Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 44 of 126
Updated version of OmniBot
A Django library for seamless LangChain integration, making it easy to add LLM capabilities to your Django applications.
A base chat bot image that can be quickly customized for domain knowledge
🥷The JedAi Council: Build powerful AI agents with CrewAI, Graphiti Graph RAG, LlamaIndex, and modern uv package management 🚀
Modular multi-agent AI framework - autonomous agents with memory, tools, and policy management built in Python
TypeScript framework for AI tools, MCP servers, and workflows, with durable execution journals and crash recovery.
A powerful framework for building and deploying Agentic Oracles on the IXO network. Built on LangGraph, Matrix, and NestJS, this framework enables developers to create intelligent oracles with secure communication, complex conversation flows, and automatic marketplace integration.
All my AI Agent projects in one place. Smart, interactive, and tool-powered! 🚀
Discovering, comparing, and installing skills in AI agents.
An enterprise-grade AI agent orchestration platform built with .NET and Clean Architecture. Create intelligent conversational agents with OAuth integrations, semantic memory, and extensible plugin capabilities.
The Stateful Agentic AI Framework for Flutter. Build "Brains" directly in your app.
Discover the End-To-End-Agentic-AI-FastAPI-Docker-Project on GitHub – a powerful, open-source framework for building agentic AI workflows with FastAPI and Docker. Clone, customize, and deploy scalable AI solutions effortlessly!
Agent is built with the help of Firecrawl for MCP tools, Gemini for LLM's.
Public version of the Human Agentic Platform
An AI-agentic IDE framework built on a plugin host architecture. Every capability is a plugin — storage, tools, transport, AI — communicating over QUIC with mTLS and Protobuf messages.
TypeScript framework for building production-ready LLM systems. RAG, agents, workflows, evaluation, multi-model orchestration, OCR, MCP, Fine-Tuning, and more.
Enables small function calling models to find and use 484,000 local source code tools from many open source repos
Google Cloud Rapid Agent Hackathon
The JIT (Just-in-Time) Tool Spawning Protocol: A Smart Routing System for Infinite-Tool AI Agents
A simple and easy-to-use Python wrapper for popular LLM APIs (OpenAI, Anthropic, and more).
Single-header C++17 client for streaming OpenAI and Anthropic chat responses token by token over SSE, with per-token callbacks and tokens-per-second stats. Only needs libcurl.
Get started integration Llama Index into your swarms application now!
Define Once. Deploy Anywhere. Govern Automatically. Framework-agnostic platform to build, deploy & govern enterprise AI agents — LangGraph · CrewAI · Claude SDK · OpenAI Agents · Google ADK · AWS · GCP · Azure · K8s · RBAC · A2A · MCP
Markdown-native multi-agent workspace framework. Define agents, skills, and workflows as plain .md files — no runtime required.
Self-Adaptive Generation Engine — Agent Development Kit with cognitive routing, evolutionary topology, formal verification, and 4-tier memory
Secure multi-agent AI framework in Rust — WASM sandbox, 50+ skills, 14 LLM providers, agent intelligence, compliance modules
AgentFlow: A production-grade Go LLM Agent framework with layered architecture, multi-provider LLM support, memory systems, reasoning modes, and workflow engine. 生产级 Go 语言 LLM Agent 框架。
Open-source platform for creating AI employees with a soul. Conversational agent builder, Docker-native sandboxes, 7-stage lifecycle, LLM-agnostic.
Powerful Python agent runtime with tools, MCP, Hooks, Skills, Rag, memory, sessions, reasoning, and streaming packets.
Agents should execute whenever possible — open registry of reusable AI agent skills and capability definitions
The complete Swift platform for Claude AI — SDK, agent framework, RAG memory, and SwiftUI components. The first and only Swift agent framework. Zero dependencies.
Comprehensive Python SDK for Venice AI - Advanced LLM, Image Generation, Audio Synthesis, and AI Assistant APIs with Full Swagger Specification Support
ShuyuanCore (数元体) — 智能进化、风格一致、深度记忆、自主行动的开源AI Agent。(ShuyuanCore—An open‑source AI agent with intelligent evolution, consistent style, deep memory, and autonomous action.)
一款企业级多语言(Polyglot)智能出行 Agent 架构实战。采用 Monorepo 单仓管理,底层基于 Java Spring Cloud 构建高并发票务微服务底座;AI 大脑层提供 Java (Spring AI) 与 Python (FastAPI+LangChain) 双引擎实现。核心特性包含:端到端 JWT 上下文鉴权透传、基于 Tool Calling 的异常自纠错 (Self-Correction) 循环,以及微服务级的数据流压缩,完整打通自然语言到真实复杂业务下单的全链路闭环。
Build AI-native SaaS agents with the ROAM Loop: Render, Observe, Act, Memorize.
Self-hostable execution engine for reliable, observable, tool-using AI agents — with custom orchestration, persistent memory, trace replay, automated evals, and MCP integration.
Open source AI agent framework to build the future of data operations.
Build workflows and agents with LangChain and LangGraph
A configurable, typed AI framework with swappable LLM, classifier, handlers, and optional memory for NLP to Action flows
Deepagents for Go, the easiest way to write LLM-based programs in Go
This project is the fourth deepagent companion project in the Cufel-X project, and the content is a deepagent framework adapted to MCP adapter
Compose agents like plain values. A TypeScript toolkit that wires LLM calls, tools, and functions into typed steps over eight providers. No framework, no ambient state.
Multi-runtime agent framework (Claude Code, Codex, Antigravity) with hard/soft controls, audit-first hooks, and multi-dev coordination.
Historical standalone Agentic repository. Active development moved to pyfly.agentic in pyfly v26.10.08. See native documentation and migration guide.
