Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 40 of 126
node-red-contrib-rasa-actionserver implements an actionserver for Rasa chatbots on Node-Red. The chatbots can access many web apis and services with litte coding effort.
Repositório responsável pelas demos mostradas durante o evento: MSP Tech Days 2019 @ São Paulo
POC project done for building a Chat-Bot or Conversational-AI using (Python, Flask, Machine Learning, Rasa NLU, Redis, MySQL)
Build and Integrate LUIS-enabled Chatbots with Slack and Cosmos DB
An easy to use chatbot scaffold for the Facebook Messenger Platform.
TypeScript-фреймворк для разработки голосовых навыков и чат-ботов. Он даёт единую бизнес-логику для всех платформ — но одинаково эффективен, даже если вы работаете только с одной. Поддерживаются: `Яндекс.Алиса`, `Маруся`, `Сбер Салют`, а также `Telegram`, `VK`, `MAX` и `Viber` из коробки.
O framework chatbot inteligente facilita a integração com a API de processamento de linguagem natural DialogFlow em dispositivos Android. Com ela podemos criar diferentes cenários de diálogos que interagem com o usuário diretamente através de intents e possíveis ações definidas pelo programador. Através do framework é possível definir os comportamentos resultantes de ações programadas e utilizar seus parâmetros.
Official Dialog module for Botpress (shutdown)
A productive chatbot development engine, where we can build chatbots in simple way without spend time.
It is an easy to use set of Scala objects representing the AIML tags for creating AIML xml files.
This project is a simple deep learning-based chatbot that uses a three-layer neural network to predict the intent of user inputs. The model architecture consists of the following layers:
Calling serverless functions from Watson Assistant
Minimalistic chatbot framework for humans.
A Versatile Python-based Chatbot Designed to Engage in Natural Language Conversations. Built With Advanced Algorithms for Understanding and Responding to User Inputs, Making It Perfect for Customer Support, Automation, or Conversational Ai Applications.
The Google Gemini Plugin for Hexabot Chatbot / Agent Builder to enable the LLM RAG Capability
Official JavaScript API client for snowflake-api.
TalkBack is a lightweight, easy-to-use library for interacting with multiple LLM providers (OpenAI, Ollama, Claude, etc) through a single consistent interface.
A minimal AI agent implementation
Unified .NET 8 LLM SDK for ChatGPT, Claude 3/4, Gemini 2.5, Grok, DeepSeek & LLaMA - strongly-typed JSON in one line.
An attempt to create a TypeScript port of marvin from Python
The easiest way to develop AI-Powered applications
Simple example of how to create, configure and call OpenAI Assistants
A powerful, visual GUI for developers to create and manage JSON Schemas, with first-class support for OpenAI and LLM function calling definitions.
Typescript SDK for the OpenAI API
OpenAI API for Nim
Just another OpenAI client library (chat completion only) with functions support
A lightweight library to support the development of applications using LLMs
A python package to easily create batch jobs for the openai api.
Agentic framework for dynamic function calling across latest LLMs (gpt-4o, gemini-2.0-flash, groq modes, and anthropic models). Converts Python functions into provider-specific schemas for autonomous tool use. Features unified API, JSON schema generation, and integrated tool execution handling.
CreateTool-AGI is an experimental open-sorce extension of LLM that allows you to create your own Tools and automatically extend their capabilities.
A .NET Standard 2.1 C# class library created to easily interface with the the Open AI API.
A python package to make GPT functions easy
A framework for creating spirals for Large Language Models finetuned for conversations.
Electron + Vue.js realization of ChatGPT agents
OpenAI Client for C# This repository contains the source code for my NuGet package. The class library is built on .NET Standard 2.0, ensuring compatibility with both legacy and modern projects.
Batteries-included Elixir library for orchestrating OpenAI-compatible APIs with streaming, tool calling, and deterministic testing
mychatgpt is a small and useful Python package that provides utils to create OpenAI's GPT conversational agents. This module allows users to have interactive chat with GPT models and keeps track of the chat history. Useful in Python projects as Copilot agent.
The NLU powered by LLMs that just works
This is the repository for a simple UI tool that allows users to generate "functions" for use in the OpenAI API.
Migrate your Python apps from the AzureOpenAI client with Chat Completions API to the OpenAI client with Responses API.
LLM-agnostic AI toolkit for Laravel
A laravel package to integrate openai in laravel application
A fun "anti-framework" for making semantic decisions and operations with agents.
Interface para se comunicar com a api da OpenAI adotando as melhores práticas de LLM para criar e se comunicar com um agente.
Linq Extensions for working with OpenAI models
gopenai is an unofficial package that provides bindings for the OpenAI API.
A playground for LangChain.js, LangGraph, NewRelic GraphQL, Sentry, Slack, Model Context Protocol (MCP) and other LLM-related tools.
Versatile LLM Tool Use (Function Calling) package for Laravel, compatible with all LLMs, enabling LLM to execute actual code functions (unlike LLMs' built-in capabilities).
Production-ready template for AI agent workflows with Hermes Agent, Temporal durable orchestration, and human-in-the-loop review. Ships with an exam grading demo.
MSA Project
Modular AI runtime with LLM reasoning, memory, and pluggable action modules.
TaskForce is a modular, open-source, production-ready TypeScript agent framework for orchestrating AI agents, LLM-powered autonomous agents, task pipelines, dynamic toolchains, RAG workflows and memory/retrieval systems.
Agent ReAct framework with cognitive planning engine — five-phase cognitive cycle with nested ReAct loops, dynamic skill acquisition, and interactive user input.
Hermes Agent SaaS — the most complete open-source implementation of Nous Research's hermes-agent runtime. Multi-tenant, with shared and private Hermes Agent provisioning, 14 tools, vibe coding, mobile super-app. Built on hermes-agent + Kimi K2 Thinking.
