Python agents

Canonical memory infrastructure: BM25 recall over trusted files for AI agents.

A streaming action language for computer-use agents. LLMs emit one JSON action per line; the executor runs each the moment its newline arrives — while the model is still generating.

Agent skills that turn Claude Code (or any agent) into an award-winning multi-modal creative pipeline — art, music, video, story. Panel-of-Experts debate, a deterministic state graph, and an immutable continuity block that makes creative drift structurally impossible. Prose contracts, not framework code.

AI agent skills for IELTS Writing Task 1 & Task 2 review with DOCX comments, customizable target bands, and model answers.

Teaching Skills for Claude Code — teaching lifecycle suite for university professors

Claude Code skill: distill a book or video series into one interactive single-file HTML · 书籍/视频深度蒸馏

Workspace-first orchestration for long-horizon Lean 4 formalization agents.

Track LLM token usage, enforce rate limit & budget policies, and trigger alerts across OpenAI, Groq, OpenRouter, and AWS Bedrock.

Local MCP server for ComfyUI — run your local ComfyUI from AI agents

Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, root-cause debugger, and code generator, all in one shell-native loop.

命理圆桌会 · A multi-school Chinese BaZi (Four Pillars) roundtable reading skill for Claude

AI-driven Abaqus workbench: describe a model in a spec, get a real solved one back. Every capability is backed by a check you can run on your own seat, and the gates refuse a doubtful answer instead of returning it. AGPL-3.0 + commercial licence.

LLM plugin for Azure AI Foundry with Entra ID authentication

Claude Code skill for generating PowerPoint decks from markdown using template slide master layouts

Drop in your Binance or Bybit CSV export. An AI agent identifies revenge trading, overleverage, FOMO entries, and other psychological errors — with dollar attribution per error class. Runs locally. No API keys. No account linking.

A bot that scrapes open-interest and liquidation heatmaps to alert traders when a "Short Squeeze" or "Long Squeeze" is imminent.

AI agent for solana

Measuring RAG solutions throughput and latency

A streamlit application to play with LLM Models

Comprehensive, scalable ML inference architecture using Amazon EKS, leveraging Graviton processors for cost-effective CPU-based inference and GPU instances for accelerated inference. Guidance provides a complete end-to-end platform for deploying LLMs with agentic AI capabilities, including RAG and MCP

Sora is a Discord bot that integrates with the Open Router API to facilitate conversation in Discord servers.

基于 Youtu-Agent 框架构建的Nexus财务智能体，专为A股市场设计。

AI for tactical cycling intelligence: Predictive mud logic, S-Scale terrain analysis, and powered GPX routing

A community-maintained collection of Pydantic AI examples.

Secure your AI Agents against prompt injection attacks

Open-source framework for stress-testing LLMs and conversational AI. Identify hallucinations, policy violations, and edge cases with scalable, realistic simulations. Join the discord: https://discord.gg/ssd4S37WNW

Liquefy is a local-first OpenClaw vault system for packing, verifying, searching, and auditing agent runs with domain-aware compression, policy/redaction, and proof artifacts.

LUMIN: Your data analysis companion that turns natural language questions into powerful insights through AI-driven visualizations and clear explanations.

This repository contains a simple but powerful chatbot built with Streamlit, OpenAI, and LangChain. The chatbot maintains conversational memory, meaning it can reference past exchanges in its responses.

Retrieval Augmented Generation demo using Microsoft's phi-2 LLM and langchain

AI agent converting natural language to Neo4j Cypher

Chat with an AI simulation of anyone as easily as copy-pasting text into a folder!

RAG based Document Assistant for Search

LLM-adaptive embeddings (Zero-shot / LoRA) with Generative Topic Modeling & Agent-based workflow for social science text mining

This is a an open-source project designed to help you improve your skills with AI engineering using LLMs and the langchain library

Knowledge base Q&A program using LangChain for retrieval-augmented prompting and PGVector as vector store.

LLM graph-RAG SQL generator for large databases with poor documentation

This is a LLM model, where it is tuned to help the farmers for clarifying their doubts about organic farming, with personalised suggestions.

Streamlit app that demonstrates a conversational chat

A CLI interface that allows you to interact with ChatGPT from your terminal using an API key.

A LangChain integrated Discord chatbot. Used by GPT Engineer's Discord server.

This Repositry is an experiment with an agent that searches documents and asks questions repeatedly in response to the main question. It automatically determines the optimal answer from the current documents or recognizes when there is no answer.

Solo Podcast Creation from Web Page content

AI-powered fundamental analysis platform. TimescaleDB, CrewAI agents, portfolio optimization, pair trading, and automated alpha extraction.

The Ranking Cost algorithm for multi-path routing of gridworld.(多智能体路径规划，电路规划)

Autonomous AI-powered academic research system.

Agentic crypto trading bot powered by local Llama 3. Chain-of-Thought reasoning across RSI, MACD & live news. 100+ exchanges via CCXT.

Misalignment Bounty submission template

An Artificial Intelligence Chat Bot and Service Provider written in Python and AIML.

This project seamlessly integrates a web-based interface with advanced AI to enable natural language interactions with a relational database. Utilizing Python, Streamlit for the frontend, and OpenAI for intelligent responses, it connects to a Postgres database for efficient data retrieval and features conversation history saving for easy reference.

