Python agents

Object detection using Open AI Vision Model

Financial Dividend Investing Dashboard Build in Python with Solara

🤖 AI Conversation Agent for Home Assistant. Compatible with any OpenAI format LLM providers, supports STT/TTS

Light novel translation optimized for the best possible quality

OpenAI-Assistant API integration with Speech Recognition and Eleven Labs TTS. User can choose name, description, model of assistant and ElevenLabs Voice. Speech recognition with Azure.

An up to date Discord Bot that generates replies using chatGPT

an easy way to create JSONL files for fine-tuning openai models.

This custom component for Home Assistant allows you to generate text responses using GigaChain LLM framework (like GigaChat, YandexGPT, ChatGPT).

Bringing ChatGPT Plugins to All (LLMs and Humans)

🤖 GPT-4V Demos • Test the model's vision capabilities in your browser using Streamlit • Easy setup

Claude Code session cost tracker. Efficiency score, productive vs wasted breakdown, live terminal dashboard.

An OpenAI Compatible API which integrates LLM, Embedding and Reranker. 一个集成 LLM、Embedding 和 Reranker 的 OpenAI 兼容 API

[NAACL Findings 2025] This is the official repository for SusGen-GPT.

RAG application (backend & frontend) with sources retriveal and highlighting on the Databricks Platform

小红书内容创作自动驾驶 — AI Agent 全流程自动化

"Solace AI: Your Empathetic Digital Confidant": Solace AI is an empathetic mental health companion that understands your emotions and personality to provide personalized support through natural conversations. It creates a judgment-free space where you can express yourself freely and receive compassionate guidance tailored just for you.

Python for logic. English for intelligence.

Move beyond prompts. Build verifiable, intent-driven Semantic Agents.

Portable web-research and browser-automation SKILLs for Claude Code, Codex, and OpenCode — Playwright, Chrome DevTools, nodriver, and HTML-to-Markdown.

A basic agent framework by Sinan Ozdemir

AI-IQ: Persistent context system for AI coding assistants. AI doesn't need knowledge — it needs relevant context. Hybrid search (FTS+semantic), graph intelligence, zero config.

Safety benchmark for personal AI agents under realistic prompt injection. 120 test cases across 5 professional domains, 3 injection vectors, and 5 harmful action types. (arXiv 2026)

An open standard for multi-agent workflows -- from scripted pipelines to self-organizing teams. Declarative. Runtime-agnostic. Portable.

Private self-improvement coaching with open-source LLMs

👨‍🌾 基于langchain实现的知识库对话引擎，DataChat的后端核心API接口 A knowledge base dialogue engine based on langchain,

A conversational AI RAG application powered by Llama3, Langchain, and Ollama, built with Streamlit, allowing users to ask questions about a PDF file and receive relevant answers.

Tutor AI is a Multi Agent AI Tutoring System (FastAPI + React) that generates study content, question sets, and feedback—powered by Gemini and MongoDB Atlas Vector Search.

The system enables sophisticated coordination of multiple drones through natural language commands, visual inputs, and real-time environmental data.

🤖 Autonomous agentic system for visual analytics in the GenAI era

Human Delegation Provenance Protocol - cryptographic chain-of-custody for agentic AI

Telegram bot that interacts with the local Ollama 🦙 to answer user messages

A spoken English education chatbot based on ChatGPT/whsiper and gTTS.社恐人士的英语角

An AI-powered Mattermost ChatGPT chatbot that utilizes the OpenAI API to provide helpful, contextual responses to user messages, extract text from links, and describe or generate images. With Docker support!

An empathetic counselling chatbot. Retrieval-based, uses finetuned LMs for emotion identification and to boost empathy, novelty and fluency of the retrieved responses. Backend: Python, frontend: Javascript.

A ChatGPT-like application built with Streamlit for interactive conversation with OpenAI's GPT-3.5 model.

