A git-backed failure-memory system that allows AI agents to search and reuse verified recovery lessons to avoid repeating known debugging errors.

GenAI Prices is a multi‑language library (Python, JS/TS, Go) that supplies up‑to‑date pricing data and lookup logic for hundreds of LLM models across dozens of providers, supporting historic rates, tiered pricing, and daily price variations.

A distributed inference engine that clusters home devices over Ethernet to share RAM and accelerate LLM performance using tensor parallelism.

A collection of sample apps and tutorials for deploying and optimizing machine learning models on Qualcomm Snapdragon devices across Android, Windows, and Ubuntu.

Chorus is a management harness for coding agents that implements an AI-Driven Development Lifecycle, allowing teams of agents and humans to collaborate through a structured proposal-and-verify pipeline.

A self-hosted, multiplayer web workspace for running coding agents on isolated git branches with dedicated dev environments and cost tracking.

Go Micro is a Go framework that combines classic micro‑service building blocks (service discovery, RPC, pub/sub, storage) with first‑class LLM‑backed agents and durable, checkpointed workflows. Agents automatically expose services as AI tools, support planning, delegation, memory, and optional per‑call payments (x402). The system is fully pluggable (registry, broker, store, model provider) and ships a CLI for scaffolding, hot‑reload, and debugging. Ideal for building backend services, AI assistants, orchestrated business processes, and pay‑per‑use AI APIs.

Moss is a sub-10 ms semantic search runtime that embeds retrieval and embeddings directly into an application's process to eliminate network latency for real-time AI agents.

A comprehensive tabular analytics and learning toolbox that integrates over 45 machine learning methods and 300 datasets to benchmark and optimize performance on tabular data.

vLLM TPU is an open‑source plugin that lets you run PyTorch or JAX LLMs on Google TPUs using the same vLLM interface. It supports high‑performance features (async scheduling, KV‑cache offload, LoRA, speculative decoding, etc.) and is tested on many top models such as Gemma‑4, Llama‑3.1, and Qwen 3. Recommended TPUs are v7x, v5e, and v6e. The project provides quick‑start docs, a support matrix, and an active community for contributors.

A Rust-based, Git-compatible monorepo engine designed to provide AI coding agents with the full codebase context and infrastructure needed for petabyte-scale software engineering.

An AI-native framework for building data portals that uses agentic skills to recommend infrastructure and scaffold Next.js frontends with pluggable data backends.

A technical SEO auditing framework that turns Google's official documentation into an AI skill, allowing coding agents to audit live servers and fix technical SEO gaps.

A high-level PyTorch framework that provides a unified interface for applying various deep learning architectures to tabular data.

An open-source toolkit for implementing and evaluating prompt injection attacks and defenses, featuring specialized tools for detection and localization of contaminated prompts.

A free, open-source collaborative web application for developing and editing OWL 2 and OBO ontologies.

A self-hosted uptime and SSL monitoring service that tracks service availability and provides status pages and AI-driven management via an MCP server.

A fast and sensitive tool for comparing and clustering large protein structure sets, supporting both monomer and multimer searches with GPU acceleration.

A native Rust rewrite of Playwright that provides a faster, lower-memory browser automation engine for Chromium with built-in tools for AI agents.

A Python framework for developing and backtesting algorithmic trading strategies, with a focus on integrating machine learning models and high-performance execution.

A real-time status bar for Claude Code and the Claude macOS desktop app that displays rate limits, context window usage, and prompt-cache freshness.

A token-compression framework for AI coding agents that reduces Japanese response redundancy to lower API costs and save context space.

An open-source tool that packages machine learning models into production-ready Docker containers and automatically generates an HTTP inference server.

A Python library for causal and probabilistic reasoning using graphical models, providing tools for structure learning, parameter estimation, and causal inference.

A local-first issue tracker designed for coding agents and humans to collaboratively track, claim, and verify tasks via a CLI, TUI, and MCP server.

A fast Rust CLI that lets AI coding agents control a real browser via the Chrome DevTools Protocol using shell-native commands and stable element references.

A collection of official and community samples, model recipes, and deployment tools for LiteRT and LiteRT-LM to enable high-performance on-device ML execution.

before auth refactor

A collection of ready-to-use public datasets provided as tf.data.Datasets to simplify the process of loading and preparing data for machine learning.

A Kubernetes-native AutoML project that provides automated hyperparameter tuning, neural architecture search, and early stopping for any ML framework.

A comprehensive LLM quantization toolkit that compresses models using methods like GPTQ and AWQ with hardware acceleration for NVIDIA, AMD, Intel, and Huawei NPUs.

A collection of security skills and signed advisory intelligence for AI agent runtimes to verify artifacts, detect configuration drift, and gate risky installations.

A provider-agnostic evaluation infrastructure that provides standardized, reproducible benchmarking for LLMs across 95+ evaluation suites.

An agent control plane for governance, safety, and trust that provides a deterministic layer to define, enforce, and audit the behavior of autonomous AI agents.

A set of agent skills and tools that enforce WCAG 2.2 AA accessibility standards for AI coding agents across multiple platforms.

Gemi2Api‑Server is a FastAPI‑based bridge that lets you call Google Gemini via an OpenAI‑compatible REST API. It authenticates with Gemini using your browser cookies, forwards chat‑completion requests, optionally proxies generated images, and provides a simple admin UI. Deployable locally, via Docker, or on Render/HuggingFace, it’s useful for developers who want Gemini access without a formal public API.

An engineering governance and context framework for AI coding agents that provides shared instructions, architecture standards, and governed workflows across teams.

A TypeScript framework for building and shipping Model Context Protocol (MCP) servers with features like file system routing and hot reloading.

A component for the ESP-IDF platform that enables running TensorFlow Lite Micro on Espressif chipsets with hardware-optimized kernels for faster inference.

An open-source Python toolbox that provides a unified API and benchmark datasets for applying and training machine learning models in seismology.

A CLI tool and set of standards for building production-ready AI agents with standardized project structures, prompt versioning, and integrated testing.

A multi-user server that manages and proxies multiple single-user Jupyter notebook instances for groups of students, researchers, or data scientists.

A synthetic micro-benchmark tool for measuring the peak compute performance (TFLOPS/TOPS) of CPUs, GPUs, and NPUs across multiple backends like CUDA, ROCm, and ONNX.

A deterministic safety guard for AI coding agents that blocks catastrophic tool calls like filesystem deletion and secret theft without using an LLM.

A compiler that transforms ONNX graphs into optimized, low-runtime code using LLVM/MLIR technology for efficient model deployment.

An MCP server that provides a structured scratchpad for AI models to record sequential reasoning steps, validate tool plans, and manage reasoning history.

A synchronization tool that automatically keeps Open WebUI Knowledge Bases in sync with 46 different external data sources using incremental diffing.

A no-code, spreadsheet-like tool for building and enriching datasets using open-source AI models from the Hugging Face Hub or local LLMs.