quiche

An Apache-2.0-licensed serving setup for Qwen3.8-27B on a single 24 GB NVIDIA GPU, built around vLLM and exposing an OpenAI-compatible API with optional key authentication. Its preparation pipeline starts from a W4A16 AutoRound model, requantizes the language-model head and embedding matrices to int8, requantizes the MTP components, and applies vLLM patches for the serving stack. The runtime combines int8 tensor-core GEMMs with an fp16 recurrent state, continuous batching, split-KV verification attention, and speculative decoding through either Qwen's MTP path or the optional DFlash2 block drafter; DFlash2 can also draft from the request's cached context for document-reproduction workloads. The repository provides Docker Compose profiles for batch throughput and single-user latency, prebuilt container images, model-download and requantization scripts, benchmark and quality-test tools, and launchers for fast, long-context, and experimental KVarN cache modes. The standard configurations target roughly 64k to 150k tokens of context, while KVarN and alternative int4 KV-cache paths extend the claimed capacity to the 256k-token range with lossy KV quantization. The setup requires a recent NVIDIA driver and a compatible Ampere-or-newer GPU; the repository notes that its benchmark figures were measured on an RTX 3090 subject to a 250 W power limit.

RustFS is an open-source, distributed object storage system built in Rust. It provides S3-compatible storage for data lakes, AI, and big-data workloads, with single-node and distributed deployments, versioning, object lock, server-side encryption, replication, lifecycle management, quotas, event notifications, IAM policies, audit logging, and a web console. It also supports the OpenStack Swift API with Keystone authentication, plus SFTP, FTPS, and WebDAV interfaces. RustFS can be deployed from binaries, Docker or Podman, Docker Compose, Kubernetes through Helm, Nix, or from source. Its S3 compatibility is tracked in a compatibility matrix, and selected features such as S3 Tables through an Iceberg REST catalog and MinIO on-disk compatibility are marked as preview. The project is licensed under Apache 2.0.

QM is a multiplayer agent harness for startups that operates through Slack and a web interface. It gives each employee and room an isolated scope with its own memory, files, keychain view, permissions, scheduled jobs, web apps, and durable sandbox, while supporting collaboration in channels, group messages, and projects. Shared skills can be granted by scope, promoted by administrators, or imported from Git repositories; background work can run through crons, watches, and inbound webhooks, and internal apps can be published to selected users. A headless TypeScript core runs directly on Node with Fastify and handles identity, policy, scheduling, persistence, and the agent loop. Deployments can select harnesses and models including Pi, OpenCode, Codex, and Claude Code. PostgreSQL stores sessions, memory, queues, and other durable state, while a fixed tool surface includes an execute tool that runs commands in each scope's isolated, persistent sandbox. Slack is an optional in-process Bolt plugin; the web UI, admin panel, and public portal are optional HTTP API plugins built with Vite and Lit. Each deployment keeps organization-specific configuration, tools, skills, sandbox images, and infrastructure in a deployment directory validated and deployed by the qm CLI. Administrators can set organization-wide configuration, available harnesses and models, and a security posture. Strict mode pauses harness tool calls for human approval, Auto mode screens provenance-labelled external data and tool results with a classifier, and Dangerous mode disables content screening and pauses; a predeclared command policy with approvals and hard denials for operations such as recursive deletion or destructive SQL applies in every posture. Deployments run in the operator's own cloud account and are initialized from the @yc-software/qm package without requiring a source checkout; the project documents its threat model, operator assumptions, and known limitations in SECURITY.md.

Cua is an open-source computer-use platform from Cua AI, Inc. that provides desktop automation, isolated cloud desktops, local virtual machines, and benchmarks for AI agents. Its Cua Fleets provision Linux desktops whose capacity is managed in pools; agents use the Sandbox SDK to run commands, capture screenshots, and interact with applications. Cua Driver exposes tools for inspecting and operating native desktop applications and browsers on macOS, Windows, and Linux through a CLI, MCP, or typed SDKs, with background delivery where supported. Lume creates and manages local macOS and Linux virtual machines on Apple Silicon using Apple's Virtualization framework. Cua Bench builds computer-use tasks, evaluates agents, and exports trajectories for training, including simulated tasks that do not require a VM, Docker, or a model API key. The project is MIT-licensed, while some third-party components have separate licenses.

Cloudreve is a self-hosted file management and sharing system developed by the Cloudreve project. It stores files in local or remote storage providers, including OneDrive and S3-compatible services, and provides a web interface for uploading, browsing, downloading, previewing, editing, and sharing files. It supports background downloads through Aria2 or qBittorrent, WebDAV across storage providers, resumable parallel uploads, archive handling, metadata and tag search, multi-user groups, expiring share links, and online editing of text, diagrams, Markdown, images, and Office documents. The project is distributed as an all-in-one package, can be deployed locally or in production, and is built with Go, Gin, and ent alongside React, Redux, and Material-UI. It is licensed under GPLv3.