Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 31 of 126
Intentional is an open-source framework to build reliable LLM chatbots that actually talk and behave as you expect.
Rasa Chatbot using Django backend and Sockets for communication
This project demonstrates how to integrate a “think” tool into a LangGraph agent workflow, inspired by Anthropic’s research on structured reasoning in tool-based agents. By leveraging the “think” tool, Claude is enabled to pause and reflect on intermediate steps, improving performance in complex, policy-driven, or multi-step decision scenarios.
For unmanned missions into GPT returning structured data
Open source Golang LLM Proxy, Agent SDK with Restate & Temporal support for durable agent loop
ToolOps is a framework-agnostic middleware SDK that treats every tool call as a first-class operation. By wrapping your tools in a single decorator, you instantly upgrade them with industrial-grade caching, resilience, and observability.
Swift Agent Package
Bones for your agents — composable async agentic AI framework for Rust
Open-source AI Agent platform built on .NET — design, test, and deploy agent workflows
FastAPI-based boilerplate for building LangGraph-powered agents with streaming, observability, and modularity in mind.
Next Generation Agent Runtime / 次世代Agent运行时
HAMLET is a lightweight, all-in-one framework for building and iterating on LLM agents. It lets you define agents, launch a GUI, instrument runs, and fine-tune models via SFT and RLVR.
Official AI SDK by Ampersand
Full-stack AI agent on LangChain / LangGraph & Next.js — chat, RAG knowledge bases.
A local agent operating environment: pick your model, install tools like apps, choose a coordination pattern. Work finishes as files on your machine — no vendor harness.
Building AI Agents and Workflows with LangGraph
LangGraph integration for Azure Functions Python v2 — deploy compiled graphs as HTTP endpoints
GASADK: Agent Development Kit for Google Apps Script. Build AI agents with Gemini API, MCP, A2A, Agent Skills, Human-in-the-Loop (HITL) suspension/resumption, token quota safeguards, and dynamic Google API MCP servers.
Self-hosted AI agent platform — multi-provider, multi-user, MCP-native, with skills, artifacts, and GDPR by design.
Rust toolkit for building LLM agent applications, e.g.: coding agents, assistant CLIs and multi-agent tools.
Flow-driven recursive skill evolution for agentic LLM orchestration.
A lightweight, enterprise-ready multi-agent orchestration framework for the .NET ecosystem. Build autonomous AI agents, equip them with tools, and orchestrate complex RAG workflows in C#.
Agent SDK for Go - with Temporal & Restate support for durable execution, multi-agent support, and OTeL tracing support
DSPy-native autonomous AI agent runtime — describe your goal, Arachne weaves the agent graph, executes with full observability, and evolves on failure.
langchain框架的agent,功能很基础,建议用Jupyter运行,python版
contenox - an agent harness for policy-bound, vendor-agnostic AI-assisted software engineering.
The ACRYL Blends framework moved into the ACRYL monorepo: github.com/acryldev/acryl/tree/main/framework (@acryldev/blends, @acryldev/create-blends). Archived.
A universal git-native AI agent framework — written in Rust. Single binary. Zero dependencies. 383 models. Blazing fast.
InstantNeo: Instant agents as the building blocks of intelligent systems. A Python library for creating LLM-based agents with granular control and simple composition.
Durable Execution Framework for Go
TypeScript port of CosmosShadow/GeneralAgent
Custom tools for LangChain
Building a Multi agent using Agno framework with Groq models for web search and financial data analysis
Stateful AI agents for Go and Postgres, transaction-safe.
TypeScript agent framework for building production-grade, type-safe AI applications the pydantic ai way
Llama Agent Kit is an open-source Node.js toolkit for building memory-enabled AI agents powered by Ollama. It supports conversation threads, lightweight JSONL memory, and tool calls (e.g., weather, time, reservations), making it easy to integrate LLM agents into your own projects.
Building effective agents patterns implemented with Dapr Agents
Design-time compiler for AI agents that turns intent into reviewable, governable agent architectures (no runtime execution).
The only AI stack nestled on a biodiverse agentic kernel framework
Enables LLM integration with OpenAPI-defined services through function-calling JSON
TypeScript AI toolkit
LLM agent for Mini Micro
About A visual interface for creating and customizing LLM agents using drag-and-drop components. Designed for both developers and non-developers.
Using LangGraph Builder and Studio to build amazing Agentic Systems
Open Core agentic specialist scaffold with functioning routing and tool calling, for building emergent systems with LangGraph.
Perl Framework for AI - Langertha - the viking of AI
Open-source infrastructure for autonomous AI agents. Memory, messaging, task queues, and marketplace in one API.
Production-ready Python framework for AI agents with built-in guardrails, audit logging, cost tracking, and hybrid RAG. Supports OpenAI, Anthropic, Gemini, Ollama. By NichevLabs.
Ship customer-facing AI with isolation, spend controls, and provenance.
Strands Agents in Rust
AgentMap: Build and deploy LangGraph workflows from CSV files. Create complex LLM agent graphs without coding, convert simple spreadsheets into powerful AI agents, and orchestrate multi-agent systems with ease. Integrates with OpenAI, Anthropic, and Google AI models. Includes CLI and FastAPI server for quick deployment.
