botanu-ai

botanu-ai / botanu-sdk-python

Public

SDK to track cost-per-outcome for AI workflows

ai-ops cloud-cost-efficiency cost-optimization enterprise-solutions finops
14
1
100% credibility
Found Feb 09, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A Python library that groups AI workflow operations into trackable 'runs' for precise per-transaction cost attribution using distributed tracing.

How It Works

1
🔍 Discover Botanu

You hear about Botanu, a helpful tool that tracks spending on AI conversations across your entire app without missing a thing.

2
📦 Add to your project

You easily include Botanu in your Python setup so it can start watching your AI work.

3
✅ Switch it on

With one quick call, you activate tracking everywhere in your app, connecting all the pieces.

4
🏷️ Tag key moments

You mark the start of important tasks like handling customer chats so costs link to real business actions.

5
📡 Link to your dashboard

You point it to your monitoring spot where all the insights will flow automatically.

6
🚀 Run your AI flows

Your app runs normally, but now every AI call, lookup, and step gets grouped and measured perfectly.

📈 See clear cost insights

You get exact breakdowns of spending per customer interaction, spotting savings and understanding value instantly.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 14 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is botanu-sdk-python?

Botanu is an OpenTelemetry-native Python SDK that delivers run-level cost attribution for AI workflows. It layers stable run IDs over distributed traces, tying costs across LLM calls, databases, and services to single business transactions like user requests—without sampling losses. Install with pip install botanu, call enable() once per service, and decorate entry points with @botanu_use_case for instant tracking.

Why is it gaining traction?

Unlike basic tracing tools, Botanu auto-instruments 50+ libraries out of the box—OpenAI, Anthropic, LangChain, FastAPI, PostgreSQL, Celery—requiring zero manual spans. Intermediate services just need enable() to propagate context via W3C baggage, scaling to Kubernetes clusters with minimal changes. All config happens via env vars like OTEL_EXPORTER_OTLP_ENDPOINT, exporting to any OTel collector for PII-safe analysis.

Who should use this?

AI engineers chaining LLM providers with databases and queues in multi-service apps. Teams tracking per-workflow costs for ROI dashboards, especially in production FastAPI or Celery setups. Observability pros extending OpenTelemetry for business attribution without custom agents.

Verdict

Promising alpha for OTel shops needing run-level cost tracking, with solid docs and pre-commit hygiene, but only 10 stars and 1.0% credibility signal early days—test in staging first. Pair with a collector for real value.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.