tracellm 0.1.0

Local-first observability for LLM applications

tracellm

Lightweight tracing for LLM applications. One import, three calls — every API interaction logged locally, queryable from your terminal.

No backend. No signup. Nothing leaves your machine.

Install

pip install tracellm

Usage

from tracellm import Tracer

tracer = Tracer() tracer.start_trace(model="llama-3.1-8b-instant", prompt="your prompt")

try: response = client.chat.completions.create(...) tracer.end_trace(response) except Exception as e: tracer.record_error(type(e).name, str(e))

Query traces from terminal

python -m tracellm.cli --Status failed python -m tracellm.cli --Latency 2.0 python -m tracellm.cli --Model llama-3.1-8b-instant python -m tracellm.cli --Status failed --Latency 1.5

What gets captured

• Model, prompt, response
• Tokens used, latency, finish reason
• Error type and message on failures
• Timestamp for every call

Limitations

Storage is append-only JSON lines. Query supports >=
for latency, exact match for everything else. Early days.

Roadmap

• Binary storage for faster querying at scale
• Cost calculation per model
• Terminal dashboard