Code action agent with local execution sandbox and first-class support for programmatic tool calling
-
Updated
Jan 6, 2026 - Python
Code action agent with local execution sandbox and first-class support for programmatic tool calling
Python code execution sandbox with programmatic MCP tool calling (PTC)
An Open Source Typescript implementation of Programmatic Tool Calling for AI Agents (Based on Code Mode)
⚡ Cut LLM inference costs 80% with Programmatic Tool Calling. Instead of N tool call round-trips, generate JavaScript to orchestrate tools in Vercel Sandbox. Supports Anthropic, OpenAI, 100+ models via AI Gateway. Novel MCP Bridge for external service integration.
A minimal kernel for agentic systems. Runtime-first architecture for programmatic tool execution. Inspired by Anthropic's Code Execution with MCP.
🤖 Optimize LLM usage by streamlining tool calls with code generation and sandbox execution for reduced costs and latency in any model.
Add a description, image, and links to the programmatic-tool-calling topic page so that developers can more easily learn about it.
To associate your repository with the programmatic-tool-calling topic, visit your repo's landing page and select "manage topics."