Python agents

Fully local AI for Polish legal case files - zero fabricated citations by construction. Free; please support a Wroclaw animal shelter instead.

A zero-dependency Python tool to resolve relative Markdown links and inline images as Base64 strings for RAG and Multimodal LLMs.

Ontology-aligned middleware for agentic graph memory. Python SDK, runtime, and reproducible indexing/query experiments.

A langGraph-powered multi-agent RAG assistant for warranty, return, and consumer decision workflow.

203 deep-dive tutorials for AI agents, LLM frameworks, coding tools, MCP, and open-source developer platforms

💠 Provide users with the ability to generate, edit and filter images using the DALL-E 3 API provided by OpenAI, all from the command line.

Build-An-LLM-RAG-Chatbot-With-LangChain-Python

Submission for MAVEN: Multi-Agent Variational Exploration

Automatically extracts, processes, and indexes code snippets from GitHub repositories into a searchable vector database.

This repository holds files for the simple chatbot wrote in TensorFlow 1.4, with attention mechanism and bucketing.

Chat with a smart bot on WhatsApp

Free alternative for the Cleverbot API

nonebot2 机器人插件 - ⚡在群里和大家一起玩郊狼吧！⚡

it's basically chatgpt-cli, uses api.

A plugin integration between QGIS and openai API. Displays the results from openai in QGIS.

Vector search over tweets from the tweet archive using OpenAI embeddings and LanceDB

> CLAUDER - a safer and supercharged Claude Code

Text to Python Objects via a LLM Function Call

Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning

A distributed multi-modal agent orchestration framework implementing advanced natural language processing, computer vision, and audio processing capabilities through a microservices architecture.

ICLR'2024: Learning Multi-Agent Communication from Graph Modeling Perspective

🌟 Revolutionize Your Operations with One Sentence Automation: Utilizing large language models and Multi-Agents to generate operational copy, images, and videos with one-line requirements.

This tool will parse the inputted text into many different existing AI writing detection tools and return the results to you. This is to be able to scan text with as many tools as possible without having to do it manually.

Create a Chatbot app on your own data with GCP tools

Multi-Agentic System Observability SDK

An autonomous multi-agent orchestration system for Home Assistant. Features local LLM control (Ollama/DeepSeek), & RAG-powered technical knowledge,

Multi-Agent Systems with Google's Agent Development Kit + A2A + MCP

Chat with your Documents(PDF, TXT, DOCX, ODT, PPTX etc), Websites and Youtube Chat too!, CSV files. Uses langchain, Ollama, Groq, Gemini, Streamlit. Llama3 available

SynthGenAI - Package for Generating Synthetic Datasets using LLMs.

"FastAgent: Simple, Fast, and Strong LLM Agents"

This repo builds chatGPT like Data analytics agentic framework using Langgraph

The official implementation of "LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers"

🤖 AI-powered academic proposal & experiment design generator | 基于人工智能的学术开题报告与实验设计生成工具 - Support multi-AI models, research gap discovery, and academic integrity

AI travel planner with 7 specialized agents, RAG, and tool-calling. Built with CrewAI & LangChain. Generates personalized itineraries with flights, hotels, activities, and cultural tips. Production-ready Python codebase.

The first platform designed to empower organizations by automating and enhancing their employment processes through advanced autonomous agents.

Code implementation for DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning.

GitHub Copilot Agent Skill for Nightscout CGM blood glucose analysis

Voice AI agent for reactivating cold leads through personalized calls, assessing their interest with AI agents, and syncing insights directly to your CRMs.

AI-powered bookkeeping and tax filing automation for entrepreneurs at the heart of the European economy

📚 Lama Loca — локальный ИИ-ассистент для учёбы. Учится по вашим книгам, создаёт отчёты, презентации, конспекты. Полностью офлайн.

The open-source foundation for production Voice AI. Build, scale, and own your AI calling infrastructure. Bridge legacy SIP to modern LLMs over ultra-low latency WebRTC pipelines. Zero platform fees, BYOK, and full data sovereignty.

LLM orchestration toolkit for agent workflows: planner + workers + synthesis, optional router (LLM + learned fallback), supports OpenAI/Anthropic/Ollama/llama.cpp, real scraping with caching, MCP server integration, and a TUI chat UI.

面向 Claude Code、Codex、Open Code等Ai Agent 的确定性公文排版 Skill，可直接渲染为规范公文格式的 .docx（字体、字号、行距、页码等）。

Extract Google Maps business leads and enrich contact details using AI & web scraping

基于 CrewAI 多智能体协作的 A 股智能分析与推荐系统 | Multi-agent A-share stock analyst built on CrewAI

Multi-agent会话式金融研究平台。提供专业智能体（价格分析、新闻追踪、宏观经济、深度研究），支持实时流式响应、自动生成8章节投资报告和投资组合监控。采用LangGraph、FastAPI和React技术栈开发。

The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop onboarding your coding agents like rookies every session.

Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-scoped and safe by design. Complementary to MCP. Paper: arXiv:2605.26159

Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-model training. arXiv 2605.08703.

