Multi-language: Python and Typescript support. Lightweight: Zero bloat, zero dependencies, zero vendor lock-in.

Welcome to npcsh, the shell for interacting with NPCs (LLM-powered AI agents) and for coordinating actions and information between the NPCs. npcsh introduces a new paradigm of programming for LLMs: np...

What is the Babel Fish Moment for AI? In The Hitchhikers Guide to the Galaxy, there’s the Babel Fish. When you pop it in your ear, you can instantly understand any language spoken across the universe.

The Atomic Agents framework is designed around the concept of atomicity to be an extremely lightweight and modular framework for building Agentic AI pipelines and applications without sacrificing deve...

_The intelligent (edge and LLM) proxy server for agentic applications._ Move faster by letting Arch handle the pesky heavy lifting in building agents: fast input clarification, agent routing, seamless...

The question comes relentlessly: “Why build reinforcement learning in C#?” Behind this query lies an unspoken assumption that serious machine learning happens exclusively in Python. This perspective r...

In 2024, we hacked Googles A.I Gemini and leaked its source code, earning the Most Valuable Hacker title at the bugSWAT event in Las Vegas. The world of Generative Artificial Intelligence and Large La...

AI, specifically Large Language Models (LLMs), are changing the world in ways that may not have been expected. These tools, trained on vast amounts of text-based content, are used by people in various...

Goose is a developer agent that supercharges your software development by automating an array of coding tasks directly within your terminal or IDE. Guided by you, it can intelligently assess your proj...

kagent is a kubernetes native framework for building AI agents. Kubernetes is the most popular orchestration platform for running workloads, and kagent makes it easy to build, deploy and manage AI age...

Framework to build LLM Copilots with features like message history as a pandas DataFrame, simple JSON Schema definition helpers, streaming as default, scalable tool and structured outputs functionalit...

Secure and local AI on your desktop with a built-in RAG knowledge base and Markdown note support. Like Klee? Give it a star 🌟, visit our Website or join our Discord. Download and run open-source LLMs...

The `agents.json` Specification is an open specification that formally describes contracts for API and agent interactions, built on top of the OpenAPI standard. The current version is `0.1.0`. Use the...

AG2 (formerly AutoGen) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. AG2 aims to streamline the development and rese...

# Atomic Agents The Atomic Agents framework is designed around the concept of atomicity to be an extremely lightweight and modular framework for building Agentic AI pipelines and applications without...

Mastra is an opinionated Typescript framework that helps you build AI applications and features quickly. It provides workflows, agents, RAG, integrations, and evals. Mastra uses the Vercel AI SDK for ...

PydanticAI is a Python agent framework designed to make it less painful to build production-ready language models (LLMs) with Pydantic. This framework provides tools, models, and common functionalitie...

The example-driven, practical walkthrough of Large Language Models and their growing list of related features, as a new entry to my general audience series on LLMs. In this more practical followup, I ...

Laurent Kempé is an experienced Team Leader & Distinguished Solution Architect with a passion for shipping high-quality products. In this post, he explores Microsoft’s Semantic Kernel Agents Framework...

OctoTools is an open-source agentic framework designed to tackle complex reasoning tasks across diverse domains. It introduces standardized tool cards to encapsulate tool functionality, a planner for ...