2,421 tools and products — trending open source, and what gets used in AI and other work.
An open GitHub guide and configuration project by jamesob for running state-of-the-art large language models locally. It documents a multi-GPU system using PCIe switches so GPUs can communicate peer-to-peer, including hardware selection, BIOS bifurcation, link-speed and ASPM settings, kernel and GRUB parameters, ACS configuration, and GPU power limiting. The repository also provides Docker-based serving configurations, a local speech-to-text configuration, and a GPU peer-to-peer bandwidth and latency benchmark.
Jacobian Lens (jlens) is a research and interpretability tool from Anthropic for examining what an internal language-model activation is disposed to make the model say. It linearly transports a residual-stream vector from any layer and position into the final-layer basis using an average input–output Jacobian computed over a text corpus, then applies the model’s own unembedding to produce ranked vocabulary tokens. The reference implementation fits lenses on open-weight decoder transformers, applies pretrained or newly fitted lenses, and renders an interactive layer-by-position view with top-token ranks, pinned-token tracking charts, and rank heatmaps. It is distributed as an Apache-2.0-licensed Python package and repository; the code is described as not maintained, and model weights and text corpora are not bundled.
An open-source native ARM64 port of Command & Conquer: Generals — Zero Hour for Apple Silicon Macs, iPhone, and iPad. It runs the real 2003 engine rather than an emulator, supporting campaign, skirmish, and Generals Challenge modes with RTS touch controls including tap selection, drag-box selection, long-press deselection, two-finger scrolling, and pinch zoom. The rendering path translates DirectX 8 through DXVK to Vulkan and then through MoltenVK to Metal. The port also reroutes the engine's writable configuration, cache, and save paths for iOS's code-signed app environment, adds an iOS DXVK cross-build and Vulkan-loader patch, and handles app-resume behavior when iOS removes the Metal drawable. It is based on EA's GPL v3 source release and community work including GeneralsX, with additional engine fixes and iOS/iPadOS support. The repository does not include or distribute game assets; users need their own copy of the game. The project is hosted on GitHub.
img2obj is a Codex plugin that reconstructs an object from an attached image, screenshot, or local image path as a code-only, procedural Three.js model. It first validates the reference, then plans an ObjectSculptSpec covering the component hierarchy, geometry, materials, pivots, sockets, motion requirements, and visual priorities. The model is built through blockout, form, look-development, and interaction phases; browser renders are compared with the source image, with quality evidence and approval required before advancing. The plugin generates procedural Three.js geometry rather than extracting or downloading a mesh. It supports hard-surface and organic assets, vegetation, fabric, glass, hair or fur, emissive elements, and decals; can define animation-ready parent-child relationships, detachable parts, pivots, and sockets; and can produce reference-derived PBR evidence such as palette, roughness, height, normal, and ambient-occlusion maps. It is intended for stylized props, mechanical objects, plants, scene assets, and interactive models, not photogrammetry, exact mesh extraction, or guaranteed production-ready geometry from a single image. The repository requires Codex with local plugin support, Python 3.10 or newer, and a browser project using Three.js.
thinking-orbs is a React component package providing dotted animated loading indicators for AI and agent interfaces. It offers nine hand-tuned states— including working, searching, solving, listening, connecting, weaving, composing, breathing, and shaping—rendered with plain 2D canvas rather than WebGL or filters. The indicators have separate 64-pixel chat-avatar and 20-pixel inline-text designs, automatic or pinned light/dark themes, adjustable speed, pause control, and pass-through canvas properties. It includes per-state accessible labels, renders a static frame for prefers-reduced-motion, pauses offscreen instances through IntersectionObserver or when the tab is hidden, and resumes them in phase using a shared clock. The package is distributed through npm under the MIT license.
