Discover open-source implementations addressing workflow automation with autonomous tool loops, retrieval augmented generation, and custom LLM reasoning.
Learn how to build a governance layer that enforces deterministic policies on AI agents, preventing dangerous actions before they execute..
The AI Financial Coach is a personalized financial advisor powered by Google's ADK (Agent Development Kit) framework. This app provides comprehensive financial analysis and recommendations based on user inputs including income,...
The AI Game Design Agent Team is a collaborative game design system powered by AG2(formerly AutoGen)'s AI Agent framework. This app generates comprehensive game concepts through the coordination of multiple specialized AI agents, each...
The AI Health & Fitness Planner is a personalized health and fitness Agent powered by Agno AI Agent framework. This app generates tailored dietary and fitness plans based on user inputs such as age, weight, height, activity level,...
A multi-agent system built with Google ADK that analyzes photos of your space, creates personalized renovation plans, and generates photorealistic renderings using Gemini 3 Flash and Gemini 3 Pro's multimodal capabilities.
Watch two AI agents battle it out in an epic used car negotiation! Built with Google ADK for the backend agents and AG-UI + CopilotKit for a jaw-dropping reactive frontend.
An intelligent meal planning agent built with Agno that helps you discover recipes, analyze nutrition, estimate costs, and create weekly meal plans based on your ingredients and dietary preferences.
Coordinates specialized AI hiring assistants to parse candidate resumes, conduct automated screening evaluations, and generate structured recruitment scorecards.
A multi-agent AI pipeline that generates competitive sales battle cards in real-time, built with Google ADK and Gemini.
An AI application that simulates a full-service digital agency using multiple AI agents to analyze and plan software projects. Each agent represents a different role in the project lifecycle, from strategic planning to technical...
An Agno agentic system that provides expert software architecture analysis and recommendations using a dual-model approach combining DeepSeek R1's Reasoning and Claude. The system provides detailed technical analysis, implementation...
A Streamlit application that brings together a team of specialized AI teaching agents who collaborate like a professional teaching faculty. Each agent acts as a specialized educator: a curriculum designer, learning path expert, resource...
A multi-agent AI pipeline for startup investment analysis, built with Google ADK, Gemini 3 Pro, Gemini 3 Flash and Nano Banana Pro.
A reference implementation demonstrating how to build a multi-agent pipeline that aggregates technical signals from multiple sources, scores them for relevance, assesses risks, and synthesizes an actionable intelligence digest.
An investor-grade earnings call companion that turns any YouTube earnings call into a playback-synced analyst workspace. Paste a call URL, watch the video, and let ADK agents surface the numbers, tone shifts, filing context, and...
A Streamlit app demonstrating the "Automatic Critique + Improvement Loop" pattern using GPT-OSS via Groq. This demo implements an iterative quality improvement process.
Learn how to build a trust layer for multi-agent systems that enables secure delegation, trust scoring, and policy enforcement between AI agents.
An AI Powered Streamlit application that serves as your personal coding assistant, powered by multiple Agents built on the new o3-mini model. You can also upload an image of a coding problem or describe it in text, and the AI agent will...
A multi-agent design feedback system that evaluates application screenshots and interface mockups using Google Gemini multimodal vision capabilities.
A multi-agent app built on EvoAgentX that turns a single natural-language goal into a working program. It automatically generates a.
A strategic thinking assistant and guided response chatbot that integrates local LLMs to facilitate structured problem-solving and critical analysis.
An AI-powered autonomous fraud investigation agent that cross-references childcare provider licensing records against physical building data to detect anomalies. The agent uses public data — Cook County property records, Illinois DCFS...
This AI-powered investment agent is built with Agno's AgentOS framework that analyzes stocks and generates detailed investment reports. By using GPT-5.2 with Yahoo Finance data, this app provides valuable insights to help you make...
This Streamlit app is an AI-powered movie production assistant that helps bring your movie ideas to life using Claude 3.5 Sonnet model. It automates the process of script writing and casting, allowing you to create compelling movie...
This Streamlit application demonstrates the use of RouteLLM, a system that intelligently routes queries between different language models based on the complexity of the task. It provides a chat interface where users can interact with AI...
