ollama

The library for character-driven AI experiences.

Agent and LLM API performance monitoring via network packet probe. Measures performance of OpenClaw, Claude, Codex, DeepAgents and more — deployed on the provider side, no SDK changes required.

Karpathy's LLM Wiki idea as a product — an AI that builds and maintains a markdown wiki from your notes and sources. MCP server + web UI, runs on free local models (Ollama), no API key needed. MIT.

Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.

Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.

Neovim plugin for code completion

bott: Your Terminal Copilot

ScrapeGPT is a RAG-based Telegram bot designed to scrape and analyze websites, then answer questions based on the scraped content. The bot utilizes Retrieval Augmented Generation and webscraping to return natural language answers to the user's queries.

The Developer's Guide to AI - A Field Guide for the Working Developer

Template for AI chatbots & document management using Retrieval-Augmented Generation with vector search and FastAPI.

AskTube - An AI-powered YouTube video summarizer and QA assistant powered by Retrieval Augmented Generation (RAG) 🤖. Run it entirely on your local machine with Ollama, or cloud-based models like Claude, OpenAI, Gemini, Mistral, and more.

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.

An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.

RetroChat is a powerful command-line interface for interacting with various AI language models. It provides a seamless experience for engaging with different chat providers while offering robust features for managing and customizing your conversations. The code in this repo is 100% AI generated. Nothing has been written by a human.

council of models for decision

Handy tool to measure the performance and efficiency of LLMs workloads.

Tiny client for LLMs with vision and tool calling. As simple as it gets.

WordNest🎯 是一个基于Flask的个性化英语单词学习系统，专为解决传统背单词软件的痛点而设计。它通过仅收录用户手动添加的生词，告别海量词库的无效重复学习；调用大模型实现AI智能例句生成与记忆技巧辅助，并构建词汇知识图谱，以可视化关联提升记忆效率。

LLM Rag Intelligent Q&A Robot

It’s an OSINT reconnaissance poc powered by Local LLMs (Ollama). You can feed it an email, domain, or IP, and it automatically performs multiple types of reconnaissance, then generates a clean human-readable report using a local LLM.