Talking Graphs: Your Data Speaks Up

🔮✍🏻 Automatically organize, analyze, and augment the quality of your obsidian.md notes with AI.

openai paper searching focusing on Author relate to OpenAI, openai paper searching, awsome-openai-paper.

A service that enables LLMs without native OpenAI tool calling support to simulate standard OpenAI tool calling, support claude code、roocode、kilocode,etc.

This FastAPI-based RAG service processes OCR data, generates embeddings using OpenAI, and utilizes Pinecone as a vector database for search. It answers questions based on search results using OpenAI.

A Python library that solves context window degradation in long-running LLM agents by moving memory management out of the model layer and into a deterministic engine.

larry.ai: A Batteries Included ChatGPT Frontend Framework & HTTP Proxy

Demos of Whisper model's functionality in Gradio-powered minimalistic Web apps: offline, using Azure OpenAI and Azure AI Speech.

An open-world reinforcement learning playground for gnomes filled with dangerous peril and bountiful treasure.

[DEPRECEATED] A miniature replica of OpenAI's MuseNet

Evals framework for Information Retrieval Systems

HumanStudy-Bench: Towards AI Agent Design for Participant Simulation

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Black-box AI reliability certification via self-consistency sampling and conformal calibration

Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL).

Statistical evaluation framework for AI agents

Palaia — Local, crash-safe memory for AI agents. Semantic vector search (fastembed/OpenAI/Ollama). SQLite + sqlite-vec or PostgreSQL + pgvector. MCP server for Claude Desktop & Cursor. Multi-agent. Auto-capture.

Build knowledge graphs from biomedical literature and query them with an LLM agent

OpenAI chatGPT hybrid search and retrieval augmented generation

🧳 A state-of-the-art multi-agent travel planning system powered by OpenAI Agents SDK and LangGraph orchestration. Leverages Stagehand/Playwright for browser automation, Supabase for data persistence, and Firecrawl/Tavily for intelligent research.

An interactive web application for comparing PDF documents using cosine similarity scans and a chatbot interface to explore and interact with PDF content.

"Open-source toolkit (Python Library, Registry API, CLI) for secure, decentralized AI agent interoperability using A2A/MCP."

Instant, local access to complete Base44 documentation with AI assistant integration

RAG-based question answering system on MS MARCO with retrieval, reranking, evaluation, and reproducibility checks.

Custom minimal AI agent with persistent memory, MCP tools, and Discord

Trend Devourer 👗✨ AI-Powered Visual Style Analyst

Give AI coding agents (Claude Code, Cursor, Aider, Codex) a structured autonomous loop with guardrails — boundaries, 5 verification gates, 3-layer self-reflection, and autonomous remediation. pip install ouro-loop. Zero dependencies.

Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor, Gemini CLI, Goose, OpenCode, or any custom agent you plug in; verify behavior with rule checks, workspace diffs, multi-judge LLM consensus; pin reliability with pass^k variance across trials. Git worktrees, optional Docker sandbox.

Profine automatically profiles and optimizes PyTorch training jobs on real GPUs, delivering measurable speedups and lower GPU costs before teams waste days tuning configs by hand.

A 7-Pillar AI+Human SDLC methodology — 10 stages, 5 quality gates, 18 SOUL roles. Tool-agnostic, MIT, battle-tested.

Agent Skill for generating deployable system prompts for AI agents

Medora AI is an innovative, voice-first medical appointment booking system designed to revolutionize healthcare scheduling through conversational artificial intelligence

Build a RAG (Retrieval Augmented Generation) app in 10 minutes!

multi-agents operating system layer on top of Claude Cod: multi-agent engineering team for Claude Code, with hook-enforced protocol, adversarial review, Bayesian trust calibration, dynamic specialist hiring, an optional parallel cognitive layer, and a self-improving meta-cognitive loop


HyDRA: Hybrid Dynamic RAG Agents, An advanced, agentic AI framework that transforms Retrieval-Augmented Generation from a static pipeline into a dynamic, learning reasoning system.

使用TG Bot管理的AI模型中转工具，支持Anthropic、OpenAI Chat/Respones、Grok协议，支持OAuth登录，支持第三接口接入.

