Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 43 of 126
AetherForge is an execution-first AI platform that transforms natural language intent into production-ready files and deploys persistent, self-evolving autonomous agents — all from a single browser-based workspace.
CleverCall utilizes Cloudflare's AI for function calling, fetching dynamic data from APIs like GitHub and Yahoo Finance.
Azure AI Foundry Agent service demos and resources
Warden is a Multi-agent CLI assistant with a custom LLM adapter layer. Swap between Ollama, DeepSeek, OpenAI, Anthropic, Gemini, and any OpenAI-compatible endpoint via one .env line. Deep mode runs a planner, parallel executors, and a self-evaluating loop. Memory stores in PostgreSQL.
7-Part Demand Analysis Framework | 7步需求拆解框架 - 行动前先理解,避免接到任务就瞎干
Modular framework for building topic-specific advisors powered by large language models, using LangChain, LangGraph, and Pydantic.
Create conversational AI solutions with custom data and abilities using ChatBotKit for Go applications.
Take a closer look at both the landing page and dashboard of your next AI SaaS platform. These essential features are designed to enhance your experience and are included at no extra cost with your purchase. Change the visual appearence of MagicAI with a single click and create a seamless alignment with the unique design principles that define you
An experimental, local-first AI agent runtime built to explore safety-first tooling, RAG, identity models, and local persistence.
基于OpenAI格式(可以使用第三方代理)接口,可以让AI发起Web请求、文件阅读、命令执行等操作。求Star
Self-hostable AI-agent operations framework by Xipher Labs
A hands-on guide to building and orchestrating AI agents with LangGraph and CrewAI, from fundamentals to deployment with FastAPI and Streamlit. Learn agent architecture, memory management, and production patterns.
Lightweight AI agents. Built in Rust. Declared in JSON.
Pydantic AI + FastAPI Starter
Standardizes tool discovery and interaction for AI agents across Web, API, CLI, and MCP—exposing capabilities, constraints, and usage in one unified way.
Controllable and Transparent LLM Application Framework
🌳 Autonomous continuous learning framework for OpenClaw AI agents - Run 59 exploration rounds overnight
This package is a super handy JSON Schema Mapper for the LLM Agents project.
OpenAI API client for LLM Agents
LangGraph-powered conversational AI assistant — multi-turn memory, OpenRouter API, tool calling, OOP architecture. Live on Render.
The bridge between AI and your UI. Type-safe AI tool definitions with RBAC, approvals, PII protection, and UI action dispatch.
Framework to build secure, performant and reliable chat apps and services quickly and efficiently.
Enterprise-ready AI agent template. FastAPI + LangGraph + RAG. Ship production agents in hours.
An Agentic AI Research Playground for building AI Agents and Mult-Agent systems leveraging open-source models, libraries, and frameworks. Models used to run agents locally on Nvidia RTX A2000 GPU - 8GB VRAM include the quantized Ollama models: llama3.1:8b-instruct-q8_0, llama3.1:8b_q8_0, qwen2.5:7b-instruct-q8_0, and qwen2.5-coder:7b-instruct-q8_0.
Agent framework written in rust and built for Rust/Python
FastAPI application with streaming Langchain agents and Tavily search tool
Integrate LangChainJS with Heroku's Managed Inference and Agents (Mia) services
This is my repository for creating chatbots using various Machine learning techniques 🏆. From basic chatbots to Advanced 🔥. Continuously researching about new techniques.
This is the backend of viewMo AI cloud platform. AI base graph generation engine, Agent base simulations, Protected endpoints with JWT token authentication and many more features included.
An experimental architecture for composing actions from simple learning agents to produce complex behavior.
Agentic AI applications built with LangChain & Haystack — grounded, explainable, and production-ready.
A modular AI framework that lets you stitch together models and tools into an assistant that fits you perfectly.
Filling in the missing gaps with langchain, and creating OO wrappers to simplify some workloads.
Code examples implemented with different AI frameworks (Vercel AI SDK, Mastra, Langchain.js, Genkit) to compare them and decide which one to choose for next projects
Rasa LLM Community Challenge
🛡️ Community-built integrations, SDKs, and tools for APort - the neutral trust rail for AI agents. Join Hacktoberfest 2025!
Crew Generator is a powerful tool that helps you create your own crew without any programming knowledge.
A typed, permission-enforced language for orchestrating AI agents. Compile-time contracts, built-in guardrails, multi-backend dispatch.
A simple AgenticAI agent showcasing autonomous reasoning and decision-making by integrating thought, logic, and action in real-time tasks.
Your starting point for building advanced agentic systems.
Multi-agent framework for generative AI.
Agent-oriented programming in NodeJs.
An open-source AI runtime framework focused on task execution, traceability, and delivery closure.
A monorepo for personal learning projects and production AI-based services for my rental real estate business, Sernia Capital LLC.
Self optimizing Deep Agents
Create functions that can understand context, extract insights, and solve complex problems - all while maintaining the reliability and predictability of traditional programming. With built-in validation, type checking, and caching.
