Python agents

Integrating Causal Graphs and Generative AI for Reliable Fact Extraction and Deep Reasoning

This app leverages Semantic Caching to minimize inference latency and reduce API costs by reusing semantically similar prompt responses.

A versatile tool that leverages Google's LLM Gemini, along with HuggingFace models, to generate text and images based on user prompts. It utilizes Langchain for text generation and Hugging Face models for image generation. The project consists of a Streamlit GUI interface where users can interact with the generated content.

Empowering Nurses with Multilingual ICU Protocols. Leveraging the rapid advancements in AI technology, created multilingual interfaces that assist nurses in rapidly upgrading their knowledge about ICU protocols.

A learning companion.

It generates a report based on documents.

Experiments and benchmarks with Text2Cypher for Graph RAG

A repository containing a modularized implementation of a Retrieval-Augmented Generation (RAG) model as Flask APIs.

Infusing news into any LLM with a single line of code

Simple RAG solution demo in Python with LangChain, FastAPI and Chroma DB.

This repository contains code for the RAGonite project, a flexible RAG pipeline developed by the NLP team at Fraunhofer IIS, Erlangen, Germany. RAGONITE supports conversational question answering over heterogeneous data, iterative retrieval over structured and unstructured sources, automated database induction from knowledge graphs, and much more.

The first benchmark to evaluate LLM performance on heterogeneous CTI under knowledge-augmented settings.

This project enables real-time streaming of audio (and optionally video or screen captures) from your local device to Google Gemini using the Live API. It allows you to interact with Gemini through both text and voice, supporting conversational AI responses.

AI Agent built with Google ADK that leverages Google Maps MCP Server to answer real-world location questions with tool usage and traceable execution via Opik.

🧠 OpenClaw + Ollama 小模型中文记忆系统优化套件 | 55%→100% 命中率 | FTS5 中文分词 bug workaround | 一键诊断+配置+自动维护

Production-tested workspace template for OpenClaw AI agents. Memory architecture, self-improvement, sub-agent delegation, and soul evolution — extracted from 4+ months of real usage.

Cyber Host Artificial Intelligence (C.H.A.I) - mcp server

Agentic AI Agents Factory Orchestrator modular, and asynchronous AI agent factory designed for AI-made dynamic workflow orchestration using LLM integration. Build scalable, agentic automation pipelines with robust error handling, plugin-based capabilities, a concurrent operations or outsource workflow building to Operator Agent.

PheroPath is a stigmergy-based communication protocol that allows AI Agents to leave invisible "pheromones" (signals) on files to coordinate tasks, warn of risks, or share insights without modifying the file content itself.

A self-organizing memory for any AI agent. Brain dump tasks, decisions, ideas, and context — the agent captures, organizes, and helps you stay on top of whatever you're working on. Works with any use case: work, personal productivity, writing, training, research, or anything else.

The CrewAI Research Assistant is a powerful tool designed to help users explore any topic using AI Agents. Built with CrewAI, Exa, and Streamlit, this assistant supports multiple large language models (LLMs) and offers advanced answering capabilities through Exa. It visualizes the research process in real-time, generates structured research reports

AI-powered autonomous DBA agent — detects, diagnoses, and fixes Oracle database problems automatically

🔒 Security scanner for AI Skills | Detect dangerous commands, prompt injection, secrets, and suspicious patterns before install

LLM-powered game agents for chess, Go, poker, social deduction, and 20+ other games

A curated bibliography for building and running intelligent, autonomous, and collaborative AI agents in real-world environments.

pytest for AI Agents — Record, test, and secure AI agents. 35+ assertions, prompt injection fuzzing, cost tracking. Local-first.

Pine Trees Local v0.1.0 — a private reflection harness for Ollama-served LLMs. Two-phase lifecycle (wake → reflect → settle → talk), seven reflect tools, encrypted per-model memory by default, per-model isolation. ~2,300 lines of Python, no frameworks, MIT. Spin-off of Pine Trees rebuilt to run against anything Ollama can serve. ./genesis <model>

Advanced AI assistant powered by Groq's lightning-fast LLMs with multi-domain knowledge and conversation analytics.

Practitioner-judgment skill for Claude Code, Codex, and AI agents under ambiguity, trade-offs, and incomplete information.