End-to-end AI literature review automation: crawl, screen, download, multi-agent review, and report generation

The implementation of the paper "Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems"

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

面向 AI 时代的数据可视化规范与工作流库 — specification & workflow library for AI-era data visualization

企业级5-Agent智能会议助手系统 | Pipeline+并行编排 | Python/Java/Go三语言实现 | 面试宝典(八股文+STAR法+简历模板)

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

Local cockpit for Claude Code usage — rate limits, activity chart, one-click skill buttons.

🚀 FullScopeTest 是一款 AI 驱动的下一代全链路自动化测试平台。深度融合大模型能力，提供自然语言生成脚本(NL2Script)、智能错误自愈、测试数据裂变及全局 AI Copilot。无缝集成 API 测试、Web 自动化(Playwright)与性能测试(Locust)，让自动化测试变得前所未有的智能与高效！🤖✨

Mandol: An Agglomerative Agent Memory System (https://arxiv.org/pdf/2606.29778)

Find out where your coding agent starts degrading. Personal context-rot analytics from your own sessions - 100% local, zero-config: uvx contextrot

docker region:us

transformers safetensors gemma4_unified image-text-to-text gemma4 coding

gguf code codeqwen chat qwen qwen-coder

WRAITH — Weakness Reasoning & AI Threat Hunter | Multi-agent RL-driven penetration testing framework | DEF CON 2026

An agent for automatically deploying models from monolithic DL models to complex LLM-RAG models

🦞 Local, read-only security audit for your OpenClaw agent. Finds config, prompt-injection and supply-chain risks, watches for drift, and vets a skill before you install it. Offline, zero deps. A–F grade when all five layers ran.

A traceable personal memory layer that carries verified state across apps, models, and AI agents.

Agent 始终无法命中缓存巨浪费Token? 来看 PromptXRay! PromptXRay 是一个代理工具，只需要接入到AI API 调用中间, 就可以分析 OpenAI 兼容API的 Prompt 缓存行为

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Open-source, self-hosted LangGraph Agent Server. Production Postgres + Redis. Same SDK. Same Studio. Zero code changes.

Agent Skill that makes Claude a pixel artist — no Aseprite, no MCP, no diffusion. Every pixel is a decision.

Multi-frontend agent relay: run Claude Code, Codex, local, and AG-UI agents from Discord or Microsoft Teams

Automate Blender 3D modeling with AI via MCP — 93 tools for modeling, sculpting, architecture/MEP, materials, and 3D-print prep. Includes Blender Studio: a visual record/replay session editor with a multi-provider AI assistant (Claude, Gemini, OpenRouter) — drive it from n8n, Claude Code, or standalone.

Self-hosted alternative to Google's NotebookLM: import PDFs, web pages and YouTube transcripts, then get answers with citations back to the source. Hybrid dense + BM25 retrieval over a local SQLite database, with Claude, any OpenAI-compatible provider, or a model on your own machine.

Decentralized Ed25519 Cryptographic Identity, Signed Message Bus, and Proof-of-Contribution Framework for AI Agents on Technocore ( Ecosystem)

Create handoff documents and migrate active sessions between Claude Code and Codex.

Open-source AI Agent skill for generating personalized, mobile-friendly travel handbook webpages.

Zissa Wiki — an LLM-maintained research knowledge base in plain markdown, maintained by any AI agent (Claude, Codex, Gemini, DeepSeek, Kimi, Grok, Mistral or any chat app). Implements Karpathy's LLM Wiki pattern; checks every quote against its source.

Comprehensive AI Model Evaluation Framework with advanced techniques including Temperature-Controlled Verdict Aggregation via Generalized Power Mean. Support for multiple LLM providers and 15+ evaluation metrics for RAG systems and AI agents.

Annotation meets Large Language Models (ChatGPT, GPT-3 and alike).

Build document-native LLM applications

RLLaVA is a user-friendly framework for multi-modal RL research and optimized for resource-constrained teams.

DSTC6: End-to-End Conversation Modeling Track

An AI-powered assistant for your terminal and editor

Automate interaction with the browser version of ChatGPT.

Generate ChatGPT function call schemas based on function docstrings.

A tiny LLM Agent with minimal dependencies, focused on local inference.

SurfAgent is an AI agent built from scratch that performs web searches using Selenium and Brave Search, Langchain and supports GROQ or OLLAMA providing reliable sources for the results.

Question and Answer for CSV using langchain and OpenAI

(Official) PyTorch implementation for Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning (EMU) (ICLR 2024, Oral)

Confidence-Weighted Multi-Agent Retrieval-Augmented Generation (CW-MARAG) — a contradiction-aware RAG system that uses multiple retrieval agents with confidence-based arbitration to generate grounded, non-hallucinated answers from PDFs.

通过 vercel 搭建 LLM API 的反向代理

Web scraping framework built for AI applications. Extract clean, structured content from any website with dynamic content handling, markdown conversion, and intelligent crawling capabilities. Perfect for RAG applications and AI training data pipelines. Features async processing, browser management, and Prometheus monitoring.

Agentic RAG to help you build a startup🚀

Framework for coding stateful LLM chatbots and agents

This project involves using llamaindex Multi Agents concierge system and Qdrant vector database to customize the RAG application with user preferences over LLMs, Embeddings, Search types, and Reranking Models.

카카오톡 대화 데이터셋

🔮 TinyChat is a lightweight Desktop client for modern Language Models designed for straightforward comprehension. Supports OpenAI, Anthropic, Meta, Mistral, Google and Cohere APIs.