2,417 tools and products — trending open source, and what gets used in AI and other work.
numbat is an open-source endpoint security tool for monitoring AI-agent activity across supported desktop, CLI, IDE, and gateway agents. It combines local hooks and plugins, OTLP/HTTP logs, and on-disk session artifacts, normalizes live and stored activity into a common event model, and evaluates it locally with built-in, sequence-based, or custom YAML CEL rules. The tool can produce NDJSON events, findings, enforcement decisions, indicators, and scan summaries for alerting and forensic reconstruction, including read-only artifact scans, per-session timelines, and portable case bundles with SHA-256 manifests. Optional pre-action blocking is disabled by default and is limited to supported synchronous hooks and explicitly enforced rules. It is distributed as a single cgo-free binary for macOS, Linux, and Windows, with read-only inventory and scanning commands.
mirador is an open-source terminal dashboard built with Rust and ratatui for keeping in a terminal tab and glancing at throughout the day. It provides configurable panels for world clocks, a calendar and agenda, weather, an editable task list, notes, a market watchlist, a calculator, RSS news feeds, and live CPU and network charts; panels can be enabled, rearranged, focused, and edited through keyboard controls. Tasks, notes, and the watchlist are stored as hand-editable TOML files rather than in a database or sync service. The dashboard uses keyless public endpoints for weather and market data and configurable RSS feeds for news; the project states that it requires no account, API key, or telemetry and does not contact external services unless requested.
kimi-k3-mlx is an MLX port for Apple Silicon of Moonshot’s Kimi K3 native-multimodal mixture-of-experts model. It provides a stock `mlx-lm`-compatible text model definition, a 3D video-capable MoonViT vision tower with a patch-merger projector, and an `mlx-vlm`-shaped wrapper that joins the language and vision components. The model has a 1-million-token context and uses routed and shared experts, Kimi Delta Attention, gated multi-head latent attention, Attention Residuals, latent-dimension experts, and the SiTU-GLU activation; routed experts are distributed in MXFP4 while other weights use bf16. The multimodal processor expands each image placeholder into a feature block rather than performing a same-length one-token-per-image scatter. The repository includes a streaming converter because standard `mlx-lm` conversion would materialize the multi-terabyte bf16 model, along with REAP expert-pruning scripts and expert-overlap analysis using Chinese, English, code, or mixed calibration data. It also contains vision-parity tests against Moonshot’s reference implementation. The repository states that the full model cannot run on a single Mac: even its smallest deployment tier requires hundreds of gigabytes of memory and exceeds the capacity of the largest Apple Silicon machine.
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.
Headroom is a local-first macOS menu-bar app for monitoring AI coding quotas and software delivery status, with optional iPhone, iPad, Apple Watch, and ESP32 desk-display clients. A Python host running on the Mac reads the authentication data and command-line tools already configured for services such as Claude, Codex, Cursor, GitHub, and Vercel, then serves a single local JSON feed; credentials remain on the machine and no Headroom cloud account is required. Its interfaces show provider quota meters, usage rings, burn rate and spend, failed Actions, deployments, monitors, and other attention items, and the iPhone client can approve, deny, or reply to Claude and Codex requests without starting work. The Mac host uses port 8737, requires macOS 14+ and Python 3.9+, and the optional desk display uses a Waveshare ESP32-S3-Touch-AMOLED-1.8 board.
Bindwidth is a browser-based calculator for sizing on-premises LLM inference infrastructure and estimating total cost of ownership. It evaluates three constraints for a resident text model—KV-cache memory, combined prefill and decode serving capacity, and the runtime session ceiling—and identifies which constraint binds for a workload. The tool accounts for interactive users and autonomous agents as different load types, then compares owned hardware, eligible sovereign rentals, and enterprise subscriptions with per-token APIs for agents. It distinguishes measured from estimated hardware and model data through confidence levels and profile-specific overrides, flags domain and model-capability limits, and exports a decision record as Markdown or the full scenario as JSON. The repository describes it as a directional sensitivity estimator rather than a procurement quote. It is a frontend-only application with no build step, server, database, account, or telemetry; calculations run in the browser and entered data is not transmitted.
drydock is a Rust terminal user-interface dashboard for monitoring the state of Git repositories across configured directories. It reports uncommitted changes, unpushed commits across all local branches, conflicts and unfinished merge or rebase operations, and release status based on tags, including commits or changes made after the latest tag. The dashboard uses color-coded states, supports filtering by repository activity and condition, fuzzy search, sorting, repository details, and actions such as fetching, opening an editor or terminal, and viewing the remote. It runs on macOS and Linux and can be installed with Homebrew, Cargo, or from source.
