Explore Ed Donner’s llm_engineering repo, an 8-week progressive Jupyter notebook course building from local LLMs to autonomous Agentic AI, emphasizing hands-on learning and budget-friendly API use.
Claude Code From Scratch reverse-engineers Anthropic’s coding AI with a minimal perception-action loop and typed tool dispatch. This repo offers a clear, incremental path to understanding a production-ready AI harness.
Explore genai-llm-ml-case-studies, a curated repo of 500+ production GenAI and LLM system design case studies from 130+ companies, organized by architecture, industry, and use case.
InternVL offers open-source multimodal large language models combining vision transformers and LLMs, featuring CascadeRL training and competitive benchmarks like GPT-4o.
jadx-mcp-server connects LLMs like Claude to a live JADX-GUI decompiler via the Model Context Protocol, enabling interactive AI-assisted reverse engineering of Android APKs.
Violin is an open-source video translation pipeline integrating Whisper speech recognition, LLM translation, TTS voice synthesis, and video remuxing. It supports CLI, web app, and Claude Code skill interfaces.
Web-Use is a Python autonomous browser agent that uses Chrome DevTools Protocol and LLMs to navigate and interact with web pages. Its WebMCP protocol enables dynamic tool discovery from websites.
ai-interview-codex offers a practical AI interview prep guide featuring iterative system design for Agentic AI and RAG, with benchmarks and production insights for ML, LLM, and system design roles.
Arkon is a self-hosted enterprise knowledge hub using a novel MRP pipeline for structured, traceable wiki compilation with external AI inference and workspace-scoped RBAC.
AutoSkill is a Python framework enabling LLM agents to extract, version, and evolve skills from dialogues, providing a persistent long-term memory system for AI agents.
ChatTutor integrates AI tutors with visual tools like Geogebra in a Vue + Bun full-stack. It supports multiple LLM providers and offers a digital whiteboard for interactive STEM learning.
Claw-Eval offers a Python-based evaluation harness for LLM autonomous agents, featuring 300 tasks and a strict Pass^3 metric to ensure reliable, multi-dimensional benchmarking.
Comic Translate uses advanced AI models and a multi-step pipeline for accurate comic translation across languages, combining speech bubble detection, OCR, and LLMs with full-page context.
DeepTeam is a Python tool for red teaming LLMs by dynamically generating adversarial attacks and evaluating vulnerabilities like bias. It requires minimal setup and no predefined datasets.
DeepZero automates vulnerability research on Windows kernel drivers by chaining Ghidra decompilation with LLM-based analysis using YAML pipelines and Jinja2 templates.
Dot bundles local LLM inference, Retrieval Augmented Generation, and Text-To-Speech into a single offline Electron app, enabling document QA without cloud dependencies.
FuzzyAI combines fuzz testing with AI models using Python and Ollama. It offers a CLI for fuzzing with local LLMs, balancing AI power and practical setup tradeoffs.
Harvey LAB offers an open-source benchmark for evaluating LLM agents on realistic legal tasks using an all-pass rubric and LLM-as-judge scoring. It includes datasets, adapters, and dashboards.
Mini-SGLang is a modular Python reimplementation of the SGLang LLM inference engine with production features like Radix Cache, chunked prefill, overlap scheduling, and tensor parallelism.
PicoAgents is a Python multi-agent framework built from scratch, offering transparent agent orchestration, LLM provider abstraction, streaming UI, and production-ready benchmarks.