GC Minimal Zine Poster is a Codex skill for turning a theme, sentence, article idea, object, mood, photograph, or reference set into a sparse editorial poster, production-ready image prompt, or reusable visual system. It compiles requests into a vertical aged-paper composition with 70–90% negative space, one small visual subject or event, restrained typography, a high-chroma color accent, and xerox, risograph, halftone, letterpress, or scanned-paper textures. The skill supports Generate, Reference Analysis, Prompt-only, Analyze + Generate, and Photo Input routes; its reference-analysis and quality-review workflows require image inspection, while image generation depends on the host runtime's available model. It is distributed as a Git repository for use with Codex or another compatible Skill runtime and contains no scripts, external fonts, API keys, private paths, or downloaded runtime assets.
AVAL is an open-source web format and runtime for short prerendered motion with continuous loops, named application states, authored triggers, bounded transitions, reversals, frame-accurate timing, and packed-alpha transparency. It packages a logical animation as codec-specific .avl files containing motion units and a state graph; the browser selects a decodable candidate from an AV1, VP9, H.265/HEVC, and H.264 ladder, while graph routes handle state changes rather than timestamp seeking. Projects are compiled from a motion.json file with the @pixel-point/aval-compiler package, producing a directory containing the .avl output and build metadata. AVAL requires the integrating application to handle unsupported browsers and fatal playback errors and does not itself create or reveal fallback video, image, text, or other content.
QuerySplat is an open-source implementation for predicting and rendering 3D Gaussian splats from multiple images of a scene while decoupling geometry and appearance representations. Its inference pipeline preprocesses custom images, predicts 3D Gaussians, and uses VGGT-Omega components for camera and depth prediction; optional test-time optimization can refine the result. It can export Gaussian PLY files, predicted input cameras, per-view depth and confidence data, and depth-derived point clouds. The repository requires Linux, an NVIDIA CUDA-capable GPU, and CUDA-enabled PyTorch.
cargo-frisk is a Rust command-line tool that checks the files a Cargo package will ship. It builds the .crate archive, compares its contents with `git ls-files`, and reports files that are shipped but not tracked, files tracked but not shipped, and the expected shipped-and-tracked files. Cargo-generated files such as `Cargo.toml.orig`, `.cargo_vcs_info.json`, and `Cargo.lock` are listed separately. It scans packaged files for provider tokens, private keys, `.env` files, credentials files, editor backups, and other patterns adapted from gitleaks, with additional rules for Cargo packaging. Findings can be adjusted using severity thresholds, entropy checks, path-based severity reductions, inline suppressions, ignored paths, ignored rules, and per-file size limits. Binary or oversized files are reported as not scanned rather than silently skipped. The tool is installed with `cargo install cargo-frisk` or `cargo binstall cargo-frisk`, then run with `cargo frisk` from a package. Its exit codes distinguish no findings, findings at or above the configured threshold, and tool errors such as a failed `cargo package` operation or malformed archive.
findphone is a macOS command-line tool for locating a nearby Bluetooth device by tracking signal strength when Find My is unavailable. It provides a survey mode for nearby Apple handhelds, a hunt mode for following a named device, and a listing mode for paired devices. An optional sound mode emits clicks that become more frequent as the smoothed signal strengthens, allowing a user to search by ear. The tool reads measurements from a connected BLE GATT link, passively observed BLE advertisements, or macOS Bluetooth data for paired devices, and reports signal strength in dBm as a coarse distance indicator. It is distributed as an unsigned universal arm64/x86_64 binary or can be built from Swift, requires macOS 13 or later, and has no dependencies.
Shitty is a terminal emulator for macOS and Linux/Wayland, built for low latency, fast startup, and predictable resource use. It keeps terminal state on the CPU and renders changed cells with native compute backends: Metal on macOS and Vulkan on Linux. It supports VT52 through VT5xx and ECMA-48 controls, ISO-2022 character sets, common xterm extensions, primary and alternate screens, scrollback reflow, hyperlinks, shell marks, mouse and keyboard input, resizing, HiDPI and fractional Wayland scaling, and Unicode 17 grapheme clusters including emoji sequences and wide CJK characters. Resize frames are rendered in the same transaction as bounds changes, and updates are damage-driven. The project provides native macOS and Linux/Wayland frontends as a small self-contained binary with embedded fonts. Its README describes more than 5,000 black-box tests driven through a real PTY, a fuzzed parser state machine, and a default security model that prevents applications from reading selections or controlling the host window unless explicitly permitted. The same terminal code is also distributed under the user-facing name Pretty.
