Python agents

Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid STS + NLI. Works with LangChain, LlamaIndex, or any RAG pipeline. pip install longtracer

NotionGPT is an AI that writes and organizes content in Notion for you.

NexDR (Nex Deep Research), a leading deep research agent that autonomously investigates complex topics and generates rich, structured reports.

Three working examples showing how AI agent development evolved - from traditional RAG to batteries-included SDKs and skill-based frameworks

A platform for Interactive AI-assisted Hypothesis Generation [ACL 2025]

[ACL 2025] iAgent: LLM Agent as a Shield between User and Recommender Systems

🚀 cto.new 免费反代 | OpenAI & Anthropic 兼容 API | GPT-5.4 / GLM-5.1 账号池自动轮询 · JWT 刷新 · Dashboard UI · 批量注册 ｜ Free OpenAI/Anthropic-compatible API proxy with account pool auto-rotation, JWT refresh, bulk registration & real-time dashboard. ⚠️ 不支持 agent 工具调用 / No function calling support.

对 Karpathy 的 LLM Wiki 理念的一次完整实践测试——让 LLM Agent 自动构建和维护一个结构化、互相链接的 Markdown 知识库。

Official implementation of the paper "Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM Collaboration". (by Yanjun Chen)

这个项目是一个医疗智能诊断助手系统，简单说就是：> 你输入病人的症状，AI系统会像一个经验丰富的医生团队一样，查阅大量病例文献，进行分析推理，然后给出诊断建议和治疗方案。

A Claude Code skill for integrating AI with Jira, Confluence, and Bitbucket. Automate Atlassian workflows using Jira Skills, Confluence Skills and Bitbucket Skills. Supports Cloud & Data Center.

[RA-L 2026] ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation

A real-time voice AI system that integrates OpenAI's Realtime API, Llama3 with Twilio Voice to create intelligent voice conversations.

Local CLI for automating Classic Outlook on Windows via COM. Includes a Claude Code/Codex Skill for AI-assisted email management with safety guardrails.

Agent-driven Android ANR evidence extraction and AI-assisted root cause analysis pipeline.

Real-time system audio translation for macOS — translate any audio (YouTube, podcasts, meetings) live on screen with OpenAI or Google Gemini. On-device speech recognition; optional low-latency realtime mode.

PRO-V: An Efficient Program Generation Multi-Agent System for Automatic RTL Verification

Files-first operating system for internet businesses: research, decisions, bets, pushes, and outputs in markdown/git, with an mb CLI and agent workflows that hide the plumbing.

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

Multi-agent architecture for Opencode — cost-optimized model routing, parallel specialist execution, dev tools, and a self-maintaining project wiki

An opinionated, agentic life-OS for Claude Code — a markdown vault with daily/weekly/quarterly review skills baked in. Includes the feedback layer most templates skip.

The harness engineering framework for coding agents

Hermes Agent-focused architecture and runtime health checks

Learning chatbot that can automatically fetch lecture transcript

Create your own Alibaba dataset and interact with it in plain English.

A collection of custom AI agent skills for Google Antigravity and the open agent skills ecosystem.

Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.

Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README

AI 驾驶的自愈式 A 股模拟盘交易赛车 · Self-healing paper-trading race car driven by AI agents

Detect phantom IAM users, decode leaked AWS Bedrock and Claude Platform API keys, and prevent LLMjacking. CLI + SCPs + SIEM detection rules.

AI skill package for paid social operators: Meta performance analysis, creative angle research, KPI workbooks, and UGC scriptwriting.

AI-powered code review agent for GitHub pull requests. Self-hosted GitHub App using PI.

Talk to your Claude Code by voice — a real voice call with your terminal agent. Local whisper STT, edge-tts voice, no API key.

AgentMill - Enterprise-Grade AI Agent Platform & Agent Factory for Building Custom Digital Employees

Claude Code plugin: AI agent for your Obsidian vault — process books, courses, papers, YouTube into connected notes

Single-file, zero-dependency AI coding agent for the terminal.

Turn a jailbroken Kindle into a local e-ink side display.

Edu-RAG：面向 K12 / 学科教育场景的轻量化 RAG 智能助教开源框架，依托教材、教辅知识库实现精准答疑、习题解析与个性化导学，有效抑制大模型知识幻觉，开箱即用快速落地 AI 教育应用

AI Infrastructure & DevOps Roadmap covering Linux, Kubernetes, Local LLMs, AI Agents, RAG, AI Observability, Security, and production-grade AI platform engineering projects.

Live context engine for AI agents: resolve verified workspace state before the context window opens. Pairs with Perseus Vault for persistent encrypted memory. Local-first, MIT. pip install perseus-ctx

领域无关的多 agent UI 自动化测试编排骨架，用 Claude Code 驱动「探索页面→设计用例→写测试→审查」流水线

gradio mcp-server-track mcp nasa space hackathon-2025 astronomy asteroids

docker agent-demo-track security mcp vulnerability-scanner ai-agent region:us

streamlit region:us

streamlit region:us

streamlit region:us

streamlit region:us

transformers safetensors gpt_bigcode text-generation conversational arxiv:2407.00121

transformers safetensors internlm2 text-generation conversational custom_code

transformers safetensors qwen text-generation custom_code zh

Model Optimizer safetensors qwen3_moe nvidia ModelOpt Qwen3

gguf quantized moe vlm vision agentic

gguf code codeqwen chat qwen qwen-coder

mlx safetensors qwen3_moe text-generation conversational base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct

transformers gguf llama llama-2 text-generation code

Research-backed Harness Engineering study repo with a runnable Python MVP built around Plan -> Work -> Review.

