Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 46 of 126
Easily manage AI agents backend with this Python library.
Entity-State-Transition-Constraint runtime for production-grade AI agents.
Durable, governed, model-agnostic AI agents in Rust — event-sourced runs, budgets, approvals, MCP, replay evals, and a drop-in OpenAI/Anthropic gateway.
Agent-first TypeScript library for safe SaaS API connectors: typed actions, pagination, retries, rate limits, and LLM tools. MIT.
Build production-grade enterprise agents in minutes, not days, weeks, or months
Starter template + technical guidebook cho AI20K Build Phase — LangGraph agent boilerplate, docs và AI usage logging.
Plurnk engine: an operation language, searchable resources, persistent context, and cooperating workers.
LLM Framework for LLMs
Lightweight (and therefore powerful) Rust agent framework inspired by Browser Use's Agent SDK
Python agent harness — 5 LLM providers, 7 real tools, sub-agent spawning, hooks, skills"
A TypeScript framework for managing AI agent skill packages — install, load, and bind tools for LLM function calling
An example of Amazon Bedrock Agent integration with external APIs via Lambda.
Simple AI-agent Conversation Orchestrator
Autonomous AI agent framework for Python using OpenAI & LangChain — generates app descriptions, architecture outlines, UX flows & code from natural language objectives. Published on PyPI.
Project AI is a platform designed to streamline the creation of AI agents using Google AI Studio. It simplifies the development, training, and deployment of AI models. Currently, the project is in its early stages, with raw files available for initial setup and exploration.
A demonstration of dynamic tool calling with AI Agent using Ollama. Showcases how LLMs can invoke external Python functions in real time to augment their reasoning with live, actionable data.
Whitefurry are an AI builded on Python and it is simple and he will be big every update and he learn from you & using that app make me happy and update it every 2week
An advanced, auditable OpenClaw-based self‑evolving agent framework with practical, human‑centered workflows.
The missing protocol between user requests and AI actions. Standardized intent parsing for every AI system. Converts any input into [Motive] [Scope] [Priority].
Make LLM workflows explicit and deterministic
一个交互式 AI 工作流控制系统框架的早期预览分支。 / Preview fork of an interactive AI workflow cybernetics framework.
Agentic Workflows with Generative AI: Building AI Agents using CrewAI.
gotoHuman Python SDK
Distributed systems reliability patterns applied to LLM agent workflows. NestJS, PostgreSQL, BullMQ, LangGraph, Python/FastAPI.
pingo智能体演示平台
A Go toolbox for building powerful LLM based application
A bridge between Fllama (llama.cpp for Flutter) and Langchain for Dart.
A simple Agent compatible for avalai.ir api
Yet another implementation of task-driven autonomous agents
High-performance LLM orchestration in Rust. Fast RAG, memory, and agents for Python & Node.js.
Architect helps you quickly prototype and validate your ideas for hackathon projects.
GEERS AI 2024
Different AI agent implementations using various frameworks and approaches
Build agents with any framework. Ship them with FastAgentic.
CrewAIMaster transforms any task description into a fully functional, production-ready multi-agent system, making advanced AI orchestration accessible to everyone.
Examples of using AutoGen agents and agentic frameworks. Requires Docker container.
Investigating the usefulness of "AutoGen" by Microsoft. AutoGen is a framework for simplifying the orchestration, optimization, and automation of LLM workflows. This repository contains experiments testing multi-agent coordination, task delegation, and performance benchmarks.
AutoGen Agents Creation and Testing - VibeCoded by a real developer to enable more people to do stuff using vibes.
AutoGen Magentic-One Sample with security best practices.
A zero-dependency Python decorator that hides internal arguments from LLM tool-calling schemas via __signature__ mutation.
A production-ready TypeScript template for building AI agents using LlamaIndex in Blaxel.
Declarative, JSON-native AI agent framework
The engineering-grade AI Agent definition spec the whole industry was missing.
Outcome-driven skill self-evolution framework for AI agents.
A bare-bones Swift agent runtime with built-in tool execution, skill support, conversation-state handling with a unified multi-provider LLM layer (OpenAI-compatible/Responses, Anthropic, Gemini, and MiniMax, plus codex OAuth)
TypeScript AI agent framework where personality is architecture. Specialists, not chatbots.
The first of a kind "AGENT AS A BACKEND" : Advanced AI/ML Agent Framework with TypeScript support, multi-model capabilities, vision controls, and comprehensive AI/ML model support including LLM, SLM, MLM, Vision, ASR, TTS, RL, GNN, RNN, CNN, GAN, Diffusion, Transformer, MLP, Autoencoder, BERT, RAG, Hybrid, Foundation, and fine-tuning
PA3 stands for Python-as-an-Agent
A modern FastAPI template for building AI-powered chat applications with GraphAI. Features streaming responses, Docker deployment, and OpenTelemetry observability out of the box.
This repository contains a minimal chat agent that uses OpenAI's API to engage in a conversational loop, retain history, and apply basic input validation and output sanitization.