A private, browser-based ChatGPT alternative running Llama-3 locally via LM Studio and Streamlit with zero external API dependencies.
An open-source autonomous agent for controlling Windows desktop applications and GUI workflows using computer-use models.
One model is a bottleneck. A team with one brain, twenty hands, and a board advisor is not.
git blame tells you who last changed a line. Commit Archaeologist reconstructs finds the introducing commit, orders later modifications, classifies commit.
Checks a working, staged, saved, or branch diff against a one-line intent. It flags unrelated paths, new dependencies, public API renames, config or CI.
Automatically optimize your agent skills using a multi-agent system built with Google ADK (Agent Development Kit) and Gemini. Upload a skill, let the agents generate test scenarios and evaluation criteria, then watch as three...
How this repo checks that its skills actually work — before they ship and on every change after. Layout: one folder per skill, evals/<skill-name>/.
Demonstrates how to use before and after agent lifecycle callbacks in Google ADK to monitor agent execution timing, manage shared state, and benchmark performance.
Demonstrates how to monitor LLM requests and responses using Google ADK interaction callbacks to track token consumption, calculate API costs, and record latency.
Demonstrates fundamental agent-to-agent task delegation using the OpenAI Agents SDK handoff system. cp ../env.example .env from agent import main.
Demonstrates fundamental session memory management with SQLiteSession for automatic conversation history. cp ../env.example .env from agent import inmemorysessionexample, persistentsessionexample.
Demonstrates manual conversation threading with toinputlist() and automatic management with Sessions. cp ../env.example .env from agent import manualconversationexample, sessionconversationexample.
Demonstrates advanced tracing patterns including custom traces, spans, and workflow organization for complex multi-agent systems. cp ../env.example .env.
Demonstrates the built-in automatic tracing system that captures all agent workflow events without any setup required. cp ../env.example .env.
A Google ADK tutorial demonstrating type-safe email generation using Pydantic schemas and Gemini models to guarantee structured subject and body outputs.
Demonstrates the three execution methods available in the OpenAI Agents SDK: sync, async, and streaming. cp ../env.example .env from agents import Runner.
Demonstrates advanced session memory operations including item manipulation, conversation corrections, and session management. cp ../env.example .env.
Demonstrates managing multiple concurrent sessions for different users, contexts, and conversation types. cp ../env.example .env from agent import multiusersessions, contextbasedsessions.
Demonstrates running multiple agents simultaneously using asyncio.gather() for improved performance and quality through diversity. cp ../env.example .env.
A basic personal assistant agent demonstrating the fundamental concepts of agent creation with the OpenAI Agents SDK. cp ../env.example .env from agents import Runner.
A complex structured output agent demonstrating advanced Pydantic schemas for product review analysis. cp ../env.example .env from agents import Runner.
An ADK agent is a programmable AI assistant that can: Think of it as creating a smart function that uses AI to handle complex tasks. The main building block for creating AI agents in ADK.
An OpenAI agent is a programmable AI assistant that can: Think of it as creating a smart function that uses AI to handle complex tasks.
Learn how to create agents that work with different AI models using OpenRouter. This example shows how ADK can use OpenAI and Anthropic models through separate agent implementations.
Teaches how to create type-safe AI agents using OpenAI Agents SDK and Pydantic models to guarantee consistent, validated JSON responses for application workflows.
Covers execution methods in the OpenAI Agents SDK, explaining synchronous runs, streaming event handling, exception management, and the internal agent execution loop.
InMemorySessionService stores session data in your computer's RAM (memory). This means: from google.adk.sessions import InMemorySessionService.
Demonstrates long-term conversational memory using Google ADK's DatabaseSessionService and SQLite to persist context across application restarts and multiple sessions.
Context management allows you to pass custom data structures to your agents that persist throughout the entire agent execution. Think of context as a shared state container that.
Guardrails are automated safety mechanisms that validate inputs and outputs to ensure AI agents operate within acceptable boundaries. Think of guardrails as safety checkpoints that.
Sessions provide automatic conversation memory that eliminates the need to manually handle .toinputlist() between turns. Think of sessions as a smart conversation database that.