Multi-session IDALib MCP router for coding agents. Analyze multiple binaries in parallel with IDA-compatible reverse engineering tools.

Claim-level provenance for multi-agent knowledge systems

Turn a slide mockup image into an editable PPTX: native text + semantic draggable sprites + inpainted background. Agent-as-VLM skill for Claude Code / Codex / any CLI agent.

Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collisions.

CareerDesk: Your Personal Career Assistant

Production-grade SEO + GEO content factory for Claude Code — research, write, fact-check, optimize, publish to WordPress, monitor. Battle-tested by Loamwright 沃匠 SEO agency.

EduFlow 畅学 — AI-driven student self-learning platform. AI agents assist, students lead. Next.js + FastAPI + LangGraph.

A multi-agent travel assistant system built using the **Agent2Agent (A2A)** protocol and **MCP (Model Context Protocol)**

A powerful Claude Code skill that provides safe disk space analysis, junk file cleaning, and real-time monitoring across Windows, Linux, and macOS.

A simple, local-first RAG framework for building document Q&A applications

[ACL 2026]From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning

Demo of Agentic RAG

Benchmarked implementations of Offline Multi-Agent RL Algorithms based on PyMARL codebase.

Goal of project is to write programs that will allow multiple agents to find optimal paths from their start location to their goal location such that all agents are able to move simultaneously. Various algorithms will be explored such as Prioritized Planning, Conflict-Based Search (CBS), A* Search. Additionally, a paper that describes Safe Interval Path Planning (SIPP) provided the inspiration for writing of SIPP versions of Prioritized Planning and CBS.

Intelligent search engine/QA module that uses GPT models to provide accurate, relevant & recent answers from Google News/Web, & can directly answer user queries using GPT's knowledge.

Enhance your knowledge in medical research with the help of LLM and RAG.

reproduce some RL or Multi-Agent models

📮 Dialogflow + Sendgrid = AI Mailbox

ChattierGPT - A Simple and Powerful UI for the ChatGPT API

AI Discord bot with Image Recognition/OCR Capabilities + Image Generation with SDXL For Free!!

Local character AI chatbot with chroma vector store memory and some scripts to process documents for Chroma

This a very basic discord bot linking to GPT3 (openai and AI21). By defaults it is Kirby, but can be any real or virtual bot (just need more or less training prompt).

Action Engine for AI Agents

This collection of AI sub-agents for Claude Code leverages a powerful agent-assembler to dynamically generate a personalized and project-specific AI development team based on your unique tech stack.

Versatile framework designed to streamline the integration of your models, as well as those sourced from Hugging Face, into complex programs

(ACL 2025 Main) Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation

Code for the paper "LASER: LLM Agent with State-Space Exploration for Web Navigation"

本仓库是一个关于 Agent（智能体） 的实验性 DEMO 项目，主要展示如何利用大语言模型（LLM）在计算机上执行“自动化代码编写”、“文件系统探索”等操作。项目基于 DeepSeek R1 系列模型做了一些初步探索，希望借此分享经验与心得，也为更多对 Agent 感兴趣的开发者提供参考。

A framework for creating voice based agents. Integrations LLMs with speech recognition and text-to-speech

(ICLR 2026 Oral) Code for the paper: Reducing Belief Deviation in Reinforcement Learning for Active Reasoning of LLM Agents

LangChain / LangGraph Q&A 에이전트

Local Agentic RAG using Langchain and Agno

WorkBrain is an advanced intelligent agent model that can make autonomous decisions based on input data to achieve automated processing of various tasks. Developed independently by Chengdu Minto Technology Co., Ltd.

Trying to extend AI Agents to a full topology of devices using CML

ML2-Multi Agent Environments

Multi-agent racing tournament on MetaDrive

Negative Update Intervals in Multi-Agent Deep Reinforcement Learning

Use Multi-Agent Deep Deterministic Policy Gradient(DDPG) algorithm to find reasonable paths for ships

A collection of tools that can be used for LLM function calling

This is a security Knowledge Framework chatbot which will answer your queries related to web vulnerabilities.

A proof‑of‑concept C2 framework that uses Server‑Sent Events (SSE) and the MCP protocol for agent registration, command dispatch, and result collection. By tunneling through ngrok, you can quickly expose your C2 server to the public internet for rapid testing and demonstration.

A comprehensive AI solution for saving, sharing, and reusing code materials in your Sublime Text environment, with a powerful integration of AI assistance and Copilot and many LLM models including ChatGPT functionality, specifically designed to enhance your coding workflow.

MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols