StableCode

StableCode-Instruct-Alpha-3B is a decoder-only model with 3 billion parameters. Pre-trained on top programming languages from the StackOverflow developer survey, it's a product by Stability AI intended for coding.

General	https://huggingface.co/stabilityai/stablecode-instruct-alpha-3b
Relese date	August 8, 2023
Author	Stability AI
Repository	https://huggingface.co/stabilityai/stablecode-instruct-alpha-3b

StableCode: Features & Highlights

Trained on a diverse set of languages from the stack-dataset (v1.2) by BigCode, including Python, Go, Java, and more.
Fine-tuned with ~120,000 code instruction/response pairs for specific use cases.
Extended context window for precise autocomplete suggestions. It can handle 2-4X more code than earlier models.
Designed to assist both seasoned and novice developers.

StableCode Resources

A curated list of libraries and technologies to help you build great projects with StableCode.

AFRI-EDGE

AFRI-EDGE is an intelligent infrastructure routing platform designed to optimize where AI and compute workloads run across Local, Edge, and Cloud environments. Instead of sending every workload to the cloud, AFRI-EDGE continuously evaluates available infrastructure conditions and workload requirements, then uses a Decision Engine to select the most appropriate execution target. The platform combines workload profiling, infrastructure monitoring, constraint-based candidate evaluation, and intelligent routing into a unified system. For each workload, the Decision Engine evaluates the available targets, ranks eligible candidates, and produces a transparent routing decision with a score and reasons behind the selection. AFRI-EDGE is designed with a practical African infrastructure context in mind, where connectivity, bandwidth, compute availability, latency, and resource constraints can vary significantly. By making infrastructure placement more adaptive, the project aims to provide a foundation for more efficient and resilient AI infrastructure. The current MVP includes an end-to-end routing flow, infrastructure state collection for LOCAL, EDGE, and CLOUD, workload profiling, candidate evaluation, and a dashboard for visualizing routing decisions and candidate rankings. Core principle: don't assume the cloud is always the right destination — evaluate the workload and the infrastructure, then route accordingly.

Fresno LUX: A Living City

Fresno LUX is a prototype for a living intelligence layer across an entire city. Fresno already contains enormous amounts of intelligence: residents know where problems exist, nonprofits know where help is needed, businesses know where opportunities exist, educators understand gaps in learning, researchers generate knowledge, and government maintains critical infrastructure and data. The problem is that much of this intelligence is fragmented across disconnected systems. Fresno LUX connects those pieces. The platform creates a shared city graph where people, organizations, resources, needs, projects, observations, experiments, and outcomes become connected nodes. Instead of simply collecting data, LUX continuously asks: What is happening? What do we know? What is missing? What can we test? What changed? A community problem can become an observable signal. That signal can become an experiment. The experiment produces evidence. Evidence changes the system's understanding. That updated understanding informs the next action. Observe → Connect → Understand → Act → Measure → Learn → Converge. The goal is to move Fresno from disconnected information toward collective intelligence—a system where knowledge can travel across boundaries and successful solutions can be discovered, tested, measured, and replicated. LUX is designed to make the invisible connections visible: the relationship between a neighborhood and its resources, between a student and educational opportunity, between a business and workforce capacity, between environmental conditions and community health, and between an idea and measurable real-world impact. This hackathon prototype demonstrates the beginning of a Living Fresno Graph: a city that can observe itself, learn from evidence, and coordinate toward better outcomes.

