L

LLMs

Convert OpenAPI and Postman to Wrekenfile and break down to mini-wrekenfiles for LLM context

🤖 AI chat & search summaries in Google Search, powered by the latest LLMs

🛒 AI chat & product/category summaries in Amazon shopping, powered by the latest LLMs

Live : https://lumen-rouge-one.vercel.app/ Lumen is a premium AI research platform that orchestrates specialized agents (Search, Reader, Summarizer, Synthesizer, Citation, Graph) to generate comprehensive reports, stream agent progress in real-time via WebSockets, and build interactive D3-based concept graphs.

A web AI interface using a selected number of models and trained to teach the German language.

💬 Epic prompts to turbo-charge your LLM chatbots.

To address limitations in existing CI/CD systems, we developed CI Agent, an LLM-powered automation system that transforms pipelines into self-healing systems.

“Every time a CI pipeline fails, a developer stops coding and starts debugging—we wanted to eliminate that interruption.”

CI Agent integrates with platforms like GitLab and automatically detects failures, analyzes logs using a hybrid AI approach, identifies root causes, selects appropriate fixes, executes safe remediation actions, and notifies results via Slack.

This converts CI/CD from a passive monitoring system into an intelligent assistant, reducing manual debugging effort and improving development efficiency.

An offline chatbot powered by WebLLM. Some LLMs available for loading are Llama-3.2, Mistral v0.3 and Stablelm 2. No MLOps required for deployment. Runs in-brower using WebGPU. Demo at: https://vite-webllm.onrender.com

This project is a Retrieval-Augmented Generation (RAG) application built using LangChain. It leverages advanced language models and vector databases to answer questions about epidemiological modeling, software development, and maintaining the EPP model for HIV modeling.

🔎 Type @brave in browser address bar to get results from Brave AI

🔎 Type @you in browser address bar to get results from You.com AI

Firefox extension that shows a prompt, chat history and gives the ability to interact with large language models which can could be on the web or hosted locally.

Django application to build and maintain chatbots that combine the best of LLMs and rule-based engines to truly assist your users instead of manipulating them.

Perplexity Model Watcher is a Chrome extension that gives you transparency into which AI model Perplexity actually uses for your queries. Read why this is needed. Get instant visual feedback on model matches and mismatches by automatically intercepting network responses, ensuring you receive the AI experience you expect and paid for.

AIlin is a tool that connects AI services, such as Perplexity.ai, with your local computer.

FUBbot - An AI counselor expert in Swedish LSS law

BDS LLM Chat - Hugging Face API Wrapper

A Flask-based chat application that serves as a wrapper for the LLaMA 3.2 model from Hugging Face. This application provides a user-friendly web interface and API for interacting with the model.

Features Modern responsive UI with dark/light mode support Persistent chat history in browser localStorage Markdown rendering for model responses REST API compatible with OpenAI-style endpoints Centralized model worker for efficient inference Redis-backed queue for robust request handling Queue-based architecture for handling multiple requests Admin dashboard for user and API key management External API access with API key authentication MongoDB-based persistence for chats, users, and API keys