Search

A complete FastAPI application for creating a WhatsApp -> LLM chat agent. Features per-user memory, OpenAI tool-calling, secure n8n integration for proactive messaging, and full setup guides for Cloudflare Tunnels and permanent Meta tokens.

Production-ready voice agents and speech pipelines: STT → LLM/Agent → TTS, voice receptionists, telephony, call recording, tool/function calling. Built with Twilio, OpenAI Whisper, ElevenLabs, Vapi/Retell, FastAPI, WebSockets, ffmpeg; designed for deployment, monitoring, and real-world reliability

🔍 面向 AI Agent 的防篡改审计溯源系统 | Tamper-evident audit trail for AI Agents — generates hash-chained JSONL logs to answer: what did the agent do, how did it decide, and was anything altered? Framework-agnostic core + OpenClaw plugin.

Eyebrowse — A Chrome bridge that gives AI agents eyes and hands in the browser. Screenshots, clicks, typing, navigation, and page inspection via MCP tools, powered by a three-layer architecture: Chrome Extension ↔ WebSocket Daemon ↔ MCP Server.

Easy-Browser is a Chrome browser extension based on Large Language Models (LLMs), designed to simplify web automation. Through natural language interaction, users can easily complete web browsing, information extraction, and automation tasks without writing complex scripts or using traditional automation tools.

An AI sparring partner for your mind. Project Eidolon stress-tests your ideas by refracting them through six intellectual domains—from physics to philosophy—including a 'Divergent' lens for unconventional thinking. It's a tool for thought, powered by a symbolic LLM-to-LLM protocol.

Luna AI is a personal modular AI assistant built with LangChain, Ollama, and Pinecone, designed to function like J.A.R.V.I.S. It combines voice interaction, conversational memory, and AI response generation into a customizable framework that lets users create hands free, context aware assistants for everyday tasks and projects.

DecTell AI is a research-backed Decision Intelligence platform that goes beyond traditional BI tools. Upload any business dataset - AI automatically cleans it, runs exploratory analysis, trains predictive ML models, simulates what-if scenarios, measures causal impact of interventions, and answers natural language questions about your data.

This project was developed as part of my internship at HERO MOTOCORP. Website Q&A Agent An AI-powered tool that extracts content from user-provided URLs, generates vector embeddings, and answers questions strictly based on the scraped context. Built for accurate, source-grounded responses without hallucinations.

An interactive AI Agent built with Streamlit that evaluates cat food quality using a ReAct decision loop. Powered by Llama 3.3, it combines real-time DuckDuckGo web searches with custom Python tools to calculate Dry Matter, NFE, and Ca:P ratios. It provides professional veterinary verdicts based on user-selectable FEDIAF or AAFCO standards.

An open-source AI runtime framework focused on task execution, traceability, and delivery closure.

🌟 基于北斗七星命名的 7-Agent 协作体系，开箱即用的 AI Agent 架构方案。

CodegniPy is a groundbreaking Python library that elevates AI to a first-class citizen of the language. It introduces a cognitive computing engine where deterministic code and non‑deterministic LLM reasoning coexist seamlessly, enabling you to write Python with intent rather than just instructions.

Typed Kotlin DSL framework for AI agent systems.

oh-my-codex (omx) — Orchestration layer for OpenAI Codex CLI. Async Claude Code delegation (no timeouts), structured workflows (autopilot, TDD, code review, planning), persistent state & memory. Like oh-my-zsh but for Codex.

A web component based AI agentic chat UI element which can be added in any website to turn it into an agentic app

A secure, stable Rust alternative to openclaw/moltbot/clawdbot

Official implementation of the paper "GazeInterpreter: Parsing Eye Gaze to Generate Eye-Body-Coordinated Narrations" (AAAI 2026)

Your own AI agent. Local. Private. Autonomous. One command.

Python SDK for the LLM Conveyors AI Agent Platform API