da-cli is a zero-dependency Python command-line tool for syncing DeviantArt galleries to local folders as a backup of watched artwork. It uses the DeviantArt API with OAuth 2.1 PKCE, stores a local SQLite index so repeat runs can avoid downloading unchanged content, and provides commands for syncing feeds, individual artists, or watched users, along with search and browsing helpers for tags, topics, users, deviations, and daily deviations. The distribution package is named da-sync and installs the da command. It supports unattended scheduling through launchd on macOS or a systemd timer on Linux; macOS secrets are stored in the Keychain, while Linux Secret Service support is planned. The project describes its sync and search flows as beta, with 868 tests reported in the README.
Jungle Trail is a first-person procedural jungle walkthrough built with Three.js, taking the player along a winding trail toward overgrown stone ruins and a waterfall. It uses no external art assets: textures, meshes, materials, character elements, and sound are generated in code, including GLSL-based procedural textures and normal maps. The scene is assembled from procedural terrain, plants, stone blocks, and a character, with synthesized audio generated at load time. The project is a plain ES-module web application with no build step and can be run through a static file server. It provides desktop mouse-and-keyboard controls, touch controls, and debug and teleport options; the README states that it is intended for a desktop GPU and has no reduced-quality mobile version.
Desko is an open-source desk dashboard that turns a spare phone into an always-on display. A lightweight Python process on a PC collects data and pushes it over WebSocket to a browser tab on a phone on the same Wi-Fi network, with no phone app, account, cloud service, or build tooling required. The dashboard cycles through five scenes: an idle view with clocks, weather, battery, latency, and PC uptime; a music view with album art, synchronized karaoke lyrics, and PC playback controls; a statistics view with CPU and GPU load and temperatures, memory, network activity, sparklines, and an optional running game; a development view with workspace, Git branch status, changed files, cursor position, commits, and lines, sourced from VS Code or Git; and a focus view with a server-side Pomodoro timer. Scenes can be manually selected or pinned, and widgets hide when their underlying data sources are unavailable.
doc7 is an open-source document-to-Markdown tool that converts PDFs, Office files, scans, screenshots, charts, formulas, and diagrams into AI-ready Markdown using an OpenAI-compatible multimodal vision model. It renders and understands complete pages rather than relying on character extraction, preserving text, tables, formulas, chart and diagram relationships, image meaning, and visible UI state; the video also describes page-level retry and resume. The model can run locally through LM Studio or Ollama or through a remote endpoint, with no required OCR stack or document-processing service. The same binary provides an interactive CLI, batch processing, model checks, MCP support, a Go SDK, and an asynchronous HTTP service, with installers for macOS, Linux, and Windows.
King's Gambit is a browser-based 3D chess game in which sculpted, rigged character pieces from the Ivory Kingdom, Sun Empire, or Grande Armée march, attack, and dissolve during cinematic captures. It supports standard chess rules—including castling, en passant, promotion, checkmate, stalemate, repetition, the fifty-move rule, and insufficient-material draws—through chess.js, while a Web Worker search engine provides the computer opponent. The game is built with Vite, React, TypeScript, and three.js; it is a static site with no backend or account requirement.
Outreachr is a free, open-source, local-first fundraising CRM for founders. It provides a private desktop workspace backed by a founder-owned SQLite database rather than an Outreachr-hosted account or subscription, covering investor research, target ranking, introductions, outreach, meetings, diligence, and committed capital. The application searches bundled investor research, ranks targets against factors such as stage, sector, geography, and published check evidence, and shows the supporting records and sources behind each score. Founders can move firms through research, introductions, meetings, diligence, soft-circle, commitment, pass, and not-now stages; draft, review, approve, and send one-to-one initial messages through Gmail or Outlook; and reconcile selected relationship metadata from existing mailboxes. Its outreach controls include duplicate-send prevention, sending caps, domain cooldowns, suppression lists, and founder approval before messages reach a mail provider. Codex or Claude may propose drafts, research, tasks, and pipeline changes from explicitly permitted local context, but agents cannot send email or bypass approval.
