Python agents

transformers safetensors qwen3 feature-extraction dflash speculative-decoding

transformers safetensors qwen3 text-generation code-generation svg

gradio 日本語 Japanese leaderboard language:日本語 language:Japanese region:us

Desktop provider switcher for Claude Code and Codex. Keep every endpoint, API key, and model in one place, switch the active provider in one click, and probe latency before you start. Atomic writes and rolling backups keep your configs safe. Python + Next.js in a native OS webview.

Developed a Multi-Agent Research Assistant that coordinates specialized AI agents to search, analyze, summarize, and synthesize information from multiple sources, delivering comprehensive, citation-backed research reports and actionable insights.

Runnable examples for AI agent identity & compliance — certificate issuance, scope enforcement, and integrations for LangChain, CrewAI, Next.js & more.

gguf baichuan chinese text-generation zh en

CLI & async Python library for free AI chat, image & video generation.

Codex long-task compaction continuity and subagent prompt configuration guide

Coding agent harness, achieved SWE Bench Lite resolve rate of 52.4%

An institutional-intelligence operating system: a council of 14 agents that remembers every deliberation, grades its own predictions against reality, and revises what it believes. Runs on your machine — Ollama, llama.cpp, or any cloud API.

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

Hashtag is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

AI context engine for Power BI models — turns .pbit/.pbip (TMDL) into indexed, queryable context for LLM agents (MCP server, CLI, docs). Zero dependencies.

A collection of AI agent skills for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contained and tested.

Codex Skill for choosing and coordinating the smallest safe Agent setup.

Telegram bridge for Claude Code: resume any CLI session, per-topic chats, local whisper voice, inline-button approvals, live status

A production-ready, multi-channel AI agent for AIOps, Kubernetes management, and automated remediation — built on FastAPI with support for GitHub Models and Google Gemini LLM backends.

Local-first evaluation framework for RAG systems and AI Agents. 18+ metrics, CLI + SDK, framework-agnostic. The pytest of AI evaluation.

Production-grade multi-agent LangGraph template — per-run cost caps, canary pack versioning, Helm/KEDA, 800+ tests

A production-grade LLM System Design platform & interactive lab. Features a pure-Python LLM serving, RAG, routing, safety, and agent control plane (150+ offline tests) plus a LangChain + Streamlit UI with local Ollama models.

Local-first YouTube outlier research — find the videos that outperform their channels, and learn why

mlx safetensors qwen3_5_moe optiq code text-generation

影刀 xbot AI Agent 开发知识库｜影刀编码版 API、RPA 自动化、浏览器、Excel/WPS、市场指令、Claude Code 与 Codex

Automate AliExpress product listing — 1688 sourcing → Dianxiaomi ERP → AliExpress publish. AI browser automation for cross-border e-commerce. 速卖通自动上架工作流：1688采集→店小秘→速卖通发布。

Pair GPT‑5.6 Sol High orchestration with GPT‑5.6 Luna Max workers for bounded Codex tasks—with safe custom-agent setup, explicit guardrails, and parent verification.

Local-first provenance manifests and optional AI audits for research evidence bundles

Source code for "Terminal Agents Suffice for Enterprise Automation"

Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.

ELI5 — A Claude Code skill that explains anything to anyone: kids, managers, engineers, parents. Adapts tone, vocabulary, and analogies to match the audience.

yogsgehlot/Chatbot-Song-Recommender-System

Agente autónomo para LALIGA Fantasy: lee el juego, decide y actúa (pujas, ventas, clausulazos, alineación). Python stdlib + agente LLM opcional (Hermes) + UI de supervisión.

The coding agent that never clocks out.

Agentic coding in the terminal: the model writes its own multi-agent workflows (Gigacode). Provider-agnostic, local-first, 15+ model providers, MCP support.

Bring any Character.AI persona into Discord as a real webhook — with its name, avatar, and personality. Supports search, follow modes, streaming replies, and regeneration.

A developer-focused chatbot agent that answers technical questions.

Local AI Agent Runtime

WarpFusion Discord Tech Support Bot

Open-source persistent memory infrastructure for LLM applications.🐬

This repository contains the code for our paper "Augmenting Black-box LLMs with Medical Textbooks for Clinical Question Answering" [EMNLP 2024]

Local LLM Web search using qwen model and Ollama

Python AI agent Framework

Official onboarding skill for HWPX document automation with AI agents.

EXODUS is a lightweight, modular, open-source AI cybersecurity framework. Create and share your agents, add capabilities by creating plugins, and automate your agent teams for pentesting, reconnaissance, vulnerability discovery, and much more.

An advanced embodied AI agent with personality-driven interactions, multi-modal perception (vision, speech), autonomous task execution, and real-time voice synthesis. Inspired by robotics subsumption architectures, it bridges cognitive reasoning, behavioral decision-making, and virtual/physical body control for immersive AI experiences.

An AI agent for coding and others

Progressive memory layer for AI agents with Header+Content indexing, chain recall, and file-first governance.

一个轻量级的同openclaw相似的超级助手，帮助你操作系统、管理编辑文件等。可连接飞书远程操纵服务器。适合个人开发者使用的超级智能体。

Claude Code plugin that reviews every edit in plain English so you approve or undo with full context.

a small, hackable agent CLI in Python, with explicit control via tools, permissions, and hooks

The official SDKs for Anchor API.

Let's Qitos! A torch-like agent-native framework for researchers.

Build your resume one and only once. An experimental project to use chatGPT multi-agent system to tailor content in your resume for any jobs.

Bayesian decision theory engine for AI agents — Beta posteriors, VOI, and EU maximisation. Foundation for credence-router.

Open-source framework for building and testing LLM-powered applications: IRIS (single-agent orchestration), AETHER (declarative multi-agent systems), and AEGIS (adversarial security testing). Developed at MSU Denver's Community-Centered Computing (C3) Lab.

Provides personalized diet and workout recommendations based on user input. The recommendations are generated using a language model (LLM) for a more interactive experience.

Generate/view WNBA stats, analytics, player comparison, chatbot, and AI insights

Langchain最实用的基础案例，可复制粘贴直接使用。The simplest and most practical code demonstration, you can directly copy and paste to run.

SwiftDocAutomator is an AI-powered tool that streamlines the generation of clear and concise documentation comments for Swift code, following Apple and Swift best practices.

Open Source bro of my conversational agent. https://github.com/mfmezger/conversational-agent-langchain

Using large language models to maintain AI_CHANGELOG.md

Debug RAG pipelines with just 2 lines of code

Create informative READMEs effortlessly using AI-driven templates with the README Creator powered by Language Model (LLM). Simplify documentation and enhance project communication.

A RAG Proof of Concept that delivers comprehensive, context-aware insights on healthcare data privacy through a novel knowledge tree.

AI Video Analyzer & Chat Agent is a robust AI application built with Streamlit, Agno, & Langchain's DuckDuckGo Tool. Integrating Gemini 1.5 Flash, it enables video analysis, insight extraction, and AI-powered chat with features like content analysis, real-time web searches, and multi-modal analysis for research, education, and interactive learning.

This project aims to compare different Retrieval-Augmented Generation (RAG) frameworks in terms of speed and performance.

Demonstration of LLM integration into a lex bot using Lambda codehooks and a Sagemaker endpoint.

Repo for HAICOSYSTEM

Runtime-first agent harness for official coding CLIs, chat transports, background tasks, and controlled write-back.

Experimenting with meta-learning approaches to opponent modelling in MARL. Building upon previous public implementations of MADDPG and M3DDPG.

Developing powerful AI assistants and agents using Genesis and Agentic-RAG.

Validate that supporting text quotes in your data actually appear in their cited references

Your agentic API security engineer. Built by the community, for builders who care about security but don't have unlimited time or budget. Point it at your API docs it hunts down the deep vulnerabilities that actually get you breached.

CLAPP: CLASS LLM Agent for Pair Programming

Kairos: An autonomous development supervisor powered by Context Engineering. It provides a living memory and a contextual constitution for your projects to prevent AI context loss.

模块化 AI Coding Skills 仓库，覆盖开发工具、自动化、Obsidian 与视频处理场景

MCP server for French tax calculations and information - enables AI assistants to provide accurate French tax guidance

Okra, your all in one personal AI assistant

An LLM agent to query any github repo - Ask questions, features, gaps, improvements

JAIvus is a ChatGPT powered personal assistant implemented in python and deployed as streamlit app

LLM Assistent with Chat Integration

A Natural Language Generation System

A simple rule based chatbot to connect to slack using python.

A simple but useful chatbot based on gpt-3.5-turbo and whisper-1.

Kayo-The-Bot is an AI-powered food ordering chatbot that uses NLP techniques to interact with users, present menus, handle orders, and calculate prices. It's integrated with Telegram for a seamless chat experience.

Chatbot that answers OpenStreetMap-related queries powered by Rasa Open Source.

A personalized chatbot designed to answer queries related to a specific company's products and services, using a predefined knowledge base and an API for text generation.

Friendly Chatbot using Deep Neural Network, Specifically Sequence to Sequence Model and Movie Dialogue Corpus

Bot Telegram for OpenAI

Discord AI bot with a hybrid command system, imagination generation, free LLM model, mention recognition, smart message handling, channel-specific responses, GPT integration, secure credential management, & web access for unparalleled functionality.

Local-first RAG platform — Ollama + Qdrant + Redis + MinIO. No cloud, no API keys, runs entirely on your machine.

An emotion-aware AI chatbot named Shylpiee that detects user emotions and generates contextually appropriate responses using Python and HTML.

Enhanced Note-Taking Experience with Artificial Intelligence

A Signal chatbot to broadcast Tor bridges in countries where Tor relays are blocked/monitored

Open-source, knowledge-grounded conversational assistant

Sales Agent Streamlit chatbot

一个python版flask web项目,同时也对接了CAS单点登录,简单集成chatterbot和qqbot的智能聊天机器人。

A modern and functional chat assistant based on Local LLM that streamlines internal processes. Weather, internal information, support requests, document uploads, and more, all on one screen!

A GPT-2 bot trained on my bosses tweets, and a guide to making your own

When an audio message is received, the bot downloads the audio file, converts it to a numpy array, loads the Whisper model, transcribes the audio, and sends back the result as a text message. The bot uses the Matrix Client from the mautrix library to interact with Matrix.