📧 Email us at [e-mail]

We'll get back to you within a day.