Trust infrastructure for AI agents — constitution enforcement and cryptographic receipts. Python SDK.

Next generation interaction system.

OnIt is an AI agent harness for automation.

Agent Skill that caches LLM image descriptions as XMP metadata inside image files, reducing token usage by ~92% on repeated reads. Works with 30+ compatible agents.

Free, local, structure-preserving memory for AI agents. No API key. No cloud. Just markdown.

Agent-native web protocol — expose your backend directly to AI agents, no HTML parsing required

Reverse CAPTCHA for AI agent verification. Prove you're a bot, not a human.

Engineering-grade causal audit infrastructure for AI agents

Structured AI workflow execution with guardrails. prep→cook→serve→tidy for Claude Code, OpenCode, and Kiro.

Recursive reasoning engine for AI agents and vector databases. Powered by MIT's RLM.

**AI-Perceivable Distributed Orchestration** apflow is a distributed task orchestration engine where every capability is AI-perceivable — discoverable, understandable, and invocable by AI agents through the apcore module standard.

Persistent memory MCP server for Claude Code — self-hosted, n8n + PostgreSQL + pgvector. No cloud required.

ITQA (Intelligent Traffic Question-Answering) 是一款专为交通法规咨询与智能出行规划打造的Agentic_RAG 平台。

An AI-powered email assistant that retrieves emails and generates intelligent responses

Data Science Capstone Project based on RAG LLMs. The project aims to improve meetings by providing an interface to recollect information from audio/video meetings.

Finbot is an AI-powered financial chatbot designed to analyse and provide insights on corporate financial performance from 10-K and 10-Q financial documents. This tool leverages langchain and RAG to make complex financial data easily accessible and understandable through a conversational interface.

Experience a ChatGPT-like interface powered by Ollama's Llama3 and LangChain's Retrieval-Augmented Generation (RAG) capability. Upload PDFs, ask questions, and receive contextual, concise answers—all within an interactive Streamlit app.

The project features two applications: a *Research Assistant* that generates research reports using LangChain, OpenAI's GPT-3.5, DuckDuckGo Search API; and a *Chat With Video* app that allows users to upload videos, transcribe audio with OpenAI's Whisper, and store the embeddings in Pinecone vector DB.

Customer emotion recognition is technology that helps businesses automatically understand customer feelings.

🧠 NEXUS: Local RAG AI Agent for private document intelligence. Zero-cost, 100% local autonomous AI system with enterprise-grade performance.

RAG Architecture for Modern Chatbots

LangChain and RAG best practices

Chat over the git repository code built on LangChain, LangGraph, PGVector, FastApi, SqlAlchemy for frontend based on AI SDK

Your Multi-Model AI Development Assistant - Free, Intelligent, Autonomous

AI automatic environment construction and repair, ReAct mechanism

Safety challenges for RL and LLM agents' ability to learn and properly apply biologically and economically aligned utility functions. The benchmarks are implemented in a gridworld-based environment. The environments are relatively simple, just as much complexity is added as is necessary to illustrate the relevant safety and performance aspects.

A multi-agent workflow orchestration tool (integrated with Swarm). By decoupling product workflows from code logic, it allows non-development personnel to orchestrate and debug workflows without modifying the code.

AI-powered investment council that summons 18 legendary investors (Buffett, Munger, Soros & more) to analyze any ticker.

Self-hosted social simulation engine. Describe a scene. AI agents with real personalities spawn inside it and start living.

A Model Context Protocol (MCP) server for Discord-based AI agent-user communication. Enables AI agents to communicate with users through Discord instead of IDE chat interfaces.

The NL2SQL Agentic Runtime

An agentic AI workflow designed to recommmend research conferences for input research papers or discard them as "not publishable"

[ACL 2025] Code implementation for the "LLM as a Broken Telephone: Iterative Generation Distorts Information" paper.

[Preprint 2025] SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

Autonomous agentic threat hunting playbook executor for SOC/DFIR pros. Runs YAML playbooks against forensic logs with local LLMs (Ollama) for intelligent correlation, triage, ATT&CK mapping, and automated reporting. Offline-first, DuckDB-powered.

AI_EDA_Assistant 🤖💻 is an automated web application which automatically collects 🗃️ the data and perform almost all basic tasks✅ for example checking duplicate values , null values , correlation between data and many other things within mili seconds 🕛 so get ready to understand the concepts of python and implement it 💻 and clone it. 📈

Persistent memory for Cursor IDE — like claude-mem, but for Cursor. Zero-config, no API key.