A ComfyUI acceleration extension for the native MiniMax H3 audio-video model. It reduces expensive transformer evaluations during sampling by retaining the packed hidden state after actual transformer steps, then using Chebyshev ridge regression to forecast that state on selected forecast steps. Forecast steps skip the H3 transformer blocks and continue through the native output and sampler path, with adaptive scheduling, sampler-aware safeguards, CPU/VRAM history storage, and native fallbacks. Spectrum is a training-free approximate accelerator: forecasted states alter the denoising trajectory, so outputs can differ from native H3 even with the same seed and workflow.
Token Saver is a local Claude Desktop extension developed at Marktechpost AI Media Inc. It searches PDFs stored on the user's computer using local hybrid retrieval—BM25 and embedding search—then sends Claude only the passages relevant to a question, with exact page citations, instead of placing the entire document in the context window. The extension is distributed as a one-click .mcpb file and bundles its search engine, requiring no Python, terminal, or configuration files; documents remain on the local machine. It also supports document-folder selection, document listing, disambiguation when multiple files match, and reusing a loaded document for follow-up questions.
Falco is a tiny browser engine written from scratch in Rust. It parses HTML, applies CSS, executes JavaScript in a custom virtual machine with a baseline JIT compiler, loads images, computes layout, and paints the result to a canvas that can be exported as PNG or displayed in a live interactive window. Its rendering pipeline runs from HTML through the DOM, style and layout trees, paint commands, and a canvas; the interactive mode supports scrolling, link navigation, form filling, and browsing history. The project includes its own HTML and CSS parsers, layout engine, SVG renderer, image loader, PNG encoder, WebAssembly interpreter, networking layer, and JavaScript DOM bindings, rather than wrapping WebKit, Gecko, or Chromium.
Stickman Video Director is a Codex skill that turns source copy, notes, articles, or a topic into a planned one-minute stickman video workflow. It first produces a six-scene directing proposal covering English narration, reference translation, visual action, camera movement, transitions, background music, sound effects, color treatment, and continuity; only after explicit approval does it generate six standalone Gemini Omni Flash prompts for roughly ten-second segments. Each scene specifies three timing beats and repeats key character, line-weight, palette, audio, dialogue, transition, and negative constraints so the prompts can be used independently, then assembled into a continuous video. It adapts composition and camera paths for 9:16, 16:9, or 1:1 formats and supports white-background/black-stickman or black-background/white-stickman styles with up to three accent colors. Global changes return the workflow to the proposal stage, and the skill is designed to avoid adding unsupported facts or claims. It requires no API or MCP integration and is distributed under the MIT license.
CommerceAgentBench is a benchmark developed and maintained by the Accio team at Alibaba International for evaluating whether AI agents can complete long-horizon business workflows in high-fidelity, stateful, reproducible replicas of online services. Its tasks cover browser operations, native-style command-line tools, file and spreadsheet production, API and MCP workflows, public-web research, supplier analysis, product publishing, logistics, storefront configuration, and other commerce operations. Each task runs in a fresh container and is graded by a deterministic or LLM-assisted verifier. The benchmark uses local mock services representing commerce, SaaS, messaging, document, and operational systems; runs preserve the resolved configuration, agent trajectory, verifier result, artifacts, logs, and container metadata for auditing and reproducibility. The repository describes 107 tasks spanning CLI, browser, file, and API/MCP interfaces, with text-only, browser-text-capable, and vision-required capability slices. The project was previously called RealReplicaBench.
