“coding”

TypeScript library that lets agents call MCP and UTCP tools by running model-written code in a sandbox.

Minimal TypeScript agent harness with an agent runtime, multi-provider LLM API, terminal UI and coding agent CLI that users extend themselves.

Open-source online code execution system that runs submitted code in a sandbox behind an HTTP JSON API.

Code-first Go toolkit for building agents with a tool ecosystem, composable multi-agent systems and Cloud Run deployment.

Small Python library whose agents write their actions as code, with sandboxed execution and tools from MCP servers, LangChain or the Hub.

Python framework for writing language-model programs as code and optimizing their prompts and weights instead of hand-tuning prompts.

Open-source agent harness from LangChain for building agents with code, with LangSmith for testing and monitoring.

JVM framework for agentic flows that plan toward goals, mixing LLM calls with code and domain models, usable from Kotlin or Java.

Python and TypeScript SDK and REST Agent Server for building agents that work with code in local or containerized workspaces.

Multi-language SDKs for embedding the GitHub Copilot agent runtime, with planning, tool calls and file edits, in your apps.

TypeScript toolkit for agents with Zod-typed tools, graph and multi-agent workflows, and Node.js or browser runtimes.

Typed Python SDK for building agents with swappable model providers, plus optional capabilities for memory, sub-agents, planning and durable execution.

Open-source toolkit for building, evaluating and deploying agents in Python, TypeScript, Go, Java and Kotlin, tuned for Gemini but model-agnostic.

SDK for browser agents with act, observe and extract calls, used from TypeScript and Python to automate sites and pull out structured data.

TypeScript toolkit for AI apps and agents with a unified provider API, streaming, UI hooks and a wrapper for running established agent harnesses.

Java library with one API over LLM providers and vector stores, plus tools, RAG and integrations for Quarkus and Spring Boot.

Python SDK for deploying agents to Amazon Bedrock AgentCore, a managed runtime with memory, gateway, tools and observability.

Browser infrastructure for AI agents: local and cloud Playwright-based browser sessions, scraping and deployable browser functions.

Reinforcement-learning trainer of about 3,500 lines that trains models behind agents run in their own harnesses, locally or as Kubernetes jobs.

OpenAI-compatible agentic API server for inference, vector stores, files and skills, on any model or infrastructure.

Python framework for generative AI agents, pipelines and parallel workflows, with RAG engines, tools, memory and swappable drivers.

Model-agnostic SDK for building agents and multi-agent systems in Python, .NET and Java; Microsoft names Agent Framework as its successor.

Library for LLM post-training (SFT, DPO, GRPO and agentic RL) and classic RL, with evolutionary hyperparameter optimization.