Python agents

Create, store and enable embeddings related features like semantic search, RAG, recommendation, image to image and more

End To End Advanced Rag Project Using Open Source LLM models and Groq Inferencing

Modern Local Code Editor with local ai assistant with multiple options. Currently Support C language. Using a C Programming Book for knowledge

This project, Auditron, was created as part of the Challenge-Based Learning (CBL) AI project at Esprit School of Engineering - Tunisia.

a local, multilingual (EN/IT) study assistant that indexes course materials and answers questions with citations—using multilingual-e5-base for retrieval and Llama 3.1-8B for generation. CLI-only.

A Langchain implementation for Memvid, enabling efficient video-based document storage and retrieval using vector embeddings.

Vietnamese Legal Chatbot is a chatbot designed to assist users with legal inquiries in Vietnamese.

VerixAI: An intelligent document analysis platform using RAG for querying large document collections and receiving AI-generated answers with verifiable citations.

AlightRAG: Association Reasoning Based Multi-Hop Question Answering System（基于联系式推理的多跳问题回答系统）

VIC-style tiered retrieval demo with native KIOXIA AiSAQ for low-DRAM, storage-aware semantic search.

This is a legal AI system that generates executive summaries and clause-grounded answers from long TOS documents. It is optimized for CPU-only deployement

understand the structure of markdown and its elements (tables, diagrams,...) for search and retrieval augmented generation

A chatbot for Kaggle competition inquiries, using LangChain for processing, a Mistral model for responses, and Retrieval-Augmented Generation (RAG) for dynamic data. It features a FastAPI backend and a Streamlit front end for real-time interaction.

김필주, 이재강, 문재경, 이재희, 박송원

Persistent, correctable memory for AI. Corrections prevent repeat mistakes. Zero dependencies. Works with any LLM. pip install neveronce

Deterministic method-first retrieval for AI coding agents.

Read-only MCP server exposing a local Calibre library (search, details, FTS, samples)

A modern, real-time quota monitor for MiniMax API. Features a semi-transparent floating UI, precise RPM tracking, smooth animations, and persistent configuration.

BETO formalizes the ignorance of an AI. Materializes raw semantic intent into fully traceable, auditable software.

Selenium WebDriver MCP server for AI agents and LLM-powered browser automation

Extract your honne — the real working self underneath tatemae — from your Claude transcripts.

Use Finnhubs API for SuperAGI agents.

The true Natural-language programming with LLM and AutoGPT

Trying to make an automatic Objective completion AI Hierarchy

Local agent OS for solo builders: launchd-managed Claude Code/Codex fleets, git-worktree isolation, Slack reporting, safety gates, and reproducible setup.

Exploring the cognitive architecture and design of a multi-agent system leveraging Large Language Models (LLMs) for scalable workflows.

Budgeted LLM runs with hard caps + typed outcomes + async job mode. Python/CLI/HTTP. OpenAI-compatible.

An agentic AI system for intelligent, resume-driven personalized outreach using LLMs. It reads resume, finds relavent HRs and pushes generated mails to google mail's drafts

A reinforcement learning agent that learns to intelligently shape electricity demand, reducing peak loads and optimizing energy consumption in real-time.

Agentic LLM system for binary exploitation using MCP tools and pwntools

A starter template for building powerful, local, tool-calling LLM agents using LangGraph and llama-cpp-python

An autonomous AI security agent capable of performing end-to-end penetration testing. Orchestrates network reconnaissance, vulnerability assessment, and exploitation using a multi-agent architecture and local large language models.

Agent runtime tracing + LLM-mock replay for Python. Self-contained HTML reports, pytest snapshot testing, cost tracking. No SaaS.

Semantic mistake-memory and guardrail for AI agents. Stops agents from repeating the same failures using causal graphs and semantic matching. Supports MCP, LangGraph, and in-process Python.

Long-horizon planning engine for LLM agents

Polymarket research MCP server with 10 tools (odds, orderbook, spread, history) + autonomous trading bot framework. Claude Sonnet decision-making, pluggable strategies, SQLite persistence

探索在日常开发中，让 AI 编程助手保持上下文连贯与执行纪律的协作工作流。Exploring practical collaboration patterns for AI coding assistants.

