---
title: "Track local and on-device models in Agent Analytics"
description: "Track agents that run on local or on-device models, such as Ollama, LM Studio, or llama.cpp, in Agent Analytics with the AI SDK's manual tracking methods."
product: general
lang: en
token_estimate: 969
---
# Track local and on-device models in Agent Analytics

> For AI agents: a documentation index is available at [/docs/llms.txt](/docs/llms.txt). Append `.md` to any page URL for markdown, or send `Accept: text/markdown`.

Agents that run on a local or on-device model, such as Ollama, LM Studio, llama.cpp, or any inference server on `localhost`, reach Agent Analytics through the AI SDK's manual tracking methods. The AI SDK has no provider wrapper for local models, so you track each user message, tool call, and model response yourself. Sessions, built-in signals, and evaluators then work the same way as for hosted models.

## Set up with your AI coding agent (recommended)

Paste this prompt into your AI coding agent, such as Cursor, Claude Code, Windsurf, GitHub Copilot, or Codex. The agent installs the AI SDK, reads its bundled instructions, finds every model call, and instruments it.

#### Node

```text
Instrument this app with Amplitude Agent Analytics using the Node SDK. Our agent runs on a local model, so track each user message, tool call, and model response with the manual tracking methods, and pass a cost of 0 on each response.

Install the SDK:

npm install @amplitude/ai @amplitude/analytics-node

Then follow `node_modules/@amplitude/ai/amplitude-ai.md`.
```

#### Python

```text
Instrument this app with Amplitude Agent Analytics using the Python SDK. Our agent runs on a local model, so track each user message, tool call, and model response with the manual tracking methods, and pass a cost of 0 on each response.

Install the SDK:

python3 -m pip install amplitude-ai

Then run `amplitude-ai --print-guide` and follow the printed instrumentation guide.
```

Review the changes it proposes, then verify with the steps in [Verify](#verify).

## What this means for you

- **You call**: `trackUserMessage`, `trackToolCall`, and `trackAiMessage` (Node), or `track_user_message`, `track_tool_call`, and `track_ai_message` (Python), inside an agent session.
- **Cost**: Local models have no price, so pass a cost of `0` on every response. The response then records zero cost instead of a missing value.
- **Tokens**: Pass input and output token counts if your runtime reports them. They're optional.

## Track a local model

#### Node

```typescript
await agent.session({ userId, sessionId }).run(async (s) => {
  s.trackUserMessage(userInput);

  const start = Date.now();
  const response = await localModel.complete(prompt);
  const latencyMs = Date.now() - start;

  s.trackAiMessage(response.text, "llama-3.2-3b", "local", latencyMs, {
    inputTokens: response.usage?.inputTokens,
    outputTokens: response.usage?.outputTokens,
    totalCostUsd: 0,
  });
});
```

#### Python

```python
import time

with agent.session(user_id=user_id, session_id=session_id) as s:
    s.track_user_message(user_input)

    start = time.monotonic()
    response = local_model.complete(prompt)
    latency_ms = int((time.monotonic() - start) * 1000)

    s.track_ai_message(
        response.text, "llama-3.2-3b", "local", latency_ms,
        input_tokens=response.usage.input_tokens if response.usage else None,
        output_tokens=response.usage.output_tokens if response.usage else None,
        total_cost_usd=0,
    )
```

Track tool calls the same way with `trackToolCall` (Node) or `track_tool_call` (Python). For the full method signatures, refer to the [AI SDK reference](https://amplitude.com/docs/sdks/agent-analytics/sdk).

## Verify

Run `npx amplitude-ai doctor` (Node) or `amplitude-ai-doctor` (Python). On a local-model project, `doctor` reports `provider_dependency` because it finds no supported provider package. Expect and ignore that result for local models. Every other check still applies.

## Privacy

Local inference keeps prompts on your machine, but the AI SDK still sends message text to Amplitude, with PII redacted by default.