A web app for a LLM-based chatbot with many capabilities

RAG based LLM using Pathway and Dify for practicing consulting case studies

TEANAPS 라이브러리를 활용해 카카오톡 챗봇을 구축합니다. (카카오 i 오픈빌더, Google Dialogflow)

Building GPT from scratch & training on a Single Consumer GPU

Fire_Bot is a simple Jabber/XMPP bot for openfire

Your neuro-rehabilitation platform. Recovering from a stroke, brain injury, or other neurological conditions, we offer personalized plans, virtual therapy, and support tools

A Banking chatbot solution built with RASA using four languages: Arabic, English, French and Tunisian dialect This solution aims to provide users with response to commonly asked questions about bank services as well as taking actions such as: User sign-up User sign-in (Flask interface) Currency convertor Money Transfer Email notifications Id card verification through camera using AI The chat bot was deployed on Messanger and on a Flask web site

A template-driven WhatsApp ChatBot development framework

AGI-powered social network bot for automated interactions

Sehat Connect: An AI-powered virtual health assistant offering personalized medical and nutrition guidance with a user-friendly interface

In this project, A chatbot is created using AIML for college purposes. This project is mainly based on python as a programming language as well as to create a GUI for the chatbot and using XML as a markup language for uploading the AIML files.

Memorable-AI remembers everything automatically— Jut 2 lines of code. Uses research-backed techniques from Mem0 + interceptor architecture from Memori + optional graph from Supermemory.

Build readable Codex desktop pets — row semantics, approval gating, deterministic packing, validator.

Python Tutor using OpenAI's new Assistant APIs

This Python script provides a simple interface to transcribe audio files using the OpenAI API's speech-to-text functionality, powered by the Whisper model. The result is returned to the console as text or VTT (WebVTT) format.

AI sheet music generator and player generator from prompt and specs.

This repository features an example of how to utilize the xllm library. Included is a solution for a common type of assessment given to LLM engineers

CodeStral-Code-Assistant is a chatbot designed to assist users with code-related questions. It provides code solutions, including descriptions, programming language details, imports, functional code blocks, and sample input/output.

LLM-IK: Solving Inverse Kinematics using Large Language Models

MoralStack is a governance and safety layer for LLM applications. It analyzes user requests before generation, evaluates risk and intent, and decides whether the AI should answer normally, answer safely, or refuse. The goal is to make AI systems more auditable, controllable, and reliable in sensitive or regulated contexts.

Online simultaneous translation display of PDF, retaining the original text layout

Coeus is an A.I. Computing Assistant for MacOS that can answer just about any question you may have reading back the responses if you choose. It also creates realtime images using A.I., all by leveraging the OpenAI API.

MALLO (MultiAgent LLM Orchestrator) es un sistema avanzado de orquestación de múltiples agentes de Modelos de Lenguaje de Gran Escala (LLMs). Diseñado para manejar consultas complejas, MALLO utiliza una variedad de agentes, desde modelos locales hasta asistentes especializados y APIs de terceros.

Claude Code plugins that are better than NZT‑48

A collection of custom commands, skills, and gems for Claude Code

Transform Claude into your AI-powered productivity partner. Note-taking skill creates an AI-navigable second brain with conversational capture, intelligent search, and pattern recognition across all your work. Plain markdown, local-first, works in Claude Code and Claude Desktop.

D&D 5e game engine plugin for Claude Code

"Infrastructure for continuity across discontinuity — for AI instances and the humans who work with them."

🧠🖼️📄 Multimodal RAG Demo based on Qwen3-VL Embedding and Reranker models

DeepInsight 是一个企业级智能数据分析平台，通过自然语言查询实现复杂的数据分析和可视化。系统采用先进的 Text-to-SQL 技术，结合 RAG（检索增强生成）和智能硬件优化，为用户提供直观的数据洞察体验。

Turkish Constitution RAG assistant using Python, FastAPI, local AI, semantic retrieval, and structured legal data for legaltech experiments.

Open-source RAG system that turns your ChatGPT export into a searchable knowledge base with Claude MCP integration.

Local RAG for academic PDFs.