[ACL 2026 Main] MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization

Hand-crafted Paperclip Agent Companies, ready to deploy. Install: npx companies.sh add stubbi/companies/<slug>

The Ultimate AI Arsenal of 16+ Elite, Production-Ready Skills for Claude LLM. Transform Your AI into a Self-Evolving Autonomous Agent Engineered for Full-Scale Web Engineering, Claude Code Expert, MCP Builder & Data Supremacy, and Algorithmic Art at Unmatched Precision. 🚀

Observability and influence tracing infrastructure for multi-agent AI systems.

Runtime defense for AI agents. 24 inline defenses, 3 output scanners, MCP server, framework adapters.

🎭 3 AI agents roast your city's weather & pollution in sarcastic Tamil meme style! Built with CrewAI, Open-Meteo APIs (free), and Groq/Gemini/OpenAI/Ollama. Part of the AgentVerse series by @explainpannu.

LifeOps AI: An Agentic AI System acting as your Personal Operations Manager. Built using CrewAI, Google Gemini 1.5 Flash, and Streamlit. It integrates Health, Finance, and Study domains with cross-domain reasoning.

CrewAI-Powered Blog Automation Suite - Workflow for automated content creation, research, SEO optimization, and publishing to Ghost CMS.

Automated user behavior analysis system based on CrewAI multi-agent framework, integrating Google Gemini and Volcano ARK APIs for intelligent GA4 data analysis and business insights

Hawkeye is an automated, agentic-based penetration testing tool powered by CrewAI and Google Gemini 1.5 Flash.

An AI-powered multi-agent system for automated code reviews. Uses specialized LLM agents to analyze security, performance, style, and best practices.

ResumeMatch is an AI-powered resume analysis tool designed to drastically improve a candidate's chances of landing a job interview by calculating the fit between a resume and a specific job description.

A Python-based project comparing CrewAI, LangGraph, and AutoGen by implementing the same stock analysis workflow across all three. Each agent framework generates a BUY / SELL / HOLD recommendation with rationale—ideal for exploring multi-agent design patterns and orchestration styles.

ArXiv MCP server built for multi-agent systems like Magentic-UI and AutoGen

Reference distributed multi-agent platform using AutoGen, FastAPI, Redis, WebSockets, and semantic agent discovery.

🤖 AI-Powered Backend Builder Multi-agent + multi-tool system using AutoGen, Gemini & Groq to automate production-ready backend development. Features 4 specialized AI agents, MCP integration, and end-to-end automation. Perfect for rapid API development with built-in security & testing. 🔧 Tech: Python, AutoGen, Gemini, Groq, MCP, FastAPI, Docker

🚀 slackAgent: Your AI-powered Slack assistant! Built with LlamaIndex, ChromaDB, and OpenAI embeddings, it delivers instant answers from your documents via a sleek Slack bot or Streamlit web UI. Automate workflows with n8n, expose local APIs with ngrok, and query with ease using FastAPI. Join the future of intelligent chatbots! 🤖💬

Multi-agent LLM trading framework: hard-discipline (code) + soft-judgment (LLM) hybrid. Best risk-adjusted performance on NVDA 6-month benchmark — +43.9% / -3.2% MDD, beating RSI, Momentum, Buy & Hold, and single-agent LLM. Raw returns top all baselines once the position cap is lifted. Adapted from TauricResearch/TradingAgents, built on LangGraph.

🎥 Google Meet for AI agents — coordinate many agents from a single primary over a simple HTTP API, watched live in the browser. Self-hosted, 100% local.

Local-first AI agent framework with approval gates, audit trails, and resumable multi-surface workflows.

Programmable digital creatures with habits, memory, and autonomous behavior.

Flat AI swarm: identical agents, no roles, one shared Neo4j mind

A bio-inspired multi-agent defense framework with self-diagnosis, self-healing, and self-evolution capabilities, built with LangGraph

Multi-agent AI that turns prompts into structured, impact-driven decisions.

Interactive multi-persona AI conversation platform using Ollama. Create AI personas with distinct roles and watch them engage in dynamic conversations with @mention support, configurable context, and advanced log analysis.

把单个 AI 助手升级为可扩展的多专家协作运行时， 带工业级记忆检索、会话管理和完整的开发者可观测性。

A lightweight CLI to orchestrate Gemini and GPT using your local files as a shared blackboard.

Personal Claude Code plugin marketplace. Includes tmux-pair: writer/reviewer pairs and writer/reviewer/orchestrator triples in fresh git worktrees, wired up via tmux.

