Agentset is an open-source platform for building, evaluating, and shipping production-ready RAG and agentic applications, providing end-to-end tooling from ingestion to hosting.

A tmux-native TUI workspace for managing multiple terminal AI agents, allowing users to preview conversation history and jump between sessions quickly.

A governance and engineering system that transforms rough workflows and prompts into reusable, cross-platform AI agent skill packages with built-in evaluation and release gates.

A lightweight search engine supporting full-text, vector, and hybrid search, enabling developers to build fast search and RAG-based chat experiences directly in their apps.

An interactive REPL CLI that provides AI coding agents with persistent, structured memory and a version-controlled context tree for project knowledge.

An AI-powered Rust development assistant that uses a meta-cognition framework to provide architecturally sound solutions instead of surface-level syntax fixes.

A native macOS menu bar application that monitors AI token usage and subscription quotas across 25+ AI coding agents by parsing local session logs.

An agent skill that transforms architecture discussions into a single-source-of-truth data file, generating both an interactive isometric map and a synchronized text documentation file.

A custom vLLM-style inference engine implementation that benchmarks Flash Attention and Paged Attention to optimize LLM prefilling and decoding.

An MCP server that enables AI agents to control and operate TouchDesigner projects by creating nodes, modifying parameters, and executing Python scripts.

A local-first observability and debugging tool for TypeScript AI agents that turns execution traces into readable trees and deterministic trajectory checks for CI.

A local proxy server that transforms the Google Gemini web interface into a standardized REST API using browser cookies instead of API keys.

A high-performance LLM inference acceleration engine developed by Alibaba that optimizes throughput and latency for production-scale deployments.

OpenLLM is a tool for self-hosting open-source LLMs as OpenAI-compatible APIs, providing a simplified workflow for local serving and enterprise cloud deployment.

A transactional storage engine for Zarr tensor data that enables safe, parallel read/write access and version control on cloud object storage.

A plugin for the OpenCode IDE that automatically reads Claude Code OAuth tokens (from macOS Keychain or a JSON file), refreshes them when needed, and injects the proper `Authorization: Bearer` header into every Anthropic API request. It works on macOS, Linux, and Windows, supports multiple Claude accounts, and requires no manual API‑key configuration.

An open-source compiler that translates CUDA, HIP, and Triton kernels into binaries for AMD, NVIDIA, and Tenstorrent GPUs, as well as x86-64 CPUs.

An MCP server that connects AI coding assistants to Sentry, allowing agents to search for errors, issues, and traces to assist in debugging.

A high-performance framework for pretraining, finetuning, and deploying 20+ LLMs with from-scratch implementations and no abstraction layers.

An automated vulnerability discovery system that uses a multi-agent AI framework to screen projects, audit source code, and generate CVE reports.

An MCP server that lets you manage Coolify self-hosted PaaS using natural language, providing 45 tools for deploying, debugging, and operating infrastructure via AI clients.

An open-source canvas editor and graphics engine powered by Rust and Skia, featuring Figma interoperability and headless rendering capabilities.

A red-teaming framework that uses a Task-Validator-Data (TVD) self-loop to bypass LLM safety guardrails by framing harmful content generation as a coding task.

A library for processing, filtering, and deduplicating massive text datasets at scale, specifically optimized for LLM training data preparation.

A configuration and component manager for OpenCode that enables users to apply portable, SHA-verified profiles and components across different repositories.

An AI-native proxy server and data plane that centralizes agent orchestration, LLM routing, and observability to simplify the deployment of production agentic applications.

A specialized IDE replacement for orchestrating multiple AI agents in parallel, using ephemeral worktrees and linked task cards to automate complex coding workflows.

A platform for building and deploying reusable, scalable end-to-end machine learning workflows on Kubernetes.

Cache‑DiT is a PyTorch‑native inference engine that accelerates diffusion‑transformer (DiT) models with hybrid activation caching, various parallelism strategies, optional 8‑/4‑bit quantization, and CPU layer‑offload. It supports 40+ DiT families (image, video, audio, 3‑D) from Hugging Face Diffusers and integrates with tools like ComfyUI, SGLang, vLLM‑Omni, TensorRT‑LLM, and Jetson containers.

An ASI plugin for OptiScaler that enables DLSS and DLSS-FG inputs in supported games without spoofing, reducing crashes and performance overhead for AMD and Intel users.

A free, open-source local AWS emulator for integration testing and local development that provides a 100% conformance with AWS services without requiring accounts or tokens.

A compact, high-performance similarity search and clustering engine for vectors and text that is designed to be faster and more portable than FAISS.

An MCP server that integrates QuickBooks Online with AI agents, providing 145 tools for managing financial entities and generating reports.

A developer platform for building application logic using a synchronized text-and-canvas interface and a high-performance Rust runtime.

XNNPACK is a highly optimized library of low-level performance primitives used to accelerate neural network inference across ARM, x86, WebAssembly, and RISC-V platforms.

A project providing sandboxed, ready-to-use Chrome browsers for browser automation and AI web agents, featuring remote GUI access and ultra-fast unikernel-based restarts.

A cloud cost intelligence tool that provides real-time cost estimates and FinOps policy enforcement for infrastructure-as-code before deployment.

A Swift API for the MLX array framework that enables machine learning research and experimentation on Apple silicon.

An integration layer that enables AI coding tools to manage and deploy backend infrastructure, including databases and cloud functions, on Tencent CloudBase.

A Model Context Protocol (MCP) server that connects LLMs to JADX, enabling AI-powered live reverse engineering and vulnerability analysis of Android APKs.

A comprehensive SEO audit tool that scans websites against 332 rules to provide actionable reports on technical SEO, performance, and AI search readiness.

aimock is a zero‑dependency Node.js mock server that emulates all major LLM, vision, speech, video, embedding, vector‑db, and agent‑to‑agent endpoints. It lets you record real API interactions and replay them deterministically, supports chaos testing, drift detection, Prometheus metrics, Docker/Helm deployment, and integrates with popular AI frameworks. Ideal for fast, cost‑free end‑to‑end testing of AI applications.

An MCP server that gives AI assistants direct access to shadcn/ui v4 components, blocks, and metadata across React, Svelte, Vue, and React Native.

A collection of open-source inference technologies from Perplexity AI, featuring RDMA-based communication for LLMs, a CPU-optimized tokenizer, and a Metal-based inference server for Apple Silicon.

A framework for training speculative decoding models that are directly compatible with SGLang to accelerate LLM inference speed.

A comprehensive GRC platform for cybersecurity management that simplifies compliance and risk assessment through a decoupled data model and a vast library of security frameworks.

A high-performance, distributed data integration tool that synchronizes multimodal data (text, video, images) across hundreds of diverse sources.

A lightweight vector database that uses graph-based selective recomputation to reduce storage by 97%, enabling local RAG on millions of personal documents.