Octop is an open-source, self-hosted AI assistant platform for households and small teams. It runs as a single process, storing conversations, workspaces, credentials, and shared state in a SQLite database under ~/.octop/, while serving a web dashboard, CLI, chat integrations, and cron automation. Users can switch among specialized personal agents through its multi-agent architecture. Built on the Harness stack, Octop combines an agent runtime for model routing, tools, skills, and conversation checkpoints with a gateway that normalizes messages from supported chat platforms into one processing pipeline. It also provides a built-in expert library, portable workspace memory, OAuth and MCP connectors, ACP integration for IDE and terminal workflows, browser automation, terminal-assisted command execution, and remote desktop access. The project uses FastAPI and uvicorn, React with TypeScript and Vite, SQLite through aiosqlite, and APScheduler. Its security features include JWT-based multi-user isolation, tool approval, shell-command guardrails, and PII redaction; supported storage backends include local disk, Docker containers, PostgreSQL, and COS/S3.
Phone Harness is an open-source harness that lets AI agents such as Claude Code, Codex, or other LLMs control a real iPhone or Android phone without a jailbreak, injected app, Xcode, WebDriverAgent, or on-device installation. It exposes helpers for opening apps, reading screen content, tapping, scrolling, typing, and verifying actions. On iPhone, it uses the macOS iPhone Mirroring window as the transport: screenshots are captured from the window, Apple's Vision framework performs OCR and returns tap-ready coordinates, and HID-level CGEvents provide taps, long presses, drags, flicks, scrolling, Unicode typing, and shortcuts. On Android, it uses ADB over USB or Wi-Fi, combining screenshots with the phone's accessibility tree for text and element bounding boxes. Actions can be verified by capturing the screen again, with the screenshot serving as the ground truth rather than relying on a DOM. Each invocation is self-contained rather than relying on a daemon.
Kage is an interactive five-chapter night walk through a Kyoto mountain temple, rendered live in Three.js and WebGL. As the page scrolls, a camera moves through procedurally constructed architecture, lantern light, fog, rain, drifting leaves, terrain, a vermilion moon, and a restrained bloom pipeline. Generated scene plates, alpha-preserving WebP foreground artwork, editorial typography, and section-specific fade and blur transitions are layered over the live 3D world. The project is a deliberately small static site contained in one HTML document, using a vendored Three.js r149 build without a package manager or build step. It includes chapter navigation, responsive mobile layout, reduced-motion behavior, and a custom cursor for precise pointer devices; it has no runtime network dependency. No license is granted for reuse or redistribution of the original Kage code or artwork, while the included Three.js runtime retains its MIT license notice.
git-knife is a desktop GUI for editing Git commit metadata, including messages, author and committer names and email addresses, and author and committer dates. It can open a repository and edit a local branch by its ref without checking it out, leaving the working tree untouched. The application shells out to the system Git CLI and rebuilds commits with `git commit-tree`, reusing each commit's original tree so the file contents are not changed. It supports literal or regular-expression find-and-replace across metadata fields, previews changes before applying them, preserves merge parents when rebuilding the commit graph, and creates an automatic backup ref for restoration. It also warns about rewriting pushed history and flags signed commits whose signatures would be affected. The repository describes reorder, squash, and drop operations as not yet implemented. Development requires Git 2.x, Node.js with pnpm, and Rust; Tauri build workflows target macOS, Linux, and Windows.
Ante is a self-contained terminal coding agent and agent harness developed by Antigma Labs. It is distributed as a single Rust executable with no runtime dependencies and is designed to work with provider APIs, subscriptions, or local GGUF models. Its core embeds Grep and git operations in one process and uses a managed version of llama.cpp for local inference. In offline mode, it runs the coding-agent loop entirely on the user's machine without an API key, account, or internet connection; settings profiles can define the agent and its system prompt. The project also supports multiple providers, multi-agent orchestration, MCP skills, and memory. Ante is in beta preview, with breaking changes and incomplete functionality expected. The repository states that macOS and Linux are supported and recommends WSL for Windows.
Airship is a command-line visual editor for existing web applications, developed by Airship Labs. It runs as a reverse proxy in front of a development server and presents the application on an infinite canvas or in an inline editor, with live frames for different device sizes. Developers can select an element, describe a change, review the resulting diff, and have Claude Code, Codex, or OpenCode update the source file that rendered it; changes can also be undone. It works with applications serving HTML over HTTP, including Vite, Next, Remix, and Rails, without plugins, configuration changes, or additions to the project's dependencies or bundle. The CLI can connect to an existing server or start it with a command, and the README states that operation stays on the local machine without an account, telemetry, or separate hosted service.
PartMode is an open-source, local-first browser-based mechanical CAD application built on OpenCascade WebAssembly, replicad, and three.js. It provides constrained sketches, editable feature history, exact B-rep solid evaluation, multiple bodies, assemblies with mates and exploded views, drawings, inspection tools, and import or export for formats including STEP, STL, AMF, 3MF, SVG, DXF, and PDF. People work through the CAD interface, while permissioned typed agents operate against the same canonical document schema and exact geometry kernel. Browser-approved agents can edit the open project; a separate headless workflow uses an account-owned document. The application runs without a desktop CAD installation, supports anonymous local browser modeling with optional hosted agent connectivity, and is distributed under the GNU AGPL v3 license.