SentryTheta AI - Autonomous Options Trading Agent

SentryTheta AI solves the fundamental flaw of Generative AI in financial markets: LLM hallucinations causing reckless capital destruction. It bridges the gap between LLM market reasoning and unbreakable mathematical risk control. Our core multi-agent architecture includes a Market Analyst AI that scans real-time Yahoo Finance RSS news feeds for directional sentiment, and a Volatility Strategist that queries live Alpaca option chains to structure high-probability trades like Long Calls, Long Puts, and Cash-Secured Puts. Before any execution, a Sentry Risk Officer mathematically audits every proposed trade against strict risk rules. Finally, a Trade Executor transmits verified orders directly to the Alpaca Paper Trading API. To protect capital, our institutional risk engine features three defense layers: strict position sizing caps that restrict single option premium exposure to a maximum of 5% of account equity, a daily drawdown circuit breaker that automatically halts trading if portfolio losses hit 3%, and an automated exit harvesting system that scans active contracts every 60 seconds to trigger Stop-Loss (-15%) and Take-Profit (+30%) liquidations. SentryTheta AI offers a real-time glassmorphic dashboard with two operating modes: a Copilot Mode for human-in-the-loop 1-click trade authorization, and an Autopilot Mode for 100% autonomous execution. Features also include dynamic ticker search for over 6,100 optionable stocks, SQLite state persistence, and Model Context Protocol server integration.

AMR Guardian AI Antimicrobial Resistance Predictor

AMR Guardian AI is an AI powered clinical decision support system designed to help healthcare professionals identify and assess the risk of antimicrobial resistance at an early stage. The project addresses a critical healthcare challenge where inappropriate or unnecessary antibiotic use can contribute to the development and spread of resistant infections. The system analyzes multiple patient specific factors, including age, symptoms, basic laboratory results, previous antibiotic use, and culture information. It combines these inputs to generate an antimicrobial resistance risk assessment and presents the results through a clear, user friendly dashboard. The platform provides a risk score, risk level, infection category, severity assessment, clinical summary, confidence score, key findings, major risk factors, and feature importance. It also provides culture testing, follow up, isolation, and antibiotic stewardship recommendations. These explainable outputs help users understand why a patient may have an elevated resistance risk instead of receiving a simple unexplained prediction. AMR Guardian AI uses React for the frontend, Supabase for authentication and database management, and AI powered analysis for generating clinically relevant insights. The dashboard presents patient analyses, AMR risk trends, infection distributions, and recent assessment records in an organized interface. The project is designed as a decision support prototype. Its purpose is to demonstrate how AI can support earlier risk assessment, improve antimicrobial stewardship, and encourage more informed antibiotic use. AMR Guardian AI combines biotechnology, clinical data analysis, artificial intelligence, and modern web development into one practical solution. It demonstrates how intelligent data driven tools can support healthcare professionals in addressing antimicrobial resistance and building more responsible approaches to antibiotic treatment.

ARCHON: AI for Engineering Intelligence

ARCHON is an AI-powered engineering intelligence platform built with IBM Bob to help developers understand, analyze, and manage complex software systems faster and more efficiently. Unlike traditional coding assistants that mainly focus on autocomplete or code generation, ARCHON acts as an AI engineering teammate that understands the entire codebase, architecture, dependencies, and business logic of a project through repository-wide AI reasoning. Modern software systems are increasingly difficult to maintain due to large repositories, incomplete documentation, technical debt, and complex service dependencies. Developers often spend more time understanding code, debugging issues, and tracing dependencies than actually writing code. ARCHON solves this problem by transforming repositories into an intelligent and interactive engineering knowledge system powered by IBM Bob and IBM Granite. IBM Bob enables ARCHON to understand software systems beyond individual files by analyzing repository structures, dependency relationships, architecture flows, and engineering workflows across the entire project. ARCHON automatically generates architecture maps, dependency graphs, and code flow explanations while allowing developers to interact with the system using natural language queries. The platform also provides AI-powered impact analysis, root cause investigation, technical debt detection, and engineering knowledge recovery from historical commits and undocumented logic. By combining repository-wide reasoning, multi-agent AI workflows, and visual system intelligence, ARCHON helps developers debug faster, reduce onboarding time, minimize deployment risks, and significantly improve engineering productivity. ARCHON’s vision is to transform software engineering from simple code assistance into true engineering intelligence.