Handoffs enable agent specialization and delegation where agents can transfer tasks to other agents with specific expertise. Think of handoffs as a smart routing system that.
Demonstrates iterative plan refinement using Google ADK's LoopAgent pattern, executing sequential sub-agents in a stateful loop until satisfaction conditions are met.
Multi-agent orchestration enables coordinated AI workflows where multiple specialized agents work together to solve complex problems. Think of orchestration as a conductor leading an orchestra where.
Release Radar is an always-on dependency briefing agent built with Google ADK. It reads requirements.txt or package.json, checks mapped dependencies against GitHub releases, and reports only changes that need attention: breaking...
An advanced Chess game system where two AI agents play chess against each other using Autogen in a streamlit app. It is built with robust move validation and game state management.
An interactive Tic-Tac-Toe game where two AI agents powered by different language models compete against each other built on Agno Agent Framework and Streamlit as UI.
A minimal example demonstrating real-time AI streaming and conversation state management using the Motia framework. streaming-ai-chatbot/.
Welcome to The Magician IA Reader! This project presents a unique application combining the power of Artificial Intelligence with the mystique of tarot reading.
A Retrieval-Augmented Generation assistant that links to your Gmail inbox to answer natural language queries, summarize threads, and surface priority emails.
An agentic canvas application that populates live charts, metrics, and real-time data into an interactive dashboard workspace built with CopilotKit, AG-UI, and Google ADK.
This script demonstrates how to finetune the Llama 3.2 model using the Unsloth library, which makes the process easy and fast. You can run this example to finetune Llama 3.1 1B and 3B models for free in Google Colab.
Minimal example to finetune Google's Gemma 3 Instruct models with Unsloth using 4-bit loading + LoRA. Small, readable, and runnable on a CUDA GPU.
An AI data analysis Agent built using the Agno Agent framework and Openai's gpt-4o model. This agent helps users analyze their data - csv, excel files through natural language queries, powered by OpenAI's language models and DuckDB for...
A Streamlit application that acts as your personal data visualization expert, powered by LLMs. Simply upload your dataset and ask questions in natural language - the AI agent will analyze your data, generate appropriate visualizations,...
An AI agent with its own crypto wallet that pays for the data it needs — no API keys, no subscriptions, no signup. Ask a question in plain English.
A Medical Imaging Diagnosis Agent build on agno powered by Gemini 2.0 Flash that provides AI-assisted analysis of medical images of various scans. The agent acts as a medical imaging diagnosis expert to analyze various types of medical...
Generates customized music tracks from natural language style descriptions using the ModelsLab music synthesis API and GPT-4 in Streamlit.
LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol.
A programming framework for agentic AI.
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption.
Pocket Flow: 100-line LLM framework. Let Agents build Agents!.
非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型，.
MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in the style of a real human. She does not pursue perfection, nor does she seek efficiency; instead, she values warmth, authenticity, and genuine connection.
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
A coding agent for open models like Kimi K3 and GLM 5.3.
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
Official Agnes AI gateway and model catalog for OpenAI-compatible text, image, video, and agent workflows.
Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目，支持在 Mac mini/MacBook 上或通过算力棒本地运行推理，实现纯视觉驱动的跨平台 GUI 自动化操作。数据完全本地处理，支持复杂多步骤任务规划与执行。.
Your Open Autonomous Android Agent — A open-source, self-planning AI assistant powered by local/remote LLMs and accessibility-driven screen automation.
An open-weight 11B model series for long-form and real-time video understanding.
[ICML 2026] ByteDance's All-in-One Video Generation Model for Human-Object Interaction Video Generation.
HEX is a whole-body vision-language-action framework for full-sized humanoid robots.
Browser Harness | Self-healing harness that enables LLMs to complete any task.
An open-source reference implementation of Midscene for AI and LLM workflows.
MagenticLite is an experimental agent that works across the browser and local file system.
Fara1.5 – A family of frontier computer use agent models.
AI agents can now use real Android and iOS apps, just like a human.
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime.
The batteries-included agent harness.
Autonomous Hacking Agent for Red Team.
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
An open-source system for building persistent worlds with multimodal AI.
