Python agents

LLM tools

An extensible Python CLI program for interfacing with LLM providers. Has file, chat, and ask modes, and can save conversations in a human-readable format for external consumption.

build a chatbot for Retrieval Augmented Generation using SurrealDB and OpenAI's API.

chat-E-AI是一款AI驱动的聊天机器人。它能将AI嵌入你的聊天频道，使你和你朋友更能够像和其他人聊天一样，来获取AI的问答响应。

A RAG app to ask questions about rows in a Neon Serverless Postgres database table. Try the live demo using the link

Persistent memory for AI agents. They learn once, remember forever.

Use the OpenAI TTS (text-to-speech) model to read any selected text on your Mac with a keyboard shortcut. Bring your own OpenAI API key.

Make OpenAI batch easy to use.

⭐ Integrates Claude Desktop with Google and Atlassian workspaces

Session and event store for MCP server, also allows distributed coordination between servers.

🔧 Turn any CLI or MCP server into an Agent Skill — zero process overhead, 98% fewer tokens. Kill MCP zombie processes. Works with Claude Code, Codex, Gemini CLI & 26+ platforms.

AI Embedder Engine: An open-source Python engine for generating embeddings from PDFs, storing them in Parquet, and indexing with FAISS for semantic search.

Context-first autonomous multi-agent system

on-device Flask-based web application designed to help you create, manage, and visualize notes effectively and securely

LangGraph RAG pipeline using DeepSeek‑V2 (67B) via Hugging Face Transformers.

Chat with Lex! A RAG app, using HyDE with milvus DB for vector store, VLLM for LLM inference, and FastEmbed for Embeddings!

Simple RAG system

A Genshin Impact Book Question Answer Project supported by LLM

local-first pipeline that turns notes into a research-style draft: extract keywords → fetch arXiv → rank (SPECTER) → summarize (PEGASUS). No chat, no API keys.

A command line utility that queries websites for answers using a local LLM

An interactive chatbot system designed to help resolve student queries efficiently. The system features both user and admin interfaces, allowing for dynamic query handling and response management.

Universal documentation extraction tool

WovenSnips: A Lightweight, Free, and Open-source Implementation of Retrieval-Augmented Generation (RAG) using Straico API

Substrate Python SDK

TinyRag is a minimal Python library for retrieval-augmented generation. It offers easy document ingestion, automatic text extraction, embedding generation, and retrieval with vector stores. Designed for quick setup and flexible provider configuration, TinyRag enables fast, contextual responses from language models.

A tool for evaluating and tracking your RAG experiments. This repo contains the Python SDK for logging to Tonic Validate.

A tool for scraping web documentation using Crawl4AI, converting it to Markdown, and preparing it for integration with local LLMs (like Ollama) to enhance their knowledge for learning and "vibe coding" workflows.

Structure-aware text chunking library for code, prose, and markup files. Intelligently splits files into context-rich chunks while preserving semantic boundaries. Supports 15+ programming languages, deterministic output, and zero external dependencies. Perfect for RAG systems, code analysis, and LLM context optimization.

腾飞智能助手是基于钉钉平台的AI助手，集成了大型语言模型、知识库、对话记忆储存和多种工具能力，提供智能问答、任务处理和信息检索服务。深度集成钉钉构建智能待办/日程/日志/审批系统等，实现自然语言到API的自动转换，用户操作步骤减少70%。

RagE (RAG Engine) - A tool supporting the construction and training of components of the Retrieval-Augmented-Generation (RAG) model. It also facilitates the rapid development of Q&A systems and chatbots following the RAG model.

End-to-end architecture for document-centric conversational AI

Muzlin: a filtering toolset for semantic machine learning

SitemapRAG is an open-source tool designed to leverage your website's sitemap as a Retrieval-Augmented Generation (RAG) source. It empowers developers to build intelligent, context-aware applications by extracting, indexing, and querying content directly from a sitemap.

Retrieval-Augmented Generation (RAG) + Multi-Agent Systems (MAS)

RAG-Enhanced Fake News Predictor analyzes news content using multi-API verification, AI assessment, and machine learning models. It cross-checks articles against a knowledge base, validates news authenticity, and provides detailed insights, helping users identify fake or misleading information efficiently.

This repository provides a template for building Large Language Model (LLM) powered microservices using FastAPI. It's designed to help you quickly set up and deploy AI-driven APIs that leverage the power of LLMs like GPT-3, GPT-4, Claude or other similar models.

Library that enables Streaming for OpenAI Assistants API using Astra Assistants

Automated pipeline for real-time market analysis: Scrape live job data, generate structured CSVs, and create analytics scripts using Kiro with Bright Data MCP.

EDAgent is a skill-based LLM agent designed to assist EDA research workflows, routing user requests to appropriate skills for code analysis, debugging, experiment setup, and research automation.

AI agent skill that creates formal, verifiable proofs of claims — every fact computed or cited, never asserted

A multi-server Discord control plane that exposes Discord operations as MCP tools, resources, and prompts for AI clients, with a built-in conversational AI agent.

AI agent skill: tell Claude Code, Codex, Gemini or OpenClaw to upload your recording to YouTube — it downloads from Drive, transcribes, generates timestamps and metadata automatically.

A smart, conversational interface for automotive part queries. Leverages Amazon Bedrock and OpenSearch to provide accurate part information, compatibility checks, and detailed responses. Streamlines the process of finding and verifying car parts for owners and mechanics.

14 Claude Code skills for content creation, knowledge management, and media automation

Empowering agents with a unique persona and ethical cognitive intelligence.

基于 LangGraph + MCP + FastAPI(SSE) + Streamlit 的本地知识库问答助手

An AI-powered system for generating complete eBooks from simple prompts. This tool uses Google's Gemini AI models to create professional-quality eBooks with minimal human input.

🚀 Веб-интерфейс для AI-агента с возможностью выполнения Python-кода, управления файлами и работы с веб-контентом

a tool that reduces token usage and request waste in coding-agent workflows by selecting, compressing, caching, and budgeting repository context

The Missing sudo Command for AI Agents.

NeuroCore is a self-hosted, modular AI agent framework for building persistent, tool-using autonomous systems. It combines workflows, long-term memory, RAG, and a plugin-based architecture into a unified platform for advanced AI applications.

LLM framework for long running agents

Agentic OS that runs on any Linux — curated knowledge API for AI agents: MCP tools, skill packs, semantic search. Works with Claude Code, Cursor, Cline, Windsurf.

Secure runtime for multi-agent AI. Kernel sandboxing (seccomp-bpf), real-time PII redaction, Merkle audit trails.

I got laid off and built a robot army to find my next job. Multi-agent job search automation for Claude Code.

Agentic stack-neutral starter pack with instant project auto-mapping. Perfect bootstrap for Claude Code, Cursor, Hermes and multi-agents — full context from minute one.

Let AI agents create compliant Google Ads - crawl websites, validate limits, generate copy-paste ads. Works with Claude, Cursor, Cline & more

Declarative framework for orchestrating multi-model Agentic pipelines with context engineering and quality gates.

A composite ai framework for agentic AI

Stay current on high-quality work at the Operations Research × AI intersection. A research agent performs deep, multi-pass analysis of each paper, scores relevance, and curates what matters, helping you spot trends and gaps faster.

AI powered ATS compatible resume generator

Multi-step Agentic Self-Corrective RAG with websearch

A production-style, agentic AI trading bot that combines LLM reasoning, sentiment analysis, market indicators, and broker APIs to make and (optionally) execute trading decisions.

Building a chatbot using Streamlit, LangChain, and SQLite

An AI-based tool that automates market research survey generation and provides a simple UI using streamlit

A curated collection of production-ready agentic AI projects—showcasing automation, LLMs, and intelligent agents for real-world applications.

EduGenius is an innovative AI-powered tutoring platform addressing challenges in modern education by offering personalized and efficient tutoring for O/Level students in mathematics.

Customer Support Chatbot that answer all your question about what your purchase. The Chatbot is build with Langchain, chromaDB, Groq, HuggingFace, Streamlit, and etc.