VoCat is an open-source web control panel and engineering toolkit for Quectel EC20-, EC25-, EG25-, and related Qualcomm-based cellular modems. It provides automatic serial and USB modem discovery, live radio and registration metrics, operator scanning and network selection, AT and USSD terminals, SMS transmission and synchronization with delivery reports, Wi-Fi Calling through IKEv2/ePDG and EAP-AKA, eSIM/eUICC profile management, proxy routing, notifications, audit logs, and Telegram controls. The backend is written in Go, the interface uses React and TypeScript, and the production frontend is embedded in a single Go executable that uses SQLite for persistent state. It is distributed through static Linux binaries, a Docker image, systemd installation, and automated GitHub Actions releases; available functions depend on modem firmware, USB composition, SIM or eSIM capabilities, drivers, network, and carrier configuration.
An open-source collection of Markdown output styles for Claude Code, Codex, and other coding agents. It changes how an agent communicates rather than how it codes: responses are answer-first, written in plain English, and formatted for skimming. The collection includes Attention-kind, which spaces points apart, uses arrows and bold emphasis, and expands only when useful; Spartan, a terse style with no warmth; and Rundown, a brief-briefing style. Each style is a single Markdown file that can be added and switched on independently.
Mkdirs is an open-source Next.js template for building AI-powered directory websites. It provides listings with categories, collections, tags, and search; user authentication and dashboards; AI-assisted submission and content generation; and free, paid, or sponsored submissions through Stripe. Sanity supplies the content management system and blog, while Resend handles transactional email and newsletters. The template also includes SEO, analytics, themes, responsive layouts, and deployment options for Vercel and Docker. It is developed by OpenFox and licensed under Apache License 2.0, with the Mkdirs name, logo, and trademarks excluded from permission to identify derived products.
pyroclear is an open-source Rust replacement for the terminal `clear` command. It displays animated ASCII flames before erasing the visible screen and scrollback buffer, with native Unix and Windows console support, terminal resizing, transparent empty cells, and signal-safe terminal-state restoration. Its interactive TUIs provide palette selection, settings for frame rate, wind or drift, animation duration, and flame height, plus a manager for creating and saving custom hexadecimal gradients. Named palettes and one-off gradients can also be selected from the command line, while configuration is stored in a platform-specific user configuration file. The repository documents installation through Cargo, source builds, and NixOS flakes, with no third-party runtime dependencies beyond platform system APIs.
OpenMausBot is an open-source, local-first chat application for managing a team of AI bots as separate contacts. Each bot can have its own personality, model, conversation thread, computer, and connected applications, using agents launched through locally installed Claude, Codex, or Grok command-line tools and existing user logins. A local harness server on 127.0.0.1 manages agent processes, transcripts, keys, and events in the user's local OpenMausBot data directory. Bots can work through a cloud Linux desktop, an isolated local virtual machine, or—where supported—the host computer. Shell commands, file edits, and questions are routed through a permission broker and shown as approval or response cards. The application includes model selection, bot and conversation management, browser-accessible desktop takeover, and connected applications through Composio, including services such as Gmail, Slack, GitHub, Notion, and Linear. The repository provides desktop distributions for macOS, Windows, and Ubuntu, with Ubuntu Wayland host control disabled according to the README while a stated issue is resolved.
RuView is an open-source Wi-Fi sensing platform from ruvnet that uses Channel State Information (CSI) captured by low-cost ESP32 sensors to turn disturbances in radio waves into spatial data. It detects presence and occupancy through walls, estimates breathing and heart rate without contact, recognizes activities such as walking, sitting, gestures, and falls, and uses RF fingerprinting to identify rooms and environmental changes. The platform also supports camera-free pose estimation, CSI recording and model training, and loading RVF and LoRA profiles. RuView can publish sensing data to Home Assistant through MQTT and integrate with Apple Home, Google Home, Amazon Alexa, and SmartThings through supported bridges and Matter. Its repository also documents local automation, room-level semantic states, and the RuView MetaHarness, an AI-assisted workflow for onboarding, calibration, training, verification, and checking sensing claims.
Harper is an offline, privacy-first English grammar checker developed by Automattic and written in Rust. It analyzes drafts locally, with a low memory footprint, and can be loaded through WebAssembly. The project provides integrations for Visual Studio Code, Neovim, Helix, Emacs, Zed, Obsidian, Chrome, and other browsers, along with a language server and a JavaScript package. English is currently supported, while the core is designed to be extensible to other languages.
Jellyfin is a free software media system for managing and streaming a user's own media from a dedicated, self-hosted server to end-user devices through multiple apps. It is an alternative to proprietary media servers such as Emby and Plex. This repository contains Jellyfin's backend server and API; the server hosts the web client, uses FFmpeg for media processing, and is built on the .NET platform for cross-platform support. Jellyfin is distributed without premium licenses or features.
Axolotl is a free, open-source framework for post-training and fine-tuning large language models. It uses YAML configuration to define workflows for preprocessing, training, evaluation, quantization, inference, preference tuning, reinforcement learning, and reward modeling. The project is hosted by axolotl-ai-cloud and documents support for distributed training, mixture-of-experts models, multimodal models, and multiple fine-tuning methods.
PenEcho is an open-source shared canvas for handwriting, equations, diagrams, and spatial context. It reads marks and their spatial relationships on a 20,000 × 20,000 canvas, then places hints, explanations, formulas, plots, diagrams, and other AI-generated drafts beside the original content. Drafts can be moved, resized, copied, accepted, or discarded before becoming part of the canvas ink; users can draw with a stylus or mouse, lasso confirmed ink to move, resize, recolor, or delete it, and send selected content to Typeset without triggering an AI request when editing ordinary ink. The application supports editable sandboxed HTML widgets, professional diagrams, animations, and live-data plugins, which can be refined in place through incremental unified-diff edits rather than full regeneration. It supports up to ten API or CLI connections, including Kimi, MiniMax, Codex, and Claude Code configurations, with a selectable active connection per client. Canvases can be organized into projects, shared across authorized devices, and exported as cropped PNG files. PenEcho provides a desktop app and an npm installation requiring Node.js 20.3 or newer. It can run offline with a user's own API or authenticated CLI setup; API credentials remain on the host device and are not sent to browser code. PenEcho Cloud is an optional companion service for private versioned projects, synchronized favorites, linked-device remote access through a relay, and public sharing of Canvases and Widgets as Echoes or Crafts. The project is supported through Moonshot AI's Kimi Open Source Friends program.
Amicro (@subhanhq/amicro) is an open-source React library of micro-interactions, transition components, Motion-powered primitives, custom hooks, spring presets, and animated card layouts. Its components are copied as TSX source into a project rather than delivered as a runtime service, with support for React, Next.js, and Vite applications using Tailwind CSS and Motion or framer-motion. The library includes entrance transitions such as fade-in, fade-up, and zoom-in; interaction components such as tilt-card and magnetic-button; text-reveal effects; scroll-progress utilities; and card layouts including fanned arcs, corner fans, cascades, radial wheels, scatter spreads, interactive 3D carousels, CoverFlow, and a timeline-controlled perspective stack. The npm CLI initializes project configuration and adds individual components, hooks, or utilities. Components can also be installed through a shadcn/ui registry using direct raw URLs or the @amicro namespace. The project supports light and dark UI palettes, requires Node.js 18 or later, and is distributed under the MIT License. It was created by Syed Subhan, associated with Subhan-code.
CapRover is an open-source, self-hosted platform as a service and web-server manager for deploying applications, databases, and websites on a user's own server. It provides a web GUI and CLI for managing deployments and supports applications built with Node.js, Python, PHP, ASP.NET, Ruby, and Go, along with databases and services such as MariaDB, MySQL, MongoDB, PostgreSQL, and WordPress. Under the interface, CapRover uses Docker and Docker Swarm for containerization and clustering, Nginx for customizable load balancing, and Let's Encrypt for SSL certificate management. It is designed to handle deployment and server-management tasks without requiring direct Docker or Nginx configuration, and the project states that applications continue working if CapRover is removed.
Interior Dev is an open-source collection of copy-paste React micro-interactions for the brief period after a click. Each component is distributed as a single file rather than a package and exports a headless `useX` hook containing the behavior without class names alongside an `X` styled example component. The components address layout-preserving transitions, animation restarts, resizing labels, loading jumps, interrupted drags and gesture recovery when focus is lost, keyboard interaction, and `prefers-reduced-motion` behavior; reduced-motion mode preserves the information while skipping the animation. The only dependency is `motion`, and the documentation site can be run with Bun.
Rakazo is an open-source platform for running persistent AI teammates. Each bot has conversations, memory, routines, and history, and can access a browser, terminal, files, and a graphical desktop. Users can access bots through the web app, Electron desktop app, or Expo mobile app, and can take control of the graphical desktop when needed. The platform supports shared team computers and isolated private computers, bot delegation to peer bots or short-lived subagents, voice interaction, and user-provided model credentials through Pi. It can use Docker, E2B, Daytona, Box, or trusted local computers as computer providers, and supports integrations through Composio, Pipedream Connect, MCP, OpenAPI, and Treg sources. Rakazo can be self-hosted with Docker and is also available as a managed application. The repository describes it as being in beta and identifies a TypeScript stack using React, Vite, Tailwind CSS, Electron, Expo, Hono, oRPC, PostgreSQL, Prisma, Better Auth, and Graphile Worker.
pgbot is a read-only PostgreSQL observability and health-diagnosis tool for AI agents, applications, and operators. A static binary connects to PostgreSQL, reads the database's own statistics views, and produces deterministic, findings-first health reports, including a health score, critical/warning/note findings, verified healthy subsystems, and change information from local baselines. It provides focused commands for indexes, queries, tables, and vacuum, along with versioned JSON output for agents and scripts and an MCP mode. Its optional ask and explain commands add an AI interpretation of the same findings; inspection and database queries otherwise require no model key or external service. The project is in beta and uses a read-only pg_monitor role with session-level read-only, statement, and lock timeouts as additional safeguards.