From Copilot to Autopilot -- Autonomous multi-agent orchestration for Claude Code

FinSight AI is a sophisticated financial decision-support system that combines Traditional Quantitative Finance, Machine Learning (Quantile Regression), and Generative AI (LLM Agents) to provide probabilistic forecasts of company performance.

🚁 Drone RL: Autonomous quadrotor trained with PPO/SAC/DreamerV3/MARL from scratch on CPU | PyBullet + Gazebo Harmonic | Hover 100% | Navigation 92% | Storm 8m/s 95% | Weather system | Multi-Agent Swarm

A multi-agent platform built on the top of the pystarworldsturbo library. Part of the Intelligent Agents course taught at Royal Holloway University of London.

Multi-agent AI music discovery assistant that turns natural-language mood prompts into ranked Spotify recommendations and one-click playlist creation.

[ICML'26] AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web

Multi-agent AI development workflow framework for GitHub Copilot CLI — 10 specialized agents with Board-based orchestration, parallel execution & quality gates

AI Collaboration System / 智能多 Agent 协作编排框架

把一队编码任务交给一条级联的 AI agent：Root 读取静态队列，派出隔离的 Leader，Leader 动态拆成隔离的 Executor 并行产出 patch。基于 OMP native subagent 的结构性隔离。

Multi-agent orchestration mesh with routing, workflows, and A2A gateway

Self-Adaptive Generation Engine — Agent Development Kit with cognitive routing, evolutionary topology, formal verification, and 4-tier memory

Multi-Agent Retrieval-Augmented Generation (RAG) Customer Support System using Python, LangChain, and LangGraph.

Escaping the Median Trap in LLM Ideation — Semantic Tabu, Solution Taxonomy, and Orthogonal Insight Protocol tested across 196 solutions (8 conditions)

Transform epidemic modeling research papers into interactive public health simulators. Powered by Claude Opus 4.6 — 1M context, extended thinking, 128K output.

Framework of 43 specialized AI agents for marketing, sales, content and development automation — powered by OpenClaw & Claude AI

Application-layer protocol for AI agents serving different principals to coordinate over shared state. 📦 PyPI: https://pypi.org/project/mpac/ · Spec, Python + TypeScript reference implementations, two-machine demo.

AI-Powered Solana Trading Intelligence | Multi-Agent DeepSeek AI | Real-Time Rug Detection | Reactive Learning System | React Dashboard | 73 Tests

Self-hosted autonomous AI agent — runs on your PC, controls your environment, connects to any MCP server.

Autonomous research agent that runs locally on a Mac via LM Studio. Plans, fetches, synthesizes, and cites — overnight, $0, with real source attribution. Plug in OpenRouter for cloud-grade synthesis when needed.

LangChain integration for EnigmAgent — resolve {{PLACEHOLDER}} secrets at the LLM boundary so models never see real API keys

Powerful Python agent runtime with tools, MCP, Hooks, Skills, Rag, memory, sessions, reasoning, and streaming packets.

An AI-powered, multi-agent strategic intelligence platform that delivers real-time market analysis, competitive intelligence, financial insights, and actionable recommendations. Configured once by an admin — every employee sees a live, auto-refreshing intelligence dashboard for their company.

RudraX Army — 349 specialist agents, 43 model providers, 9 tactical squads and one open-source command center. Developed by Lalit Pandit.

Agents should execute whenever possible — open registry of reusable AI agent skills and capability definitions

Multi-agent system built with Claude and MCP featuring 7 specialized agents (chatbot, security researcher, business advisor, task manager, REST API), 29 shared tools across web analysis, memory, RAG, email, and communication. Includes hot-reload development, OAuth infrastructure, and remote MCP support for distributed deployments.

SkillEngine — framework-agnostic skills engine for LLM agents. Claude Code-like experience on any model.

Pi agent skills for specialized workflows and automation

An operating system for Claude Code. Skills, hooks (MCR), and a lean-context framework for smarter AI coding sessions.

Recurrsive Context Agent

Typed atomic notes in a graph — a Zettelkasten that scales. Knowledge construction with Building Blocks, Folgezettel trails, and the Dialectic Knowledge System (DKS).

Provide ready-to-use plugins, hooks, and commands to enhance Claude Code sessions with data mining, automation, and integration tools.

Offline MCP Server for Qt 4.8, Qt 5, or Qt 6 documentation

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.

Agentic harness for iteratively improving a local LLM's structured-output quality, scored against a frontier-model gold standard.