grademaster-pro
notable
AI‑powered grading pipeline for Canvas LMS
Automates grading at scale
2026-05-23
102 fresh ai & ml projects, scored by craft.
AI‑powered grading pipeline for Canvas LMS
Automates grading at scale
Per-step Integrated Gradients analysis for diffusion-policy robotics models
Enables detailed attribution of vision, language, state inputs
SymQNet: fast adaptive Hamiltonian learning via amortized acquisition
RL‑driven VAE speeds quantum system identification
iSCAT‑based NMC battery degradation analysis pipeline
Comprehensive scripts for optical‑electrochemical data processing
Leakage‑aware backtesting framework for financial metric forecasting
Ensures point‑in‑time validation on public finance data
PHANTOM: Zero-copy multi-agent LLM KV-cache serving on Apple Silicon Unified Memory
Optimizes LLM inference by sharing KV-cache across agents without copying
AI mod for Slay the Spire 2
automates gameplay
RAG pipeline for clinic info
accurate answers
A functional open-source implementation of Claude for seamless browser integration.
Offers reliable, customizable AI tools without restrictions.
End‑to‑end GNN traffic forecasting on PeMS sensor data
Full pipeline, multi‑GPU training, reproducible results
Validates LLM specs via cross-model PBT to catch intent drift
Fast, cheap spec validation without ground truth
AI-driven financial triage service for small businesses
Structured advice via LLM with fallback logic
WebRTC‑enabled surgical robot simulator powered by Cosmos‑3 AI
Runs action‑conditioned AI model for realistic surgery demos
CLOVA: Closed‑Loop Visual Assistant for tool usage and updates
Combines LLM reasoning with visual tool execution
Offline speech-to-text and speaker diarization pipeline
Combines Vosk and SpeechBrain for batch audio processing
KayzeeOCR: layout detection and structured OCR using Qwen2.5-VL-2B
End‑to‑end OCR with JSON output for 17 document element types
Local RAG indexer that guarantees every chunk is stored
Verifies coverage to avoid silent indexing failures
Secure self‑hosted console for AI image generation & Composio integration
Encrypts API keys server‑side, Google SSO, ready‑to‑run
Explainable AI football match predictor with chain‑of‑thought reasoning
Provides transparent predictions with data‑driven reasoning
LLM-powered web app for natural-language Q&A on YouTube channel data
Secure LLM queries via Cloudflare Worker, static React UI
Desktop GUI for TabICL to train and forecast tabular models
Easy visual interface for TabICL with LLM constraints
Contrastive encoder trainer for Llemma‑7B on Lean proof pairs
Ready‑to‑run pipeline for GPU/Apple‑Silicon training
Forgewright: a web workbench for designing, analyzing, and refining LLM prompts
Discovery, scaffold editing, and reverse analysis in one UI
AFM Safety Studio builds safety test trajectories for Apple Foundation Models
Enables proactive tool-use safety labeling for AFM
sesh: a minimal Go AI coding agent for LLM‑driven code tasks
Zero‑dependency, extensible Go CLI for AI coding
Bayesian lag selection tool for VAR models
Implements thesis with CmdStan integration
Node.js SDK for AI agent governance and audit trails
Enables policy‑enforced, tamper‑evident AI runs
AI-powered outbound calling agent for dental clinics
Automates calls with LLM, STT, TTS integration
StudioAI – local AI‑powered video and animation studio
All‑in‑one local content creation without external APIs
Agent-based crypto policy simulation platform for stress-testing regulations
Provides realistic policy impact analysis with adaptive adversaries
Reproducible benchmark for forecasting U.S. honey‑bee colony loss
Data, code, and leaderboard for honest out‑of‑sample testing
On-device perception‑to‑reasoning pipeline for Apple Silicon
Combines Core ML vision with swappable LLMs for offline AI
olive-arena: automates model optimization for HuggingFace models using Microsoft Olive
streamlines model quantization and benchmarking
Tamaya is a full-stack AI diary service for emotional well-being and loneliness mitigation
Combines FastAPI backend with Vite/React frontend, using Naver CLOVA AI and pgvector
DeepResearch Agent: LLM‑powered research assistant with citation checking
End‑to‑end research, retrieval, and citation verification
KodaAI: privacy-first AI search & chat app with multi-model support
Offers search-augmented chat with cited answers and customizable models
AI-SDLC governance kit for predictable agent work
Tool-agnostic, YAML-driven governance engine with SDLC factory
Self‑hosted AI‑powered markdown knowledge base with hybrid search
Combines vector + keyword search with chat UI
Anneal is a CLI tool that captures and recalls agent mistakes, promoting recurring patterns into version-controlled rules.
Solves the problem of agents repeating mistakes by capturing and recalling lessons learned.
AI-powered video analysis pipeline for local object detection and scene understanding
Combines OWLv2 and local LLM for adaptable video analysis without external AI services
AI prompt engineering tool that turns vague goals into effective, verifiable prompts or stops when AI is not the right tool
Solves common prompting failures with a thoughtful, multi-phase approach
AI meme generator for agents with 30 templates
Easy integration for AI humor
JEPA-based world-model agent scaffold for AI research
End‑to‑end training and evaluation of a JEPA world model
AI-powered trading workstation with live market data and natural language trading
Combines real-time streaming, portfolio simulation, and LLM trading assistant in one interface
AI chest disease detector using X-rays with Streamlit web interface
Complete working solution with pre-trained model and web UI
Local RAG‑powered clinical assistant with Streamlit UI
Searchable medical evidence with AI analysis
IDP design tool
Physics-guided
Evidence-first workflow kit for auditable AI deliverables
Enforces source-backed claims
A learning-focused language for teaching programming design principles
It clearly aims to educate developers about language design through a toy language, offering structured examples and exercises.