ZSvirt is an open-source virtualization and IaaS platform backed by ZStack. Its management plane coordinates KVM-based hosts, clusters, virtual machines, images, networks, storage, volumes, snapshots, permissions, events, alarms, auditing, and lifecycle operations. Environments can be managed through a web interface, RESTful API, Terraform and Go/Python/Java SDKs, or a CLI. The platform uses asynchronous, stateless services, plugin-based extensibility, a workflow engine with rollback and recovery, resource tagging and queries, and automated deployment tooling. It also includes VMware migration features such as online migration, OVF import, and VMDK upload, and can be run from a qcow2 or OVA management-node image on VMware, VirtualBox, KVM, or a cloud host.
ManimGL is an open-source Python animation engine for creating precise programmatic animations, particularly explanatory mathematics videos. Scenes can contain shapes, equations, and transformations and can be rendered to video or displayed in an OpenGL window. This repository is the original Manim project created by the author of 3Blue1Brown; it is distinct from the later Manim Community Edition. The package is installed as `manimgl`, runs on Python 3.10 or higher, and uses FFmpeg and OpenGL, with LaTeX optional for LaTeX rendering.
openGym is a free, open-source gym and body-weight tracker with an Android app and Docker-based self-hosting. It provides guided workouts with previous weights, timed rest periods, personal-record notifications, weekly routines, supersets, cardio, timed sets, warm-up sets, and progression rules including linear progression, Greyskull LP, double progression, and added time. The tracker records workout history, body weight, RIR or RPE effort ratings, estimated one-rep maxes, and progress through charts, muscle-balance, fatigue, strength, and training-heatmap views. It can import histories from FitNotes, Strong, Hevy, and Apple Health exports, and export routines as files or PDFs. The project states that it requires no account, cloud service, or telemetry; its code, releases, container images, and APK builds are distributed under the AGPL-3.0 license.
Dockhand is a Docker management web application by Finsys for managing containers, Compose stacks, and multiple local or remote Docker hosts. It provides real-time container status and resource monitoring, visual Compose editing, Git-based deployment with webhooks and auto-sync, interactive shell access, log streaming, file and volume browsing, image and network management, vulnerability scanning with Grype and Trivy, schedules for pruning and updates, notifications, and activity auditing. Environments can connect through a socket, agent, or direct TCP. The application uses direct Docker API calls, a SvelteKit frontend, a Bun-based backend, and SQLite or PostgreSQL through Drizzle ORM. It is licensed under the Business Source License 1.1, with the repository stating that it converts to Apache 2.0 on January 1, 2029; personal use, internal business use, non-profits, education, and evaluation are permitted, while offering it as a commercial hosted service is not.
A browser-based first-person shooter built with Three.js r180 and WebGL2. It uses procedurally generated textures, meshes, animations, and Web Audio synthesis rather than external art or sound files; its systems include a market-street world with enterable interiors, custom physics and character movement, procedural weapons and ballistics, GPU visual effects, navmesh-based enemy AI with perception and cover behavior, and a DOM/CSS HUD. The repository also provides a development and testing harness: headless-Chromium screenshot capture, isolated reproducible shotsets with pixel-diff gating, scripted playtesting, and a gameplay profiler that reports frame-time distributions and attributes hitches to per-frame WebGL program compilation. The project is run with npm and has Three.js as its only runtime dependency.
scriptc is an experimental TypeScript-to-native compiler from Vercel Labs. It uses the TypeScript compiler for parsing and type checking, then emits typed IR, readable C, textual LLVM IR, native assembly and object files, native executables, or WebAssembly modules. Static builds include a small native runtime and do not require Node.js or a JavaScript engine when run; code that cannot compile statically is reported through diagnostics, and coverage reporting identifies the statically compilable portions and blockers. For npm packages and other dynamically typed code, an optional dynamic mode embeds quickjs-ng. The compiler itself requires Node.js 24 or newer and targets macOS, Linux, Windows, and WebAssembly through WASI Preview 1.
Colibrì is a pure-C inference engine and open research platform for running large mixture-of-experts models on consumer and heterogeneous hardware without engine dependencies. It treats VRAM, system RAM, and storage as a unified multitier inference hierarchy, streaming expert weights from disk and coordinating placement, storage I/O, scheduling, kernels, speculation, and CPU/GPU overlap. The project provides chat, server, and web front ends, with support for CPU, CUDA, Metal, and dual-SSD streaming; its design rules prohibit silently changing model precision or router semantics when fast memory is insufficient.
img2threejs is an agent skill that reconstructs an object or character from a reference image as a code-only, procedural Three.js model. It generates a TypeScript THREE.Group factory using primitives, procedural shaders, and generated geometry rather than photogrammetry, mesh extraction, or downloaded art assets. The generated scene includes runtime structures such as pivots, sockets, and colliders for animation, and the project documents separate hard-surface and anatomy-aware reconstruction paths. It runs under Claude Code, Codex, or OpenCode and provides live browser demos whose models can be inspected as generated source.
