An AI-assisted toolkit for enterprise architects to transform architecture governance into a systematic workflow for strategy, design, and assurance.

A pure C implementation of an AI assistant for the ESP32-S3 chip, providing a low-power, always-on agent with local memory and tool-calling capabilities via Telegram.

A multi-agent AI code review system that uses independent reviewer personas and structured discourse to provide redundant, requirements-aware feedback on code changes.

A macOS menu bar app that monitors AI coding assistant usage quotas in real time across multiple providers, featuring Touch Bar and Notch integration.

A compute substrate for AI agents that provides hardware-isolated, persistent micro-VMs to run OCI images securely.

A production-grade SQLite extension that brings efficient vector search and quantization to embedded databases for Edge AI and RAG applications.

A comprehensive toolkit for large model compression that provides unified access to quantization, speculative decoding, and sparse attention to reduce model size and increase inference speed.

An MCP bridge that gives AI agents full access to SAP ADT APIs for ABAP development, debugging, and system analysis without requiring server-side installations.

A Python framework for creating production-ready data engineering and data science pipelines using software engineering best practices.

A code and markdown context engine that uses AST-aware structural search to provide AI agents with complete, meaningful code context without requiring indexing or embeddings.

A practical guide and benchmark suite for running local LLMs on AMD Strix Halo / Ryzen AI MAX+ 395 systems, providing setup scripts and evidence-based performance profiles.

An open-source optical design platform in Python that supports classical lens systems and computational optics through differentiable modeling and GPU acceleration.

A collection of agent skills for automating PR review workflows across GitHub, GitLab, and Perforce using Greptile.

An MCP server and C++ plugin that enables AI assistants to control Unreal Engine, automating tasks from asset management to cinematic sequencing.

A benchmark for evaluating document parsing tools to ensure they convert PDFs into structured output that AI agents can reliably use for autonomous decisions.

A VS Code extension that integrates multiple LLM API providers into GitHub Copilot Chat, enabling the use of custom models and advanced code completion.

An open-source forecasting agent that combines LLMs with time series foundation models to automate model selection and provide natural-language analysis of forecasts.

An OpenAPI-native toolchain that automatically generates type-safe SDKs, Terraform providers, and contract tests from API specifications.

An automated pipeline for de novo binder design that uses AlphaFold2 backpropagation, ProteinMPNN, and PyRosetta to create proteins that bind to specific targets.

A security layer for AI coding CLIs that blocks destructive commands and access to sensitive secrets before they are executed by an agent.

A benchmark that measures the ability of CLI agents to autonomously post-train pre-trained LLMs to improve their performance on specific benchmarks.

An MCP server that enables AI agents to read, search, and edit Notion workspaces using token-efficient Markdown tools.

A risk-aware AI programming workflow plugin that prevents AI drift by routing changes through lightweight or full specification and review paths based on change risk.

An AI-native CLI for trading crypto, stocks, forex, and derivatives on Kraken, featuring a built-in MCP server for seamless AI agent integration.

A Go CLI for evaluating AI agent skills by scaffolding evaluation suites, running benchmarks, and comparing results across different models.

A macOS application that centralizes the search and management of local conversation histories from various AI coding agents while tracking quota usage.

LightLLM is a Python‑based, high‑performance inference and serving framework for large language models. It combines fast kernels (FlashAttention, Triton) with lightweight, token‑level KV‑cache management, supports multi‑GPU scaling, and adds research‑grade features like constrained decoding and SLA‑aware request scheduling.

A self-hosted mission control dashboard for AI coding agents that provides persistent sessions, mobile-optimized access, and autonomy tools for unattended runs.

A full-system DNN hardware exploration platform that allows architects to design and evaluate the performance of AI accelerators using a configurable systolic array architecture.

A desktop companion plugin for DeepSeek Harness that provides a real-time, always-on-top visual status indicator of an AI agent's work progress.

A privacy-first CLI for semantic code search that uses vector embeddings to find code by meaning rather than exact text, reducing token usage for AI agents.

A research project and toolkit for analyzing and improving On-Policy Distillation (OPD) in LLMs, providing strategies to recover failing distillation and understanding its token-level mechanisms.

A tool for bypassing CPU memory protections by scrambling DRAM address translations via the memory controller to expose protected regions like the PSP and SMM.

DocETL is a declarative and agentic framework for processing large-scale structured and unstructured data using LLMs, automating the optimization of prompts and models for cost and accuracy.

A Claude Code plugin that uses the Balanced Coupling model to analyze and design modular software architectures to prevent technical debt and coupling imbalances.

A CLI for spec-driven development that turns product intent into a governed AI coding workflow with repo-native tracking and git worktree isolation.

A Rust-native local repository intelligence tool that provides a persistent SQLite map to help coding agents navigate large codebases and reduce token costs.

A Python package for probabilistic record linkage and deduplication that identifies and links records without unique identifiers using the Fellegi-Sunter model.

A modern attack surface reconnaissance platform that uses a decoupled microservices architecture and MCP integration to map enterprise assets and monitor vulnerabilities.

A collection of Colab notebooks for fine-tuning and running inference on various open-source LLMs, featuring data prep and advanced training techniques like GRPO.

A complete X/Twitter automation toolkit providing scrapers, a CLI, and an MCP server for AI agents, allowing full platform interaction without requiring official API keys.

CuPy is a NumPy and SciPy-compatible array library that enables GPU-accelerated numerical computing for Python on NVIDIA CUDA and AMD ROCm platforms.

A native macOS workspace for running MLX models locally on Apple silicon, featuring a chat interface, model manager, and OpenAI-compatible API server.

A high-performance code-intelligence engine that indexes codebases into a knowledge graph to provide AI agents with precise context, reducing token usage by up to 50x.

A durable red-team runtime for Codex App and CLI that automates security workflows using goal contracts and evidence-based verification to prevent session interruptions and false completions.

A universal AI gateway that provides a unified local endpoint for multiple AI providers, enabling tools like Claude Code and Codex to share a single server.

A sudoless Apple Silicon system monitor that provides deep visibility into the Neural Engine, Media Engine, and memory bandwidth to help optimize on-device AI and media workloads.

A unified model and agent manager that lets you run any AI agent on any local or hosted model using a single command and a standard OCI-based storage system.