A generic, batteries-included, async-first agent toolkit — configurable loop, tools, security guards, streaming, persistence, and MCP. Import as 'agentix'.
Vue 3 native bindings for CopilotKit — the full-stack SDK for agentic apps, Generative UI, and chat.
Full Form : Expert Network for Intelligent Guidance and Multi-task Assistance. Using multiple LLMs, for Conversational as well as Functional Request.
Standard for authoring and deploying agents and workflows.
Agents and humans live adjacently.
This package makes it simple to start building a chatbot in PHP
🏛️ Delphi is a versatile and adaptable conversational agent framework that streamlines chatbots and AI-driven agent systems.
Give your AI agent access to any API in ~1,000 tokens. Two tools replace hundreds. 56 APIs included.
A swift rest api for OpenAI
saige - Super Artificial Intelligence Graph Environment. A unified Go SDK, CLI, and MCP server for streaming AI agents, knowledge graphs, and RAG pipelines, with Ollama, OpenAI, Anthropic, and Google providers behind one interface.
Self-improving pure-Rust AI agent runtime with closed-loop reinforcement learning, OpenAI-compatible API gateway, multi-provider LLM support, APO prompt self-optimization, and operator dashboard
App-first AI framework with a built-in, governed memory engine (memory, agents, RAG, MCP)
Spinosa is a local framework for working with LLMs. It features a set of sub-agents coherent with modern SKILL and AGENTS protocols to streamline research and build better practices.
ExoBrain CLI - atomic reasoning engine for agents
First LLM runtime that preserves chain-of-thought under continuous user interruption. S(t+1)=f(S(t),ΔU)
Typed TypeScript/React client SDK for Agentflow. Covers invoke, streaming, threads, memory, files, and graph ops, with React hooks for token-by-token streaming and client-side tool execution.
Stateful agent-graph framework with deterministic governance — rules route transitions, not the LLM. Auditable, replayable. Built on Fathom.
Team AI agent built on Hermes Agent — Feishu-native, per-user memory isolation, layered skills, embedded RAG knowledge retrieval
Provider-agnostic Python library for composable LLM execution patterns, including consensus, refinement, ReAct tool loops, structured output, and budget-aware calls.
A lightweight library that integrates Radical Asyncflow with agentic frameworks like Academy and LangGraph to enable running agentic workflows on HPC systems.
Forgewisp — safe, function-calling AI agents for the browser. Register your own functions as validated tools, with risk-tier execution, OpenAI-compatible streaming, dual reasoning streams, and an audit log. Runs entirely client-side.
Behaviour trees for AI agents. Define agentic workflows in YAML, drive deterministic agent runs from a CLI works with any agent, Claude, Codex, Copilot, Gemini etc.
The ultimate autonomous AI agent framework for Termux, powered by Google Gemini. Features a high-autonomy reasoning loop and dynamic tool loading.
Hermes Agent 官方插件仓库 — 智能体能力扩展的模块化解决方案
gradio region:us
gradio region:us
gradio region:us
streamlit region:us
gradio smolagents agent region:us
gradio smolagents agent smolagent tool agent-course region:us
gradio smolagents agent smolagent tool agent-course region:us
gradio region:us
gradio region:us
gradio agent-demo-track mcp-server-track mcp-server region:us
一个支持 MCP、Tool、Skills、Subagent、知识库检索与沙盒执行的模块化 AI Agent 应用。
This is OS of AI. And AI model.
Autonomous Agentic Framework.
Self-hosted AI agent framework with permission modes, audit logging and MCP. Runs on your machine, in Docker, or on a Raspberry Pi.
Agent-native RPC for the multi-agent era — write a Java interface, get gRPC + HTTP/MCP gateway and generated TS/Dart/Python/Rust clients, no protobuf. 智能体时代的契约先行 RPC:接口即 API,天然带 MCP 网关
Uses beads, souffle, z3 and mcps to give first-order logic powers to your thinking agents
🤖 Bots framework and sample chatbots for Ethora. Structured as a monorepo with a reusable bot framework. Features: • Modular bot framework for easy bot development • OpenAI GPT integration • Real-time XMPP messaging • TypeScript support • Easy deployment. Tech: TypeScript, XMPP, OpenAI API
Botkit is a framework for creating chatbots for different services.
chatbot in python using chatterbot module and chatterbot-corpus for data training.
A simple and powerful chatbot made with deep-learning using tensorflow feedforward neural network. Uses RESTful API and Streamlit for ease of use. A smple solution for small scale business or anyone who needs AI chatbot ready to use/ integrate in apps / websites.
Self-hosted AI agent framework built on Mastra + Convex. Central daemon, multi-channel (HTTP/Discord/Telegram), CLI-first.
An app for creating, managing, and sharing AI assistants, vector stores and related tools.
Unofficial Rust parity port of Anthropic's TypeScript SDK, including Bedrock, Vertex AI, and Azure AI Foundry providers.
Completion-native async runtime for Rust with optional orchestration
A mechanical eureka loop for AI agents: obsessions x wandering x recognizers | 给 AI 装一条『灵光乍现』的机械回路
Multi-lane autoloop/autoresearch extension for Pi — run optimize, research, dev, and punchlist loops with isolated state, compound verifiers, and compaction-aware resume.
Go/Golang multi-agent LLM framework — ReAct loops, parallel tool calls, streaming, sub-agents, and pluggable Anthropic / OpenAI / Gemini providers.
The AI Agent framework for enterprises and agencies
Minimal CLI agent framework with compounding project memory — gets smarter with every session. Clean, modular, any LLM provider
A hands-on implementation of Deep Agents and Sub-Agents using LangGraph, featuring autonomous planning, tool calling, web research, task delegation, and multi-agent orchestration workflows.