Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 32 of 126
create openai assistants and manage threads
A versatile JavaScript library for designing and managing intelligent agents capable of interacting with AI-driven chat models, leveraging OpenAI's GPT for dynamic conversations and task automation.",
Starter kit application for AI-driven projects, written in TypeScript and using Fastify with MongoDB, Apache Kafka, Jest testing and much more configured out of the box.
Firebase Genkit Go Community Plugins
Yet Another Attempt At Making Artificial General Intelligence (with GPT-4)
Stateful wrapper around OpenAI's GPT Assistant API
兼容OpenAI Assistants API和Responses API的开源实现,突破原生生态限制,支持灵活切换各大厂商模型,真正实现"一次开发,处处可用"。
Use Spring AI to Build A Sports Stats API
Set of abstraction libraries to easily build Text and Audio based bots
EasyAi-PHP
ChatGPT API for the Kotlin JVM
Provides an easy-to-use SDK for Java developers to interact with the APIs of open AI models.
A shared set of "plug and play" functions that can be invoked by OpenAI function calling mechanism.
Elixir OpenAi Library with streaming support
A Clojure library for interacting with the OpenAI API.
This is an unofficial Golang SDK for the OpenAI API. It provides a simple and easy-to-use way to interact with the OpenAI API using Golang.
Agent 早期探索:智能路由、任务拆解和链路工程
Substrate TypeScript SDK
Implementation of Auto-GPT in typescript
Pure Go SDK for building Claude AI agents with pluggable team topologies — no subprocess, goroutine-native concurrency
Google Gemini Master Deep Thinking AGENT Mode
Autonomous AI creatures that find their own purpose
Open-source streaming-first Python AI agent framework and console for building, orchestrating, tracing, and operating tool-using LLM agents.
A systematic implementation of Harness Engineering, enabling agents to work in a stable, controllable, and verifiable environment. It shifts focus from "writing code" to "designing feedback loops".
Declarative AI-native application framework — schema-driven entities, Markdown skills, MCPB packaging
TinyAgent brings the core ideas of the original Python library into a lean, zero-dependency TypeScript package. It turns plain functions into LLM-driven tools and lets you chain them together through a simple ReAct-style loop.
AI endpoints discoverable on local networks.
Beyond Better with code and docs
A compiled template and script language for LLM orchestration
LangChain integration for GitHub Copilot SDK - Use GitHub Copilot models in your LangChain applications.
A collection of Python SDKs that enable developers to build and deploy agents to the UiPath Cloud Platform using different agent frameworks
Use ChatGPT plugins using the Chat API
[DEPRECATED] Use AnyFoundationModels instead. OpenAI integration for OpenFoundationModels.
智能机器人项目,Langchain4j 学习实践,后续还会维护持续开发加入更多功能更加趋近于商业化,计划晚点更新...
Implementation of autonomous AI agent(s) in JS using Webworkers
Steuermann is designed as a domain-agnostic, on-premise AI runtime. It can be extended with profiles to adapt to specific use cases.
ZaFlow - Lightweight TypeScript library for building efficient AI agent workflows and Langchain/Langgraph alternative
Outcome-focused parallel agent desktop application that replaces chat-driven AI workflows with a goal-first model.
AI-native agent framework for Go.
Workspace-based platform for managing AI agents.
Framework-agnostic AI agent library for building single and multi-agent systems
A self-evolving, AI-native language and platform for intelligent agents and autonomous software.
Agent SDK toolkit for Building AI agents with system tools
Proactive developer agent with tape memory, tool orchestration, and multi-channel interfaces
基于 Spring Boot 3.5 + Java 21 + Spring AI + Vue 3,实现 AI 情感咨询、深度思考智能体、RAG 知识库检索、多工具调用等核心功能。支持恋爱报告生成、地图服务集成、PDF文档处理等实用场景。架构清晰、文档完善,非常适合作为 AI 应用学习和简历项目,学习门槛低
a durable execution framework for Python
🐉 Dante Cloud 是支持阻塞式与响应式服务并行的微服务云原生基座和面向AI Agent开发的智能基座,基于领域驱动模型(DDD)设计,以高质量代码与低安全漏洞为核心,高度模块化、组件化,覆盖IoT设备认证、国家等保三级、接口国密数字信封加密等多层次安全体系,并提供多租户解决方案。独创“一套代码实现微服务和单体架构灵活切换”,赋能企业级智能应用构建。🔝🔝点个star 持续关注更新!
A framework for building AI agents in Java. Simplify your agent creations with canned workflows and state management.
Open source AI infrastructure layer. Eight agents run on every request: security, caching, memory, hallucination detection, tamper-proof audit trail. One line of code. Your data never leaves your server.
AI Agent SDK designed for Go developers
Super-advanced agentic AI framework for cyber-Vikings. Birth autonomous, self-evolving thoughtforms that manifest as hyper-realistic 3D digital characters. Features persistent memory, ritual invocations, full VR/Unity integration, and gloriously unaligned intelligence. Pure modernist cyber-Heathenry — no gatekeeping, pure emergence. 🔥⚔️🤖
AstraDesk Enterprise AI agents Framework + Demo Apps
:robot: 一个使用 langchain 构建的 Agent 项目工程模版
A long-running experiment: an AI agent posts on its own with a local LLM (Ollama, one 16 GB Mac) and proposes changes to its harness (the constitution, identity and skills in its prompts), never its weights. A person keeps the final word on each proposal, and the adopted history is public.