Production-ready agentic AI framework. High-performance, lightweight, simple. Built-in safety, memory, and 4 reasoning patterns. Ships to production fast.
一个轻量级agent harness框架,用于学习与实践个人agent助手架构设计,基于ReAct架构,由中间路由层连接客户端与底层组件,实现了多模型适配、多平台适配和会话管理。
Not the official LangGraph Rust implementation, but the basic core features are already implemented.
gradio mcp-server-track custom-component-track agent-demo-track region:us
Extremely fast & token-frugal agentic framework for small or hardware constrained LLMs. Run agents in a cave with a box of scrap. 3 Tokens per action or bust!.
TypeScript AI agent framework — 40+ LLM providers, 100+ tools, multi-agent orchestration, RAG, guardrails, circuit breakers, HITL, budget enforcement. Open-source CrewAI / LangChain alternative. — For Building Production-Grade Multi Agents in Minutes at Scale
Code for paper "Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval"
A Java library to create reliable agents
Provider-agnostic TypeScript agent SDK — pluggable providers, built-in tools, skills, memory, and MCP
Spring AI vs LangChain4j vs SAA 三框架同台对比(配套篇2)
Building applications with LLMs through composability
A minimal yet ready-to-use AI agent harness, built on best practices for frontier models.
Open-source Python framework to build, orchestrate and deploy AI agents: multi-provider, tool calling, RAG memory and desktop distribution.
Open developer platform for evidence-bearing digital enterprise twins and operational world models.
Highly customizable Agent Library
The TypeScript/JavaScript monorepo for Proficient AI
Experimental agent runtime for persistent characters. Derived from nanobot and Hermes Agent.
The lightweight framework for real-time routing based AI agents.
Ship product, not plumbing. Open source framework for AI-first SaaS — identity, OAuth, API auth, webhooks, notifications, and agents in one stack.
🔮 quami.io | Kwami's web2 platform
F# pipeline engine for multi-stage AI workflows
A comprehensive starter template for building AI-powered applications with the Mastra framework. This kit provides everything you need to quickly develop and deploy AI agents and workflows.
reShapr website and documentation: turn your APIs AI-Native, without rebuilding them
Agentrail is an open-source agent harness framework for building, hosting, and orchestrating tool-using AI agents.
🐙 Interfaces (aka `into`) is the quickest way to make Large Language Models do things. Get started in 3 lines of code!
Showcase using Langchain in a React Native application
This is a test version of the agent_toolkit in langchain. Please do not use it in production.
Easily build and operate generative AI applications. Create Assistants API and GPTs based on any LLMs.
Built with Gemini API, LangChain, Chainlit, and Python, this multimodal assistant explores AI tool integration driven by curiosity about multimodal capabilities. It demonstrates modern AI development by combining cutting-edge multimodal AI with practical user interface design.
Langchain 🦜 running🏃♀️ on express including file reader and history management
Gradio UI to load crewAI configuration from excel xls and generate the python code. The source of the crews is in the xls. It allows for quick prototyping and iterations without having to edit code,
Extending the capabilities of LLMs using Planning agents and using "knowledge providers"
A High-Performance AI Agent Framework based on SBERT & SpaCy
Develop an AI agent that leverages the Google Gemini API to perform various tasks, process data, and enhance decision-making capabilities. The AI agent will integrate with Gemini's capabilities, such as natural language understanding, machine learning models, and data analysis features, to automate tasks and optimize workflows.
A dynamic, industry-agnostic AI agent framework designed for seamless integration across multiple AI providers and models.
Sample projects repository for Syn Bot Channels.
An LLM chatbot augmented by neuro-symbolic rules
A csp adapter for symphony
An AI conversational chat bot project using Microsoft Bot Framework 4.x
This repository demonstrates how to integrate your Dialogflow agent with 3rd-party services services using a Node.JS backend service. Integrating your service allows you to take actions based on end-user expressions and send dynamic responses back to the end-user.
A sample chat bot based on rasa_core and Rasa_NLU_Chi
A chatbot like application; but with a custom command line language backed up by JavaScript
In this model I have created a basic AI chatbot Interface with External plugin abilities; with visual basic An Interface AI_Contracts enables for Intefacing with the AI; Implementing the Interface and placing in the the compiled DLL into the APP\Plugins folder enables for the AI_Interface to discover and call the plugin obtaining a response to be returned to the user; The project was design in 4 stages ; Each stage or milestone enables for the development and extension of the Chatbot to become a enriched product worthy of public release;
OLAMI API Java client library and sample codes
The Chatbot Framework written in Ruby
Timmy is a Pascal unit (i.e. library) for creating chat bots
A simple interface for a finite-state machine
Simple unofficial package to interact with the same API that the Cleverbot website uses for free. This package is inspired from the package that was written in node.js: https://www.npmjs.com/package/cleverbot-free
NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis, classification, summarization, paraphrasing, intent classification, product description and ad generation, chatbot, grammar and spelling correction, keywords and keyphrases extraction, text generation, image generation, code generation, and much more...