General-purpose AI agent that acts via code actions through a unified execution interface.
-
Updated
Apr 7, 2026 - Python
#
programmatic-tool-calling
Here are 9 public repositories matching this topic...
Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.
python ipython mcp code-execution code-sandbox code-mode code-interpreter mcp-server mcp-client claude-code-plugin programmatic-tool-calling sandbox-runtime
-
Updated
Mar 24, 2026 - Python
An Open Source Typescript implementation of Programmatic Tool Calling for AI Agents (Based on Code Mode)
typescript tools mcp sandbox agents ptc ai-agents deno code-mode tool-calling programmatic-tool-calling
-
Updated
Mar 17, 2026 - TypeScript
⚡ 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.
typescript nextjs virtualization ai-sdk vercel shadcn-ui vercel-ai-sdk llm-optimization ai-gateway model-context-protocol mcp-server mcp-client token-optimization ai-elements vercel-sandbox programmatic-tool-calling
-
Updated
Dec 3, 2025 - TypeScript
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.
python mcp code-execution agent-systems ai-runtime llm-agents agent-architecture agentic-ai agent-runtime anthropic-mcp programmatic-tool-calling microsandbox
-
Updated
Mar 17, 2026 - Python
Programmatic tool calling / Code Mode for MCP — turn any OpenAPI spec into two sandboxed tools (search + execute).
-
Updated
Apr 15, 2026 - TypeScript
An MCP server implementation for Programmatic Tool Calling (PTC) that runs JavaScript
-
Updated
Apr 2, 2026 - TypeScript
Generate typed Python APIs from MCP server tool schemas
-
Updated
Mar 21, 2026 - Python
🤖 Optimize LLM usage by streamlining tool calls with code generation and sandbox execution for reduced costs and latency in any model.
typescript nextjs virtualization ai-sdk vercel shadcn-ui vercel-ai-sdk llm-optimization ai-gateway model-context-protocol mcp-server mcp-client token-optimization ai-elements vercel-sandbox programmatic-tool-calling
-
Updated
Apr 15, 2026 - TypeScript
Improve this page
Add a description, image, and links to the programmatic-tool-calling topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the programmatic-tool-calling topic, visit your repo's landing page and select "manage topics."