Gemma

An open-source Cotypist with macOS system wide AI autocomplete

A self-improving AI agentic harness aimed at hyper-local edge use on Mac OS on llama.cpp, Gemma 4, Bonsai Ternary 1.58 Bit, and Applefoundation models

A framework for benchmarking human and large language model (LLM) text using stylometric, readability, and emotion-based features. The project supports comparative analysis across models such as GPT, LLaMA, Falcon, Gemma, OPT, and Claude to investigate patterns in machine-generated language and its similarity to human writing.

Queen Protocol v2.12.0 — Automated enforcement daemon (colony-watcher.sh runs every 10 min via launchd, auto-normalizes failing reports + seals stale state) + 6 operator-discipline patterns from Elev-W1 22-shard colony. 22/22 reached CONVERGE_AUDIT_PASS this session. Workers: claude/kimi/codex/gemma4-local.

USB_AI

Local-first, AI-native personal health records — Track 3 (On-Device Private Health) submission for Build with Gemma NYC. Runs fully offline via Ollama / Gemma 4.

bulding a chatbot based on gemma finetuning

Conductor: a small orchestrator LM (Gemma 4 E2B -> 7B on DGX Spark) that cost-routes tasks across Claude, mid-tier and local model fleets with a measured fail-up safety invariant

AI-powered Customer Complaint Management System for pharma (API/FDF) manufacturing. React+Redux, FastAPI, LangGraph AI agent, Groq (gemma2-9b-it) for extraction, completeness/duplicate checks, risk classification, root cause & CAPA recommendations, and summaries. PostgreSQL/MySQL backend. Built for AIVOA assessment.

PoC codebase demonstrating Indirect Prompt Injection attacks on LLMs (Gemma 4) and mitigation techniques using Microsoft Presidio and Zero Trust architecture.

Run Claude Code against open-weight models on PLGrid LLMLab (ACK Cyfronet) — GLM-5.2, Qwen3.6, Gemma 4

Companion demo for the dev.to Gemma 4 entry on cross-model RAG drift detection (ragvitals + Gemma 4 + Claude).

Paper: Multi-agent LLM trading for Bitcoin. 72 real calls to Gemma 7B comparing panels of 1, 3, 5 and 9 agents. 9 agents beat B&H by +2.91pp.

Enclave Local is a fully offline, air-gapped AI synthesis platform for generating production-ready codebases and native PowerPoint presentations without cloud API connections.

A nostalgic, privacy-first desktop paperclip for macOS: a local Gemma model watches your screen, pops tips, runs reminders, answers questions, optionally reacts to your webcam, and scoots away from your cursor.

Petit coding agent CLI local avec Ollama et Gemma 4

An AI-powered clinical triage bot and physician dashboard built with MedGemma 1.5

Context Relay saves your project context once and drops a ready-to-paste briefing into ChatGPT, Claude, Gemini, Perplexity, Grok, or Mistral — so you stop re-explaining the same project every time you switch tools. Runs on Gemma 3 via Fireworks AI.

Gemma Chatbot (Ollama + LangChain + Streamlit) This project is a simple conversational chatbot built with LangChain and powered by the Gemma 2B model running on Ollama. It provides a clean Streamlit interface where users can ask questions and receive AI‑generated answers in real time.

An interactive AI-driven sports analytics simulation platform. It functions as a hybrid between an instant search interface and a sports management game.

# AI Enabled Healthcare Chatbot AI-powered healthcare assistant built using **Spring Boot, React, MySQL, Ollama (Gemma 2B), and GPT-4**. Features include **multilingual chat, voice interaction, emergency alerts, chat history, nearby hospital suggestions, JWT authentication,** and **role-based dashboards** for patients, doctors, and admins.

AI Career Copilot - Build with Gemma hackathon project

News2Market AI is an autonomous Gemma-powered agent that monitors financial news, predicts its impact on BTC, ETH, and the S&P 500, executes

leverage LLM gemma3:4b to implement an text to SQL query system with two caching system: exact text match and semantic match via embeddings

Personal Context Operating System (PCOS) — a local-first hybrid AI agent across Chrome, Android, Pixel Watch, PiecesOS, and cloud LLMs. Built on LiteRT-LM, Gemma, Chrome Built-in AI APIs, and MCP.

Multimodal Bengali-first AI agent for street vendors, powered by Gemma 4.

Personal AI assistant chat for INNIE GROUP - drafts emails, social posts, notes via Gemma/OpenRouter

Interactive AI-powered analytics platform using Streamlit, Pandas, Plotly, LM Studio, and Gemma.

Agentic AI Red Teaming Lab

W.A.R.V.I.S. — Forensic IR agent (Go orchestrator + Python MCP + Gemma 4). SANS FIND EVIL hackathon entry by WoopsFactory.