Minimal agent runtime for any OpenAI-compatible LLM
An LLM agent library for go
Minimalistic extensible agent for Cloudflare serverless infrastructure
Research and development environment for building autonomous AI agents. Features practical implementations of agentic frameworks, cognitive architectures, and specialized tools for creating AI systems with enhanced reasoning capabilities.
Multi-Agent, Plugin-First Framework
Agent communication UI sdk
Infrastructure for Web4 Autonomous Agents.
Building an AI Agent from scratch 🐥 Designing the brain, memory, tools, and reasoning system step by step.
RustyFlow is a lightweight, high-performance agent framework built in Rust for developers who need reliable, efficient, and type-safe AI workflows. A complete rewrite of the Python-based PocketFlow, RustyFlow brings memory safety, fearless concurrency, and zero-cost abstractions to agent-based systems.
The tool surface every agentic AI framework reimplements.
The repair layer for AI agents. Validates and fixes malformed API calls in <30ms before they crash your production systems.
LLM function calling library
A library to accelerate REST agent app development on top of Express, enabling users to focus on Langgraph agent development.
A starting point for building custom agentic LLM applications using Open Source tooling and models. Incorporates Ollama, Open WebUI, Langchain, Streamlit, Chroma, & PGVector using Docker and Docker Compose and optionally Codespaces.
Backend-agnostic C# library for building stateful AI entities with per-persona memory, tool access, mood systems, and autonomous agent behavior.
Lightweight TypeScript agent framework for building reactive, event-driven systems with trigger-condition-action flows. Zero dependencies, full async support.
Bizy is the first rules and logic layer that machines, engineers and business stakeholders can directly configure and understand.
Full Form : Expert Network for Intelligent Guidance and Multi-task Assistance. Using multiple LLMs, for Conversational as well as Functional Request.
Modular TypeScript SDK for building AI agents — agentic loop, tool use, MCP, streaming, provider-agnostic
Build AI-powered video, voice, and chat applications with real-time intelligence in hours. Self-hosted. No cloud dependencies.
🎭 Portable non-human identity specification (persona.json schema)
*(Under Development) Rockbot Assistant is a web-based AI chatbot platform for conversation management, supporting real-time chat, PDF/text export, and agent selection. Backend is Flask+SQLite; frontend is TypeScript+Vite+Tailwind.
A comprehensive Swift SDK for the Anthropic API
Blazing-fast AI agent framework written in Rust. Simple, fast, and extensible.
Go library for building real-time AI chat applications with streaming responses
用 Go 实现的 Anthropic SDK,支持 Claude 2.1、Claude 3、Claude 3.5(文字和图片)等模型。Anthropic SDK implemented in Go, supporting models such as Claude 2.1, Claude 3, and Claude 3.5 (supports sending images), etc.
Demonstrate how to build a Next.js app with AI chat agents using Cloudflare Workers, Durable Objects, and the Agents SDK for seamless full-stack deployment.
A simple toolkit that provides basic schemas and validation logic for tool calling functionality in Large Language Model applications.
A powerful Custom Tool that enables AI agents to autonomously execute GraphQL queries and mutations. This package allows AI agents to intelligently interact with GraphQL APIs, making decisions about when and how to fetch or modify data through GraphQL endpoints without explicit human intervention.
Allows autoGPT to use absolute paths
I wanted to play with an autonomous AI and I wanted to do it in Ruby...
The true Natural-language programming with LLM and AutoGPT
Trying to make an automatic Objective completion AI Hierarchy
Research framework for adaptive, purposeful agents under uncertainty
Long-horizon planning engine for LLM agents
An LLM agent runtime that treats context like virtual memory: swim-lane paging, semantic retrieval, and an inline stream-marker DSL for runtime control. Multi-provider (Anthropic, OpenAI, Google, xAI, Groq, local). MCP-integrated. Self-modifying agent mode (PLASTIC). Containerized deployment.
Local-first AI agent framework with approval gates, audit trails, and resumable multi-surface workflows.
Programmable digital creatures with habits, memory, and autonomous behavior.
Runnable multi-agent LLM workflow examples in Java — RAG, ticket triage, web research, Slack bot, batch processing — with AgentFlow4J and Spring AI.
Minimal, forkable workspace template for AI agent development. AGENTS.md + SOUL.md + HEARTBEAT.md + MEMORY/ structure.
一个 golang 原生 Agent SDK,支持 multi-agents/skill/spawn 等能力以及全量的中文文档
LangChain integration for EnigmAgent — resolve {{PLACEHOLDER}} secrets at the LLM boundary so models never see real API keys
AI Agent Evolution Model --- AI Behavior Constitution Framework
SkillEngine — framework-agnostic skills engine for LLM agents. Claude Code-like experience on any model.
Minimal AI agent framework in Rust.
Spring AI Alibaba Graph 的声明式编排扩展。| A declarative composition extension for Spring AI Alibaba Graph.
Anytime Verified Agents (AVA) is a framework for building reliable LLM-based reasoning systems that adaptively allocate computational resources under budget constraints. AVA combines adaptive search strategies, uncertainty estimation, and verification cascades to maximize reliability while respecting token, tool-call, and verification budgets.
🐙 Private intelligence, everywhere. Sovereign AI and hybrid infrastructure.