CogniVault is a modular, CLI-based multi-agent assistant designed to help you reflect, refine, and organize your thoughts

🥇 Raise Your Hack Paris - Concierge AI Travel Agent

In the deepest waters of the ocean, the orca navigates with intelligence, curiosity, and precision — the same spirit that guides every research journey.

A cloud-native RAG system for research paper analysis featuring structured PDF ingestion via LangExtract, high-speed Groq (Llama 3.3) inference, and Supabase vector storage.

Create agentic systems from scratch and monitor them using LangGraph studio

Multi-agent medical assistant for medical Q&A, RAG, web retrieval, and medical image analysis with human review.

This repository contains Model Context Protocol (MCP) server implementations that demonstrate how to create and integrate custom tools and data sources with AI applications. MCP is an open-source standard that enables AI applications like Claude or ChatGPT to connect to external systems, data sources, and tools in a standardized way.

Use your ComfyUI anywhere. ComfyPlus_Anywhere is an open-source plugin that lets you deploy ComfyUI on any computer and remotely access it from any device with a simple Token connection.

A Automated Ai Stock report builder using Crewai + Django+Yfinance

Artificial Collective consciousness: A New Way To Study, Learn and Have A Fun!

Penjaga — a doctrine for running multi-persona AI agents on Facebook Pages in Bahasa Melayu, at production scale, without getting banned. Architecture, runbooks, and war stories from Pendakwah Teknologi. Intelligence layer withheld.

nod is a platform-agnostic, rule-based linter that ensures AI/LLM specifications contain critical security and compliance elements before any agentic or automated development begins.

Self-hosted AI control plane for intelligent local LLM orchestration. OpenAI-compatible API · ML-powered multi-model routing · LoRA finetuning · vector memory · RAG

基于MCP（Model Context Protocol）的中国A股市场智能分析系统，通过多个专业智能体的协作和辩论，为投资决策提供全面的分析支持。（主要是基于我之前开发的FinanceMCP进行开发的）

A general-purpose distributed agent cluster framework

MCP server: semantic search (RAG) across Obsidian, Joplin & any markdown vault with live sync, quality-based chunking & pluggable post-processing

This is a multi-node collaborative travel planning agent based on LangGraph, used to improve my own agent development skills. You can refer to my development history. I hope my mistakes can help you.

Large Language Model Frameworks curated List

Agent Policy Engine is an AI agent enforcement runtime (PEP) that prevents untrusted data from becoming executable authority in AI agents

Memory Layer for AI Assistants: Persistent memory, semantic retrieval, and evaluation tooling for building assistants that remember users over time.

Discord Bot that inadvertently passed the Turing test against five people

Backend source code of the wahl.chat platform. Our mission: Make politics more accessible.

Сhatbot based on chatGPT for telegram groups. Сreate your own unique chatbot for your group chats, wich can act as user. It is free, unlimited and does not require API keys.

A csp adapter for slack

A framework to create chatbots in the easiest way

This project leverages SOTA techniques to retrieve relevant information from large datasets and generate coherent, contextually accurate text that includes image data references.

A ollama based chatbot. We use llama3 8b model via groq for this project.

Python interface to make requests from EVDS API Server. Fast, efficient and user friendly solution. Caches results to avoid redundant requests. Creates excel files reading configuration text file that can be easily created from the menu or console. Provides visual menu to the user. It is extendable and importable for user's own python projects.

Train expert conversational role-play LLMs with synthetic data

MeowBot! A YouTube Chat Bot For Live Streams.

Enterprise LLM Evaluation & Responsible AI Framework — Benchmark bias, hallucination, PII leakage, and toxicity across Healthcare, BFSI, Retail & Legal industries. Supports OpenAI, Anthropic, Gemini & HuggingFace. Python SDK + CLI + Web Dashboard. 191 tests. Compliance-ready reports.

End-to-end ASO toolkit for App Store Optimization — 6-stage pipeline (industry refresh → app analysis → locale research → draft → audit → write+verify), Snowball stem + CJK substring detection, free iTunes Search API + Google Suggest validation. Claude Code skill + standalone Python scripts.