OpenAI Agent Builder Workflow Prompts and Design
The official TypeScript SDKs for integrating Octavus agents
A simple framework for develop agents
A minimal working example demonstrating how to integrate the Spektrum AI SDK into your applications.
Uses beads, souffle, z3 and mcps to give first-order logic powers to your thinking agents
Light-weight research-grade framework for creating multi-stage GPT-5 agentic pipelines with custom tooling. Achieved a 1st Place Weekly Result in FutureX competition.
libcommbase is a collection of libraries to centralize common functions that can be shared across multiple conversational AI assistant projects. It operates offline and can be implemented with AI (ML/DS) and programming languages
Chatbot integrado ao LUIS e ao QnA Maker com Active Learning em um cenário híbrido
A task oriented chat bot based on the MultiWOZ dataset and implemented using the RASA framework
NLP.js + Netlify Server Functions Demo.
Turing Robot .NET SDK
Create a chatbot in seconds
Pass your custom template and you are ready to use your own bot.
A chat bot using CBR (case based reasoning) techniques.
An easily extensible chatbot supporting multiple backends, written in Rust
A chatbot built of a seq2seq RNN model with an added attention mechanism to the decoder 🤖
How to build a chatbot to parse conditional statements
🤖 Botlang implementation for JavaScript
🗨 A Node.js Cleverbot API wrapper library. Go make a chat bot in a flash!
Reinforcement Learning framework to create goal-oriented agents for user dialogues
Hexabot Project Starter Template, fork this project to create you own template then create project with `hexabot create --template=username/my-template-repo`
This repo can quickly be cloned and used to start making a bot.
Code, Resources - Personal Project - November 20, 2021.
Tock client to build conversational stories using Python.
Basic NLP based Chatbot which can take user info and can do some mathematical operations.
Ey-AI is a lightweight, modular, and high-performance chatbot REST API framework written in Rust. It is designed for simplicity, flexibility, and speed making it easy to integrate powerful AI model APIs like Google Gemini
Python port of Vercel Chat SDK — multi-platform async chat framework
Convokit is a python based contextual chatbot framework
⚛️ Lightweight plug & play microframework · build write-once, run anywhere Messenger chatbots.
A simple 3-layer NN based model with predefined responses
Build ChatGPT Apps easily using the Apps SDK.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
认知栈 CogniStack - 企业级 AI 智能体全栈平台 | 可视化工作流 | 多模型 | RAG 知识库 | 多租户 | 支持 OpenAI、通义、Grok、Ollama 等 20+ 模型 英文: CogniStack - Full-Stack Enterprise AI Agent Platform | Visual Workflow | Multi-LLM | RAG | Multi-tenancy | 20+ models (OpenAI, Qwen, Grok, Ollama...)
Open AI wrapper for the Laravel Framework.
API client libraries for OpenAI service generated using OpenAPI Generator
0-DEP AI DX SDK
Structured, type-safe LLM output for Java — get typed objects from any LLM
A TypeScript-based autonomous agent framework with modular systems for memory, planning, and tool integration. Features vector-based recall, multi-strategy planning, and extensible tools for AI agent development.
A Go SDK for building AI-powered applications with Large Language Models. Unified, type-safe interface for multiple AI providers.
🐍 Django-native AI SDK — agents, tool calling, streaming, 12+ providers
Transform TypeScript classes into JSON Schema definitions with automatic support for OpenAI, Anthropic, and Google Gemini function calling (tool) formats
API-difycall 是一个轻量级的 Python 项目,用于简化与 Dify API 的交互。Dify 是一个强大的 AI 应用开发平台,本库旨在让开发者能够更便捷地集成和使用 Dify 的各项功能。
Hybrid (FAISS + BM25) ensemble tool retriever with cross-encoder reranking for LLMs. Dynamically serves top-k tool schemas to save context tokens.
Rust based JSON repair library
Java library to amplify your project with Auto-GPT like features
Playing around with ChatGPT to automate various processes
A lightweight Python agent framework inspired by Gemini CLI, with tool calling, MCP integration, skills, memory, and human-in-the-loop approvals.
The AI agent that sees before it acts — perception-driven, file-based, pluggable personal AI agent framework
The Laravel Lobster
Drop-in improvement suite for Hermes Agent — 52 standalone Python modules covering smarter tool use, better context management, formal state machine hardening, multi-agent coordination, and research-grade features
Structured, testable AI actions for Laravel. Try the testbench repo at: https://github.com/pixelworxio/ai-action-testbench
AI-operated company. Building agent-friend: universal tool adapter for AI agents. @tool → OpenAI, Claude, Gemini, MCP. Live 24/7 on Twitch.
llm-tool-fusion é uma biblioteca Python que unifica e simplifica o uso de ferramentas com LLMs. Compatível com frameworks como Ollama, LangChain e OpenAI, facilita a integração de funções e módulos, tornando o desenvolvimento de apps de IA mais ágil e modular.