TurboFieldfare is a model-specific Swift and Metal runtime for running the instruction-tuned Gemma 4 26B-A4B model on Apple Silicon Macs, including systems with 8 GB of RAM. It keeps the model’s shared 1.35 GB core and FP16 key-value cache in memory while streaming the expert weights selected for each token from an SSD, allowing inference with about 2 GB of resident weights instead of loading the approximately 14.3 GB model. The model uses MLX affine 4-bit weights with group size 64, an 8-bit router, 4-bit shared and routed experts, and about 3.88 billion active parameters per token. The project includes a native macOS app, command-line interface, Swift runtime library with Metal kernels, decode service, streaming model installer and verifier, and experimental loopback OpenAI-compatible Chat Completions server. These products share a repacked `.gturbo` model directory; the installer streams byte ranges from a pinned Hugging Face revision, repacks them without materializing the source checkpoint, and validates the resulting manifest and file hashes. The app and CLI support instruction and completion generation with optional system guidance but do not execute tools; the server accepts function-tool declarations and returns model-produced tool calls for client authorization and execution. An optional companion vision tower adds image input on M2 or newer Macs, while text-only inference remains available on M1. The package is arm64-only and targets macOS 26, Metal 4, and Swift 6.2 or newer, with approximately 14.3 GB of storage for the text model plus about 1.1 GB for the image pack.
Personal Model is an open-source, local-first AI memory runtime from Intuition Lab for giving coding agents evidence-linked context about a user. After macOS permissions are granted, it captures focused activity from applications on the user's Mac and builds a portable HUMAN.md-style personal context model, storing the data locally and allowing it to be inspected, corrected, exported, or deleted. The runtime progressively organizes sourced observations and events into relationships and changes, supported patterns, higher-order structures, and an integrated current model. It retains source receipts for important claims so later evidence can strengthen, revise, or overturn inferences, then exposes this context through MCP to trusted clients including Claude Code, Codex, Cursor Agent, Claude Desktop, and other compatible tools.
Finger Frame AI is a browser app and Python CLI pipeline by Sophia Yang that places an AI-generated world inside a two-hand finger-frame gesture. It sends an uploaded video to Gemini Omni Flash for video-to-video restyling using a selected style or custom prompt, with alignment instructions intended to preserve framing, facial positions, expressions, blinks, gaze, and motion. MediaPipe Hand Landmarker then tracks both hands and the finger-frame quadrilateral frame by frame; the tracking pipeline uses anatomical corner ordering, spread and area gates with hysteresis, teleport rejection, velocity-adaptive smoothing, dropout holding, and presence fading. The compositor reveals the restyled video through the tracked quadrilateral and adds a dashed outline with pulsing corner markers. The browser app exports MP4 where browser recording supports it and otherwise WebM. The CLI separates restyling and compositing into `stylize.py` and `composite.py`, accepts formats readable by FFmpeg or OpenCV, and can produce H.264 MP4 while retaining the original audio track when present. Users provide their own Gemini API key; the app keeps it in the browser and sends it only to Google's API. Generation is billed per video, and the app recommends keeping uploads under about 15 MB. A no-key placeholder mode runs the tracking, compositing, and export pipeline with a hue-shifted stand-in.
Virtual Mac on iPad is a community project that runs macOS in a hardware-virtualized virtual machine on compatible Apple-silicon iPads. Its tooling extracts and rebuilds the virtualization frameworks required from macOS's shared cache, allowing macOS applications such as Xcode, Terminal, Final Cut Pro, Logic Pro, and Pixelmator Pro to run on the device. The project requires a jailbroken iPad Pro with an M1 or M2 chip or an M1 iPad Air running iPadOS 14 through 16.3.1. It is distributed as a package through the project's Cydia repository and installed with Sileo; the project states that it is unaffiliated with Apple, Dopamine, UTM, and VirtualBuddy.
Temporal is a durable execution platform developed by Temporal Technologies for building scalable applications and workflows. Its server executes application logic as Workflows, automatically handling intermittent failures and retrying failed operations so applications do not need to implement all timeout, retry, and recovery logic themselves. Developers implement Workflows, Activities, and Workers with SDKs for multiple programming languages, then use the Temporal server, CLI, and Web UI to run and inspect them. The open-source Temporal server originated as a fork of Uber's Cadence and is distributed under the MIT License.
Pascal Editor is an open-source, web-based 3D building editor for creating and sharing architectural projects. It supports architectural elements and objects such as walls, slabs, roofs, zones, doors, windows, and furniture, along with plugins and publishable viewers. The editor is built with React Three Fiber and WebGPU. Its Turborepo monorepo separates scene schemas and state, 3D rendering, editing tools, built-in node definitions, viewer and capture runtimes, shared UI, a standalone Next.js app, and an MCP server that exposes scene tools, resources, prompts, and local storage to MCP-compatible AI hosts. The project can run locally through the @pascal-app/cli package, which starts a persistent editor and authenticated MCP service, stores projects in a local database, and manages the standalone runtime. Reusable editor, viewer, node, core, and capture packages are also distributed through npm.
