Launching AgentCost

Source: Dev.to

The Problem

Last month, my LangChain agent cost me $800 in OpenAI fees.
I had no idea which agent was expensive or where to optimize — I was flying blind.

The Solution

I built AgentCost, an open‑source tool that tracks every LLM call your agents make.

How It Works

AgentCost works by intercepting LangChain’s LLM calls using Python’s monkey‑patching.

Architecture

Three components:

• Python SDK – intercepts calls
• FastAPI backend – stores data
• React dashboard – visualizes costs

Results

After using AgentCost for 2 weeks:

• Identified that my Router Agent was called 10× more than needed
• Switched simple queries to GPT‑3.5 instead of GPT‑4
• Reduced costs from $800/month to $450/month (44 % savings)

Technical Challenges

Monkey patching without breaking user code

How I solved: …

Accurate token counting

The challenge: Different models use different tokenizers…

Batching for performance

The solution: Hybrid batching (size + time‑based)…

Try It Yourself

AgentCost is open source and free to use:

• GitHub:
• Docs:

pip install agentcost

What’s Next

• Cost alerts (Slack/email when a threshold is hit)
• Automatic optimization suggestions
• OpenAI and Anthropic SDK support

Feedback Welcome

If you try AgentCost, I’d love to hear your thoughts!

• Twitter: @KushagraA15
• GitHub: