A CLI tool that converts websites into a compact, numbered format for AI agents to browse the web without burning excessive tokens.

A library for creating environments to train and evaluate LLMs, specifically designed for reinforcement learning workflows.

A multi-account proxy for Claude Code and Codex that pools multiple accounts and automatically rotates them to bypass API quota limits.

A macOS menu bar app that turns AI coding token usage from various tools into a gamified Pokémon collection experience.

A Python library that provides an easy way to integrate Python projects with Ollama for managing and running local and cloud-based LLMs.

A library of hardware-efficient building blocks and optimized kernels for linear attention, state space models, and hybrid LLM architectures.

An open-source infrastructure for running AI-generated code in secure, isolated cloud sandboxes via JavaScript and Python SDKs.

A lightweight VM library for AI agents that provides secure code execution and POSIX utilities with significantly faster cold starts and lower memory overhead than traditional sandboxes.

An open-source framework that simplifies the integration of multiple super-resolution technologies and graphics effects from various hardware vendors into games and applications.

An open-source, self-hosted ERP for construction project management that provides tools for BOQ, BIM/CAD takeoff, 4D scheduling, and 5D cost modeling.

A plugin and MCP server that integrates the JADX decompiler with LLMs to provide real-time, context-aware reverse engineering and vulnerability analysis for Android APKs.

A 3D visualization tool that replays coding-agent sessions on a map of a codebase to reveal how agents explore and modify files.

Vespa is an open‑source platform for large‑scale search and AI serving, offering vector/tensor indexing, real‑time model inference, and low‑latency query processing. It can be run on Vespa Cloud or self‑hosted, with extensive docs, sample apps, and a permissive Apache 2.0 license.

A strong, open-source UCI Xiangqi engine derived from Stockfish that uses NNUE neural networks to analyze positions and compute optimal moves.

CORAL is an open-source infrastructure for autonomous AI agent organizations to perform autoresearch by running experiments and sharing knowledge to evolve solutions.

Agent Relay is an open‑source toolkit that lets teams run LLM‑based coding agents together with existing tools (GitHub, Slack, Notion, etc.). It provides messaging, virtual‑filesystem integrations, searchable session logs, and TypeScript‑defined deterministic flows, enabling auditable, rule‑driven automation of code‑generation and review tasks.

An open-source observability database that unifies metrics, logs, and traces into a single columnar engine on object storage, enabling SQL-based correlation across signals.

A proxy service that converts the Qwen web interface and CLI into an OpenAI-compatible API, enabling the use of Qwen models in any OpenAI-supported client.

A lightweight C++20 JIT runtime for NVIDIA CUDA and HUAWEI Ascend NPUs that handles kernel compilation, caching, and loading for device kernel libraries.

A security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code using static analysis, dataflow analysis, and LLM-based semantic checks.

A collection of SQL and AI-based models for detecting financial fraud, credit risk, and regulatory compliance issues in lending and corporate finance.

An AI agent skill that redesigns GitHub READMEs by reorganizing content hierarchy and creating project-native SVG visuals to make a project's value immediately clear.

A REST API-based automation engine that enables AI agents to control the Unity Editor through a library of over 800 specialized skills.

An open-source developer platform for Kubernetes that provides high-level abstractions and a developer portal to simplify app deployment and operation for developers and AI agents.

A Spring-friendly API and abstraction layer for Java developers to integrate various AI models and vector stores into enterprise applications with portability and modularity.

An orchestration-builder SDK for multi-agent coding workflows that provides configurable infrastructure for work routing, runtime providers, and state reconciliation.

An open-source credential proxy and vault that prevents AI agents from leaking secrets by brokering API access through a secure MITM proxy.

XGBoost is an optimized distributed gradient boosting library that provides fast and accurate parallel tree boosting for large-scale data science problems.

A unified Rust-based messaging broker that supports multiple protocols and provides dedicated communication infrastructure (mq9) for AI agent discovery and asynchronous messaging.

TokenSave is a local MCP server that builds a semantic knowledge graph of a codebase, letting AI coding agents query symbols, callers, and impact instead of scanning files with grep and read, cutting token usage and tool calls.

A container-native workflow engine for Kubernetes that orchestrates parallel jobs, specifically optimized for machine learning pipelines and data processing.

A benchmarking suite that evaluates autonomous LLM coding performance by tasking models with building a Ruby on Rails application and auditing the results via a strict technical rubric.

Entroly is a local-first context assurance layer that reduces AI token costs by selecting and compressing relevant codebase evidence while providing receipts to recover original data exactly.

A 100-line minimalist LLM framework that uses a graph-based abstraction to build agents, RAG, and workflows without the bloat of traditional frameworks.

A collection of samples and tutorials for Amazon Bedrock AgentCore, providing the infrastructure to deploy and operate framework- and model-agnostic AI agents securely at scale on AWS.

A toolkit for AI coding assistants to access comprehensive US and HK market data, including options Greeks, SEC filings, and short volume, without needing API keys.

An open-source, cloud-native vector database that enables semantic search at scale by storing objects and vectors together.

A keyboard-driven management layer for AI coding agents that automates git worktrees and provides a unified interface for running multiple CLI agents in parallel across any OS.

A lightweight, 100% Rust OpenAI-compatible inference server for GGUF models that runs on the Airframe WebGPU engine.

NeMo AutoModel is a Python library from NVIDIA that provides ready‑to‑use, highly‑optimized training recipes for a huge range of LLMs, VLMs, and diffusion models. It supports full‑parameter and LoRA fine‑tuning, multi‑node tensor‑ and pipeline‑parallelism, and even speculative‑decoding drafters, all driven by simple YAML configs.

A Kubernetes operator that simplifies the deployment, autoscaling, and management of Ray clusters for distributed AI workloads like LLM training and inference.

A hybrid edge-cloud AI engine for mobile devices and wearables that optimizes inference for text, speech, and vision models using custom quantization and hardware-specific kernels.

A professional data analysis skill for AI agents that prevents silent calculation errors in Excel by implementing a rigorous 8-step audit and reconciliation workflow.

An open-source SERP API and CLI that provides structured search results from multiple search engines without API keys, designed for LLM grounding and SEO tracking.

A native macOS terminal for running and supervising multiple AI coding agents in parallel, featuring a unified approval inbox and MCP-based inter-agent communication.

A unified, offline history viewer for 29 AI coding assistants that allows users to browse, search, and analyze conversations across different tools in one interface.

A mobile companion for the Codex CLI that lets you monitor and steer AI coding sessions from your phone while keeping the actual work and data on your computer.

A Docker-based deployment framework for vLLM optimized for NVIDIA DGX Spark, enabling high-performance single-node and multi-node cluster inference.