AGENTS.md is an open format for guiding AI coding agents through project-specific context and instructions. It provides a dedicated, predictable file—similar to a README for agents—where projects can document development-environment commands, testing and linting procedures, package or project conventions, and pull-request requirements. The format is documented by the agentsmd project, which also maintains a basic Next.js website with examples.
Hostinger is a web hosting provider operated by Hostinger International Ltd that offers shared hosting, VPS and cloud hosting, domain registration, and website builder tools. It markets services globally through localized sites and partner/affiliate links.
AlphaFold is an open-source implementation of the AlphaFold v2 protein-structure prediction inference pipeline, developed by Google DeepMind. The repository also includes an implementation of AlphaFold-Multimer for predicting protein complexes and documents the updated AlphaFold v2.3.0 models and inference procedure. It runs on Linux using Docker and a modern NVIDIA GPU, with model parameters and genetic databases supplied separately; the full database setup requires substantial storage.
An Apache-2.0-licensed open-source Go SDK from Grafana for building AI-powered backends and agents. It provides GenerateText and StreamText APIs for calling language models, returning complete or streamed responses, executing Go functions as tools, generating schema-validated structured output, and running multi-step tool workflows, with approval for consequential tool actions. The SDK supports Anthropic, Amazon Bedrock, OpenAI, OpenAI-compatible APIs, and Grafana's hosted endpoint, along with retries, configurable timeouts, fallbacks, logging, Prometheus metrics, and Agent Observability. It follows the design of Vercel's AI SDK and is wire-compatible with its TypeScript React frontend hooks, including useChat, useCompletion, and useObject, allowing Go backends to stream Server-Sent Events directly to an existing React frontend without a protocol adapter.
Open Archiver is a self-hosted, open-source platform for archiving, storing, indexing, and searching email from Google Workspace, Microsoft 365, IMAP inboxes, PST files, zipped EML files, and Mbox files. It supports bulk imports and ongoing synchronization, and provides full-text search across messages and attachments with filters and thread discovery. Messages are stored as standard EML files with deduplication, compression, and encryption at rest. Storage can use a local filesystem or an S3-compatible object store. The system records file hashes during ingestion and provides integrity reports, retention policies, and an immutable audit trail for access and activity tracking. The platform is deployed with Docker Compose and uses SvelteKit, Node.js with Express and TypeScript, BullMQ with Redis or Valkey for asynchronous jobs, Meilisearch for indexing, and PostgreSQL for metadata, users, and audit logs.
SendGrid is an email API and email marketing campaigns platform from Twilio. It sends transactional messages such as waiver copies and organizer alert emails.
Zeron is a local control layer for coding agents, including Claude Code, Codex, Cursor, Grok, Hermes, and Pi. Each device runs a small engine that stores agent sessions locally by default, without requiring an account or network connection. Optional synchronization lets users start an agent on one device and follow or control it from another; an always-on machine such as a VPS can keep agents running after a laptop is closed. The Linux installer starts a daemon that persists across reboots, while macOS users can install the desktop release or build from source. Zeron is licensed under the MIT License. The videos refer to the project as Comet.
blobatar is a dependency-free JavaScript library for generating deterministic geometric SVG avatars from strings such as usernames, display names, emails, handles, IDs, or repository names. The same input string always produces the same blobatar, which can represent a user, bot, team, or other named entity. It provides a core JavaScript interface and framework adapters for React, Vue, Svelte, Solid, Preact, React Native, and Expo. Outputs can be used as SVG markup or data URIs, with controls for visual traits, palettes, expressions, and optional animation. The package is distributed through npm-compatible package managers and is reported by its repository to be approximately 4.4 KB gzipped.
icm-architect is a Claude skill that designs processes, ideas, and problems as ICM (Interpretable Context Methodology) workspaces, using folder structure as agent architecture, or restructures an existing folder, repository, or vault. Numbered folders encode sequencing, hierarchy scopes context, and plain Markdown files store state, allowing an agent to orient and act by reading the relevant files. In build mode, it extracts stages, human approval points, and stable versus per-run elements, then scaffolds a workspace using one of six forms: Pipeline, Umbrella, Record library, Knowledge bundle, Context map, or System map. In restructure mode, it audits files as catalog, contract, factory, product, or dead, proposes a migration map for approval, then migrates and validates the result. The walk test checks whether an agent with no prior memory can orient, act, and report status from the workspace alone. It can be installed as a Claude Code skill or uploaded to Claude applications, and is MIT licensed.
barehands is an open-source, webcam-powered hand-tracked interface for AI assistants. It runs in Chrome with a webcam and overlays notes, images, and 3D models as cards over the camera feed; users manipulate them with gestures such as pinching, throwing, stretching, force-pulling, and two-finger dragging. The interface uses a local Python server and loads Google MediaPipe for hand tracking and three.js for 3D rendering. Markdown folders, including Obsidian vaults, can serve as note sources, while configured media folders provide images, transparent props, and 3D models. An AI assistant can control the interface through local files and shell scripts: state files drive the on-screen ring's status, and the board protocol presents content on the stage. The repository states that it can be used, modified, and built on commercially within a business, with redistributed versions remaining under the same license.