An Alexa skill providing a conversational interface to any public figure (as mimicked by GPT3). The legacy GUI is no longer maintained.

针对保险话术培训场景设计的陪练机器人/培训机器人的demo

Mentoring system for an organization like SSN

Llava, Ollama and Streamlit | Create POWERFUL Image Analyzer Chatbot for FREE - Windows & Mac

rpi based TelegramBot

Personal Assistant with useful features for Windows written in python. Simple and easy to use.

Build an AI Assistant Wolfram Alpha and Wikipedia in Python

A collection of simple transformer based chatbots.

The goal for this project is to create an LLM based music recommendation system. This project is currently in its very early stages, however the goal of this project is to create an extremely flexible music recommendation system using a chat focused LLM on the frontend to interact with a robust recommendation system on the backend.

Python Voice-Chatbot with offline voice recognition.

Deep Reinforcement Learning Toolbox for Robotics using Keras and TensorFlow

AI agents that can define their own goals to interact with a game environment. Powered by GPT-4o.

Perfect for anyone who needs to quickly calculate the token amount of ChatGPT in prompts for their project.

MCP prompt tool applying Chain-of-Draft (CoD) reasoning - BYOLLM

Get deterministic output in any format like json from any LLM.

OpenAI CLIP based image generator with complex config file controlled transformation and training pipelines

Транслятор запросов к LLM Yandex Cloud из SDK OpenAI

An AI-powered chat system that allows users to communicate through a terminal interface. Uses ChatGPT's API by OpenAI.

An AI-Powered Python Script for Teaching Machine Learning Topics

FastHTML app that makes other FastHTML apps with LLMs

Gym env for TurtleBot3 robot

FAQ Generator for Classroom Climate Change Education using OpenAI

Outbound PSTN calling agent using LiveKit SIP trunks with a voice pipeline (Silero VAD, Deepgram STT, OpenAI LLM+TTS). Includes a simple CLI for local development, health checks, and model prewarming.

generate & query embeddings from VTT files using openai & pinecone on Andrej Karpathy's's latest GPT tutorial

Predict the exact openai token usage of functions

ChatGPT-Turbo SMS is a Flask application that allows users to send SMS text messages to ChatGPT-Turbo using Twilio and receive instant responses.

Command line large language model conversation and experimentation environment

Archived (2026) — superseded by gbrlpzz/transcribe, a fully local macOS dictation & transcription tool. Scribe: Python transcription toolkit turning audio/video into titled PDFs via OpenAI Whisper + GPT.

Talk to chatgpt from command line

See all your MCP servers, skills, commands, rules, and CLAUDE.md files in one place — TUI for Claude Code

BestRAG: A library for hybrid RAG, combining dense, sparse, and late interaction methods for efficient document storage and search.

The implementation of Test Time Diffusion paper by Google with some tweaks to run on 24gb gpu

RAG system with real-time news scraping built using mixtral-8x7b, ChromaDB, bart summarizer

Realign is a testing and simulation framework for AI applications.

Sharing Session Python.id Jakarta X Indigo X Alibaba Cloud

Self-learning AI agent that gets smarter and cheaper over time. Routes between local and cloud LLMs, learns from every interaction, remembers everything.

This repository provides a basic guide on building and deploying an AI agent.

MCP server for inspecting, searching, and decompiling Maven .m2 JARs for Java AI coding agents.

The bottleneck in AI coding isn't the model: It's the babysitting. Gobby is a local daemon that turns a task into a PR across Claude Code, Codex, Gemini, Qwen, and Droid. Stage dispatch, hook-time rules, progressive MCP proxy, and more. Gobby built Gobby: ~5K commits, ~15K completed tasks and counting.

一個以人類大腦結構為靈感的神經符號認知 AI 系統。具備三層圖譜記憶、虛擬神經化學、夢境反思引擎，以及 OpenClaw 整合，讓 AI 擁有真正的記憶、情感與自我。

Tree-of-Debate converts scientific papers into LLM personas that debate their respective novelties. To emphasize structured, critical reasoning rather than focusing solely on outcomes, Tree-of-Debate dynamically constructs a debate tree, enabling fine-grained analysis of independent novelty arguments within scholarly articles.

Unified harness for hot-swapping between OpenAI Agents SDK and Anthropic Claude Agent SDK with shared tool registry

Synapse is a lightweight peer-to-peer substrate for agent infrastructure. Give each process a Node and Synapse gives that node a name, peers, capabilities, RPC endpoints, shared conversations, agent cards, heartbeats, and periodic tasks.

Skill-as-API: P2P agent collaboration over XMTP. Call remote skills without exposing code. E2E encrypted, revocable trust, async delegation. Zero deps.

Multimodal AI Assistant is an advanced chatbot designed for local interactions with LLMs, files, and multimodal functionalities. Built on the Chainlit framework, it integrates Langchain and ChatOllama for hosting models locally, with cloud storage and monitoring via LiteralAI.

RAG-based Telegram assistant bot for freshmen

NaLaMap is an open-source application to create webmaps and analyze geospatial data using natural language.