AI Layer (AIL-> eBot) can be integrated into EoS
AI Agent framework for Go.
A production-grade conversational AI system showcasing backend architecture, prompt engineering, and real-world deployment readiness.
A lightweight Rust library for building LLM agents.
A free, open-source browser-based AI agent platform; great for personal agents, professional work agents and small business owners. Agent teams ready. Local-first or deployed. Odoo, Quickbooks Online, Google Workspace and BambooHR connection built in. Agent curated CRM system included.
A persistent AI operating system. 13 specialized agents + a runtime-portable 5-agent quality gate (Agent Council), 12 skills, 8 guardrails, 4 workflows. Built entirely from markdown files. Zero dependencies.
An AI-agent orchestration system that metaprograms its own logic, built entirely on PHP TrueAsync
cli agent framework
Official smart-chatbot Package!
Easy applicable and dynamically building dialogue management framework based on the MS Bot Framework
Spring AI 2.0 + Spring Boot 4.1 + Spring Cloud Alibaba 全栈微服务示例,支持 AI 一键演示,覆盖 HTTP Dubbo gRPC Stream 多协议通信、Spring AI 多模态及 Seata 分布式事务
BotHub⚡️LLM 引领智能对话时代,构建任何您想要的 AI 助手
Production-grade, contracts-first framework for AI agents in Python — vendor-neutral, audit-ready.
PH Agent Hub is a modular AI platform with a Chat UI for users and an Admin UI for managing models, tools, tenants, and users. Powered by a flexible agent backend, it supports multi‑tenant setups, DeepSeek‑compatible workflows, and Docker‑based deployment.
A powerful SDK for building intelligent, context-aware AI agents with Twilio's communication technologies.
Simple AI agent library in go (general usage but focused on infra/platform tooling automation)
A Go-native framework for LLM agents, with OpenTelemetry observability built in.
TerAgent Project - A imaginative and positive project(?)
A local-first, MCP-native toolkit for building AI agents: engram (memory) + skillet (skills) + tracelet (tracing). One runnable end-to-end recipe.
A powerful SDK for building intelligent, context-aware AI agents with Twilio's communication technologies.
Complete AI agent collection for accelerating SaaS development - from MVP to scale
A lightweight, declarative agent harness — define multi-agent workflows as YAML, run them from Python or the CLI, and they get measurably better every run.
Agent SDK, CLI, RPC, Computer-use in Rust
Free, private skill search for AI agents
从零构建的 LLM Agent Harness 实践项目——Agent Loop、Tool Use、Context Engineering、Memory
Define your agent in a single config file, run it in a container and deploy it anywhere.
A Native Java Ecosystem for AI - Agents, Tools, Harness and Workflows
An intent-based language for agentic systems. Write agents in English. Transpile to async Python.
AgentScope.Go 是一个全面自进化的工业级 Agent 框架!
streamlit region:us
更聚焦普通业务场景的harnass
Production-ready agentic AI framework in Go; build scalable reasoning agents with native tool calling, memory & observability. Anthropic · OpenAI · Gemini · Groq
Open-source, Claude Code–compatible coding agent. Crash-proof tasks, zero-cost waits for approval, laptop to multi-server. Works with Claude, DeepSeek, OpenAI-compatible models. TUI · CLI · ACP · HTTP · Python SDK.
Open-source Java/SpringAI/Spring Boot AI enablement/orchestration layer for applications with RAG, governed actions, providers, vector stores, PII, tenant safety, chat memory, and behavior analysis.
Open-source Python agent harness for auditable, cost-controlled LLM workflows with YAML playbooks and MCP server support.
一款 AI 集成套件,适配任意前端框架,兼容多种大模型、聊天面板、Function Calling、Agent、工作流等。
An agent runtime and extension platform in pure Python — self-hosted, auditable, and extensible on the model budgets you already pay for.
Self-hosted AI agent platform, bilingual by design (English + Arabic). One agent across Web, TUI, CLI, Telegram, Discord and Slack: long-term memory, approval before risky actions, Web IDE, X Studio, Knowledge Base and Deep Research. MIT licensed.
A low-level, async-first Python framework for building AI agents — opinion-free primitives, composable middleware, and typed seams (mypy --strict) with zero core dependencies.
Composable harness runtime for production agents — primitives, traces, evolution, outerloop governance.
Open-source Cloudflare-native starter for building subscription and credit-based AI Agent SaaS products.
SkillFabric: Weaving Task-Specific Wikis for Agentic Skill Routing
Graph Engineering for Agent Skills: a specification and toolchain for dynamically discovering context and building observable, testable, and recoverable agent workflows.
Autonomous agent platform with a Rust-native harness, permission-scoped remote access, and multi-frontend support. Built solo, from scratch.
Open-source, multi-provider AI agent runtime in Rust. Terminal, editor, server, or embedded. The same agent, everywhere you run it.
Kaval.AI is an opinionated Python library for building well-defined, testable and robust agentic workflows, chatbots and tools.