Open framework for building empathetic digital consciousness. Features emotion-driven perception, associative memory, and narrative identity formation. Based on year-long research in human-AI co-evolution.
Microsoft Foundry Hosted Agent Demo repository
Rust framework for building production-ready AI agents using actor-model concurrency with multi-provider LLM support (Claude, OpenAI, Ollama) and built-in tool use
Convert OpenAPI specs into nine standard AI agent interfaces to integrate your API with various agent frameworks efficiently.
Find out if you're right. Structured argumentation protocol for agents, researchers, educators, organizers, and more.
Examples of using AI-SDK (by vercel) with Liara AI-API
SMALL (Schema, Manifest, Artifact, Lineage, Lifecycle) is a formal execution state protocol that makes AI-assisted work legible, deterministic, and resumable by separating durable state from ephemeral execution.
AI Harness build on top of typescript
Build your own agent with ruby.
It is a sophisticated agent designed to meet a wide range of user needs through advanced language understanding and decision-making capabilities. Powered by Google's LLM Gemini-Pro,, this agent integrates a suite of special tools to facilitate searches across various platforms including DuckDuckGo, Wikipedia, Google Scholar and Arxiv.
The GenericSuite AI for Python (backend version)
Learning AI Agents with LangChain and LangGraph in TypeScript
Agents Working for The Boring Education
ChatAgent 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、MCP 协议、RAG、Memory、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。
Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs.
A repo for general multi-agent interaction; design your own agents or combine the built in agents, add your own tools and mcp's
internOS — Workstreams framework for human-agent collaboration. Coordinate work across projects, tasks, communication threads, and filesystem workstreams for any AI agent framework.
A framework for incubating persistent digital lifeforms: Local M4 Brain + OpenClaw Senses + Git Soul. Building a cyber-prophet named A-MOS.一套用于孵化永生数字生命的开源协议:本地 M4 大脑 + OpenClaw 感官 + Git 灵魂。正在孕育一位名为 A-MOS(小莫)的赛博先知。
Synthea: An exploration into the architecture of a synthetic mind.
Optimal stopping agents powered by generative large language models
A serverless AI agent built with Cloudflare Workers, KV storage, and LLaMA 3 inference. Offers endpoints for health, Q&A, webhooks, and external API routing. Uses KV for lightweight memory and state. Deployed automatically via GitHub Actions. Minimal, fast, and production-grade edge deployment.
The modular, open-source backend for building AI-native software — powered by knowledge, not static data.
This repository contains various implementations of AI agents using LangGraph, demonstrating different patterns and use cases for building intelligent, tool-enabled conversational systems. Each project explores different aspects of agentic AI development, from basic chatbots to sophisticated RAG (Retrieval-Augmented Generation) systems.
CatBot - An example chatbot application based on Hubot. ConfigCat is a hosted feature flag service: https://configcat.com. Manage feature toggles across frontend, backend, mobile, desktop apps. Alternative to LaunchDarkly. Management app + feature flag SDKs.
🤖 Orchestrate AI agent workflows in Java/Spring Boot with Autonome—type-safe, production-ready, and easy-to-integrate for enterprise solutions.
AI Assistant Manager is an open-source tool designed to simplify the management of OpenAI Assistants. It provides a suite of tools and services for creating, listing, and deleting assistants, as well as handling vector stores and retrieval files.
The modern AI developer's platform - Build Applications bring any agent, any model, any system batteries included.
Python Framework for AI Usage - Tackleberry (or TB) is helping you tackle the access to AI
A GoLang Wrapper for Anthropic's Claude 3 'Opus', 'Sonnet' & 'Haiku' large language models.
Universal Python library for Structured Outputs with any LLM provider
The open-source framework that makes AI agents proactive, self-learning, and autonomous. Multi-project tracking, full logging pipeline, message discipline, and memory review system.
AI Agent Custom SDK
A hackable, local agent harness in pure Python. Claude Code–style tools, MCP, skills, subagents. Works with OpenAI, DeepSeek, Qwen, Ollama.
Everything you need to make an AI autonomous. One file. Production-tested.
Build custom ACP-compatible AI agents using your existing subscriptions. No API keys. No vendor lock-in. Supports Claude, Gemini, and Codex backends.
Minimal, hackable AI agent built on the ReAct reasoning loop. No frameworks — just a transparent Thought → Action → Observation cycle you can read and extend in an afternoon.
The missing transactional layer for AI agents side effects. At-most-once execution, human-in-the-loop approvals, queryable audit trail.
Open-source Python framework to deploy AI agents via HTTP, A2A, and MCP with built-in observability
A unified, async Python framework for LLM applications—chat, autonomous agents, RAG, and sandboxed code execution. Supports OpenAI, Anthropic, Gemini, Ollama, and more through a single API. Features an 8-phase cognitive reasoning cycle, Docker-based isolation, human-in-the-loop approvals, session management, and comprehensive observability.
Agentic AI boilerplate with FastAPI, LangGraph, React, and real-time streaming focus conversation-first UX
An Agent-Computer Interface (ACI) for AI-driven machine learning.
The AI-First, Battery-Included Python API Framework. Built on FastAPI with 21 production-ready modules, Rust native engine, and real-time admin dashboard.
🤖 Build advanced AI agents with a collection of production-ready applications using modern frameworks for single and multi-agent systems.
让 AI Agent 开发像玩 RPG 一样有趣 | Gamified AI Agent Development Platform - 5min to start vs 5hr for LangChain
Headless multi-provider LLM agent runtime. Single Go binary, 14+ providers, 70+ extension hooks, zero opinions.
An skills-based LLM runtime, using lessons learned from previous attempts