J.A.R.V.I.S is a Python voice-controlled desktop assistant combining speech recognition, facial authentication, and multi-voice personas without AI models. A pre-LLM design worth exploring.
Kimi-Audio combines continuous acoustic and discrete semantic tokens within a 7B LLM for unified audio-text understanding and generation. It achieves state-of-the-art ASR with low-latency audio synthesis.
Kodo is a Python multi-agent orchestration layer coordinating AI coding agents via a plain API orchestrator, improving autonomous coding accuracy by 24% over single-agent setups.
This repo complements a ROS 2 course with hands-on C++/Python exercises, Gazebo simulation, and real robot control focusing on localization, mapping, and obstacle avoidance.
linkedin_scraper is a Python library using Playwright and async/await for structured LinkedIn scraping with typed Pydantic models, session management, and progress callbacks.
LiveTradeBench benchmarks LLM trading agents like GPT and Claude in live US equity and prediction markets with real-time news and sentiment integration.
LLM-MM-Agent uses LLMs as autonomous agents for end-to-end mathematical modeling, featuring a unique hierarchical method library with actor-critic selection. Supports GPT-4o and DeepSeek-R1.
llmstxt_architect automates generating and updating llms.txt files that communicate website content to LLMs. Supports multi-provider LLMs and preserves file structure during updates.
loki-mode automates software builds from Markdown PRDs, GitHub issues, or OpenAPI specs using AI and a Bun-based runtime. This article explores its architecture, strengths, and quickstart.
LuaN1aoAgent uses a P-E-R multi-agent framework and causal graph reasoning to achieve 90.4% autonomous success on penetration tests with low exploit cost. Key for AI-driven pentesting.
Lynx generates personalized videos from a single image using a frozen Diffusion Transformer with ID and Ref adapters. This modular design balances fidelity and efficiency.
MarkPDFDown is a Python CLI tool that converts PDFs and images into Markdown by using vision-capable large language models for visual recognition-based parsing, handling complex layouts and formulas.
MASt3R-SLAM integrates a pretrained 3D reconstruction model as a geometry prior in a dense SLAM pipeline, enabling real-time tracking and mapping without classical bundle adjustment or depth sensors.
Matkap is a Python tool that hunts down malicious Telegram bots by hijacking leaked bot tokens and forwarding their messages for active threat intelligence gathering.
Metube is a self-hosted web UI for yt-dlp providing browser-based video downloading with playlist subscriptions, queuing, and a layered config system. Dockerized for easy deployment.
Mini-Wiki enables AI agents to generate and maintain structured wiki docs from codebases incrementally, using a safe instruction-based plugin system. Supports Mermaid diagrams and multi-language output.
qxresearch-event-1 is a collection of 50+ minimalist Python apps showcasing core AI patterns like fine-tuning, vector DB, and Whisper in about 10 lines each. A practical learning resource.
ML-From-Scratch offers bare-bones Python implementations of key machine learning algorithms using only NumPy, focusing on transparency over efficiency. Explore how it demystifies ML fundamentals.
MonoGS rethinks monocular SLAM by replacing point-cloud maps with differentiable 3D Gaussian splatting, enabling real-time dense reconstruction and camera tracking in a unified pipeline.
A practical guide to bishwaghimire’s AI learning roadmaps repository, offering modular, career-focused paths for AI and ML self-learners, with setup essentials and a flexible curriculum.
