zeke-john/codecall

An Open Source Typescript implementation of Programmatic Tool Calling for AI Agents (Based on Code Mode)

34
/ 100
Emerging

This project helps AI agent developers create more efficient and powerful AI agents. Instead of traditional methods that clutter the agent's memory with every tool definition and execute tasks one by one, Codecall allows agents to write and run code to orchestrate multiple tools programmatically. This results in faster, more accurate task completion with significantly less computational overhead. An AI agent developer looking to build or optimize complex AI applications with many tools would use this.

Use this if you are developing AI agents that interact with many tools and you want to reduce token usage, speed up execution, and improve accuracy by enabling programmatic tool orchestration.

Not ideal if you are working with simple AI agents that use only a few tools and do not require complex, multi-step programmatic interactions.

AI-agent-development large-language-models AI-tool-orchestration AI-workflow-optimization agent-architecture
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 13 / 25
Community 5 / 25

How are scores calculated?

Stars

17

Forks

1

Language

TypeScript

License

MIT

Last pushed

Jan 31, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/zeke-john/codecall"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.