Agent harness and CLI tool that acts and self-improves via code actions
-
Updated
Mar 7, 2026 - Python
Agent harness and CLI tool that acts and self-improves via code actions
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.
Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and self-growing tool libraries. Compare 3 sandbox backends: Docker (OpenSandbox), MicroVM, and in-process AST.
Programmatic tool calling / Code Mode for MCP — turn any OpenAPI spec into two sandboxed tools (search + execute).
Generate typed Python APIs from MCP server tool schemas
🤖 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."