Smart traffic routing system
Solves traffic congestion
Evaluates indirect prompt injection in LLM email agents with tool-call logging and detection mechanisms.
Tests email agent security against hidden malicious instructions.
GUI Agent Benchmark harness for reproducible failure analysis
Captures full evidence chain for GUI tasks
Real estate price predictor with ML API and web UI
End‑to‑end Azure‑deployed ML model with explainability
FastAPI service that ranks place recommendations using a scikit‑learn model
Ready‑to‑run ranking API with synthetic data and tests
Deletion‑aware RNA nanopore basecalling with student model training
Training and evaluation scripts for accurate RNA basecalling
GNN-driven Monte Carlo framework for magnetic alloy simulations
Combines graph neural nets with MC to study ordering
Framework for evaluating multi‑region LLM agent handoff performance
Runs realistic distributed LLM experiments with Docker
Terminal AI assistant for Northeast Indian languages, runs locally
Local LLM with language ID and vector search
Rust toolkit for optimal poker strategies and AI training
Fast hand evaluator and MCCFR solver for poker AI
PersonaDrive: controllable trajectory prediction with multi-dimensional driving personas
Adds persona conditioning to trajectory models
Hermes skill-graph plugin adds searchable knowledge graph for agent skills
Typed relationships improve skill discovery
Admission control & idle model reaper for shared local LLM servers
Manages memory, priorities, and external tenants
AI-driven multi-tenant commerce platform for chat‑based sales agents
Autonomous sales bots with human‑style chat and owner approval
TrueFoundry‑focused RAG server for answering docs queries
Provides grounded answers with source URLs
ZINA detects and edits hallucinated text in multimodal LLM outputs
Fine-grained hallucination tagging and correction
Browser‑based AI tool that turns transcripts into SEO‑ready content assets
Single‑file, no‑server, bring‑your‑own‑key design
LangGraph-based AI agent framework with sandbox execution
Manages sandbox lifecycle, integrates web search & file upload
AI-powered web app that analyzes CSV/Excel data via natural language
Combines Gemini AI with Streamlit for instant data insights
Local GPU-accelerated pipeline that extracts policy text from PDFs
Runs entirely offline, no cloud APIs needed
Jensen: AI‑powered knowledge‑graph platform for client‑specific insights
Integrates embeddings, LLM chat, and Supabase for live knowledge graphs
Swahili TTS pipeline for data prep, baseline evaluation, and fine‑tuning
End‑to‑end workflow for building Swahili speech synthesis models
AI Studio app for running math quizzes locally
Provides a working AI Studio app with local deployment
Biomedical Agent Teams Codex Marketplace plugin for local Codex Desktop
Exposes biomedical-agent-teams skill with 35 agent prompts and more
Offline LLM agent runtime for edge devices
Runs locally on Jetson/Raspberry Pi without cloud
AI Studio app for running and deploying AI models locally
Simplifies local deployment of AI models with Gemini API integration
EEGlas: an explainable EEG dashboard for dementia classification
Combines explainable AI with an interactive UI for clinicians
GNSS urban PNT learning portfolio for robust pseudorange positioning and LEO-like aiding
Demonstrates robust pseudorange positioning and simplified LEO-like ranging-source aiding
AI Studio app for running AI models locally
Simplifies local AI app development
AI Studio app for remote healthcare management
Implements AI-powered healthcare management locally
Multi-agent simulation system for modeling conversations and memories
Simulates agent interactions, memory formation, and relation mapping
Fast-PIKAN: a physics-informed neural network solver
implements PIKAN for solving PDEs
AI agent skill for clear, non-duplicated project documentation
Teaches agents to create token-efficient docs
AI adoption visualizer generates interactive charts for automation adoption and FTE displacement
Provides useful insights into AI adoption trends and impacts
AlphaZero‑style micro‑chess engine with beam‑search inference
Runs a compact GPT‑2 model with search for strong play
Tic-Tac-Toe AI game
unbeatable AI opponent
UAV multimodal trajectory prediction framework for ProjectAirSim
Provides ready‑to‑use 3D trajectory forecasting
AI-powered photo toonifier
Energizing photos
AI Agent platform with FastAPI & Gradio for multi‑tool interactions
Combines LlamaIndex agents, REST API, and web UI
LangGraph-powered content generator using Google Gemini
Self‑correcting LLM pipeline with evaluation loop
Proxy server that routes Claude Code API traffic to many AI providers
Lets Claude Code use free, local or alternative models
Turkish TTS model
Working TTS model
White blood cell classifier
Accurate WBC classification
Financial PDF extractor using LLMs and embeddings
End‑to‑end pipeline for structured data
Diagnostic toolkit for GP boundary bias in Bayesian optimisation
Shows how variance inflation skews acquisition
AI-powered short drama production studio
End‑to‑end workflow for script to video
A solution for optimizing urban traffic flow
Addresses real-world congestion with data-driven insights and efficient routing.
An innovative approach to agentic LLM systems.
Demonstrates practical implementation of AI-driven decision-making.
AI chatbot with real‑time RAG for PDFs and docs
FastAPI, WebSocket, FAISS, Groq
Physics-Informed Neural Network training with precision and optimizer switching
Enables efficient, accurate PINN experiments
An AI-powered solution enhancing productivity
Valid application addressing automation needs
AI PDF Q&A app that answers questions from uploaded PDFs
Combines RAG with Gemini for instant answers
AI agent for scientific calculations using local LLMs
Functional prototype with actual code, not just educational demo