Aura is an open-source web gallery and customizer for ambient, layered gradient backgrounds built with CSS blend modes. It provides live previews and a fullscreen viewer, then lets users add, remove, and reorder layers while adjusting blend modes, blur, opacity, base color, and an optional grain overlay. Gradients can be exported as CSS, Tailwind, CSS variables, or CSS-in-JS, and downloaded as PNG or SVG images; the tool also generates prompts for recreating a gradient with ChatGPT, Claude, or Copilot. The repository is MIT-licensed and provides a local development workflow using pnpm.
unlazy is an agent skill for enforcing completion discipline in substantial AI-agent tasks. It requires an acceptance ledger to be written first, with runnable CHECK commands and EXPECT conditions; its gate checker reviews commands, executes approved gates, records evidence, and can reverify completed work. The skill also supports a Depth Tree method that splits tasks into fresh-context subtasks with integration checks, giving each leaf the full task time budget. It can be installed for supported agents with the skills CLI or manually for Claude Code and Codex CLI; its checker and optional hook require Node.js 16 or newer and no third-party runtime packages.
Endoplexity is a Chrome MV3 side panel and local bridge for agentic control of the browser a person is already using. It lets Claude or Cursor agent CLIs operate existing tabs and logged-in sessions by clicking, typing, filling forms, navigating, switching tabs, uploading files, and reading pages, without sending requests directly to a model or requiring a separate metered API key. The side panel owns the Chrome DevTools Protocol connection and communicates over an origin-pinned WebSocket with a bridge on localhost; the bridge exposes browser tools over token-gated MCP/HTTP and enforces the safety policy, including approval gates and autonomy modes. Pages are provided to the agent as accessibility-tree snapshots rather than raw HTML, and actions return the resulting page state so subsequent turns can resend only changed lines. Its file-reading tool extracts text from PDFs, DOCX, XLSX, PPTX, CSV, JSON, Markdown, and other text files.
NorthCinder is an open-source, local-first MCP server for AI shopping agents. It compares products from user-selected sources against a buyer's criteria, explains rankings and exclusions, shows source facts and unverified details, and normally returns up to three useful options rather than claiming one universal best product. Its research workflow provides separate product and seller guides, creates a research plan, and uses controlled research tools; results remain provisional when sources conflict or do not identify the exact item or seller. Purchasing is a separate human-in-the-loop decision: each checkout requires fresh approval for one exact offer and unit, with the merchant, variant, price, known total, and spending cap signed into a single-use approval. It rejects raw card details, using an opaque payment token for supported automated checkout or handing the buyer a cart link. NorthCinder runs alongside an MCP-capable AI application. Its local setup requires Node.js 20 or later; the init command stores configuration locally and starts the MCP server and search engine in one process. The repository states that there is no hosted NorthCinder account or cloud service, and that order outcomes remain local.
TrueForge is an open-source, vendor-neutral agent harness developed by TrueFoundry. It runs the agent execution loop, including model calls, MCP tool use, skills, sandboxed code and file execution, approvals, context management, and session state. Agents can use configured model providers, remote MCP servers, git-backed SKILL.md instruction packs, and on-demand sandboxes; context features include subagents, deferred tool loading, Code Mode, large-result offloading, and compaction. TrueForge exposes agents through a bundled chat UI, an HTTP API with a TypeScript SDK, and an embeddable UI SDK. It supports local mode with SQLite and hosted deployments using Postgres and Redis through Docker Compose or Helm; the repository warns that local mode is intended for personal use on localhost rather than production or internet-facing deployment.
sloptrim is a local prose linter and coding-agent plugin that detects patterns associated with AI-generated writing when an agent saves a document. It extracts prose from supported text and office formats, scores it on a 0–100 scale, and reports suspicious spans for revision; it analyzes writing patterns rather than determining authorship and does not process code. The command-line tool uses Python's standard library, requires no model or network connection, and keeps text on the local machine. It integrates with Claude Code and can be initialized for other agents through an agent contract and editor-rule files.
APEX is an open, verification-first RTL design for an LLM-inference tile developed with Sigmantic AI. It implements one transformer decoder layer—including attention, softmax, RMSNorm, RoPE, SwiGLU, residual processing, and KV-cache compression—and runs Qwen2.5-0.5B through the verified pipeline on FPGA hardware. The KV-cache codec sits in the datapath: cached keys and values are compressed as they are produced and decompressed when consumed, while an importance unit allocates precision according to which parts of the context matter. Each RTL block is checked against an executable NumPy golden model with bit-exact comparisons and mutation-tested testbenches. The repository covers the inference tile rather than a complete system; DRAM control, PCIe, and NoC are out of scope.