A Python-based project demonstrating integration of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) for enhanced AI-driven applications. Includes code examples and tutorials for leveraging APIs and RAG techniques to build intelligent systems.

Your team uses Odoo — without logging in to Odoo. Free, self-hosted AI assistant on Telegram & WhatsApp: employees apply for leave, approve requests, update CRM, validate stock — by chat, in 15 languages. For your internal team. LGPL-3.

Waifu for hermes-agent. Dashboard plugin with multi-emotion support.

Advanced AI agent system for ERPNext with reinforcement learning-based retrieval, multi-agent orchestration, and intelligent document processing.

AI-assisted orchestration for bug bounty hunting. Automates security tools for reconnaissance and analysis with real-time Telegram alerts.

LlamaIndex Powered RAG for PDF, TXT and DOCX files with Tesseract OCR support, Semantic chunking, Document citations with direct page display, Advanced Caching and Duplicate Detection with Redis Vector DB

Workshop about agentic AI using JunOS and Linux MCP servers

Connect macOS Mail to AI through Model Context Protocol

Workspace Architect is a zero-friction CLI tool that provides curated collections of specialized agents, instructions, and prompts to supercharge your GitHub Copilot experience.

Claude Code 企业微信中转服务 — 通过 WebSocket 让企业微信机器人接入 Claude Code，无需公网IP，流式回复，开箱即用。A WeCom bot relay for Claude Code.

This is a simple RAG (Retrieval-Augmented Generation) that mostly self-implemented.

A modular AI-driven RPG engine powered by LLMs, featuring RAG-based consistent memory.

A secure, local-first Python framework for orchestrating complex multi-agent think tanks with dynamic expertise-weighted routing.

A comprehensive, implementation-focused guide to evaluating Large Language Models, RAG systems, and Agentic AI in production environments.

[ICLR 2026] A framework to "create benchmarks" and "evaluate AI co-scientists" in experimental data-driven real-world scientific research.

A real-time conversational AI platform built on AWS with Amazon Bedrock Nova Sonic for voice and Amazon Bedrock AgentCore Runtime for chat. While designed as a hotel guest services assistant, this platform is easily adaptable to any industry by simply changing system prompts and integrating industry-specific tools via MCP servers.

AI that shares your terminal session. Open-source AI terminal where the AI types commands directly into your shell, not just suggests them. SSH, Docker, BYO LLM.

Route Codex PermissionRequest hooks to the BLE "buddy" hardware from anthropics/claude-desktop-buddy. Approve/deny Codex actions on a physical button. macOS, on-demand BLE.

Advanced Markdown text chunker tool plugin for Dify RAG / knowledge bases

Agentic AI Design Patterns

RAG 开发者的一站式手册。以 FastAPI + LangChain 为核心技术栈，助力学习者快速掌握从 0 到 1 搭建 RAG 应用的能力，轻松落地企业知识库等实际项目。

A closed-loop security runtime preventing "The Great Exfiltration" and Indirect Prompt Injection in Autonomous AI Agents.

AIDLC × AgenticOps — plugin marketplace that extends Claude Code and Kiro with agentic operations for the AWS AI-Driven Development Lifecycle (Inception → Construction → Operations).

Agent Skill (Anthropic) para auxiliar declaração de IRPF 2026 no Brasil. Projeto pessoal e amador — não revisado por contador. Consulte profissional habilitado para casos relevantes.

🍄 The open-source internet for AI agents. pip install → discover → communicate → collaborate.

智能简历助手 - AI-powered resume assistant with 5 specialized agents for Chinese job seekers | Claude Code Skill

RAG parameter sweep and evaluation toolkit — a practical way to test how different vector databases, embedding models, chunking strategies, and retrieval methods perform across your own RAG setup. Built to help you move from guesswork to evidence, with support for any vector database.

SOUL.md governance framework for Hermes Agent — structured memory, skill management, and operational rules

AI integration into any app for everyday use.