diri is a native desktop orchestrator for coding agents on macOS and Linux. It runs Claude Code, Codex, Cursor, Gemini, and ordinary shells in parallel, using separate Git worktrees or remote hosts over SSH and tmux. Each session is a real terminal with a persistent PTY managed by a background daemon, so closing or reopening the app does not terminate sessions; the daemon restores their output and state. The app displays working, needs-you, and done status, while its MCP server allows one running agent to spawn, monitor, read, and respond to another. Claude Code and Codex have first-class status detection and resume support, while Cursor and Gemini have partial support.
creakwork12 is a Rust utility that reads a Framework 12 laptop's hinge position and movement, turning the hinge into a creaky wooden-door sound. The sound pitch depends on the hinge position, while volume depends on how quickly the hinge is adjusted; its filtering is optimized for the Framework 12's hinge stiffness. It is distributed as an executable in the GitHub releases or can be built with Cargo, requiring the system's IIO and ALSA development libraries. The project was built on Fedora and may have dynamic-linking issues on other Linux distributions.
A Rust library for creating and reading specially crafted .tar.gz archives with embedded chapter-boundary information. A chapter contains zero or more consecutive tar entries; chapter markers are encoded as valid empty gzip blocks with distinctive Huffman code alphabets, allowing readers to skip groups of entries in constant time without decompressing intervening data and to decompress separate chapters concurrently. Archives remain readable by existing tools as ordinary tar.gz files, and archives without chapter metadata are treated as one chapter.
FlightGlitch is a web service that monitors airline pricing around the clock for unusually low airline tickets caused by pricing errors, commonly called mistake fares or error fares, and sends subscribers notifications when they are found.
Breadcromb is the developer of Trace, an AI-powered web browser that builds a private knowledge layer from users' reading and uses local-first AI to answer questions, automate tasks, and orchestrate agents within the browser. Trace is offered as a free download and emphasizes privacy and local-first operation.
LikeC4 is an open-source modeling language and toolset for describing software architecture as code and generating live, browsable diagrams from the model. It is inspired by the C4 Model and Structurizr DSL, while allowing users to define custom notation, element types, and nested architecture levels. The project provides a CLI for previewing diagrams, along with a VS Code extension and other tools for working with the models. LikeC4 is distributed under the MIT License.
Strix is an open-source AI penetration-testing tool from usestrix that uses autonomous, multi-agent AI pentesters to dynamically run applications, perform reconnaissance and exploitation, and validate vulnerabilities with working proof-of-concept exploits rather than static-analysis findings. Its developer-oriented CLI produces remediation guidance, generated patches, and pentest reports, and it can run scans in CI/CD pipelines to detect insecure changes before deployment. The tool runs in a Docker sandbox and requires an LLM API key; the associated Strix platform supports repository and domain testing, continuous scanning, and integrations with development and issue-tracking workflows.
npcpy is a Python library for research and development with multimodal language models, agentic AI, and knowledge graphs. It provides primitives for defining personas, making direct language-model calls, creating tool-using agents and multi-agent teams, and building AI applications with local providers such as Ollama, llama.cpp, omlx, and LM Studio as well as cloud providers. Its NPC Context-Agent-Tool data layer is designed to enforce context and tool-use rules through software rather than prompts. The Agent class includes tools such as shell execution, Python, file editing, and web search, while ToolAgent supports custom tools; the examples include image generation, Hugging Face image-dataset retrieval, and diffusion-model fine-tuning. The library is distributed through PyPI.
An open-source collection of common React job-interview questions with detailed answers and explanations in Spanish. The repository organizes material from beginner to intermediate topics, including JSX, components, props and state, hooks such as useState and useEffect, rendering, hydration, server-side rendering, controlled components, custom hooks, and React design patterns. Its companion site, reactjs.wiki, supports searching, saving, and sharing questions.
USBridge Remote is a unified client for managing remote machines, combining software-based remote desktop control with integration for USBridge KVM hardware. Its client runs on Windows, macOS, Linux, Android, iOS, and the web, while an agent on the target machine handles screen capture, input injection, and Tailscale networking. The system provides live remote desktop, virtual device passthrough, snapshot management, shared clipboard transfers, encrypted peer-to-peer connections, and Moonlight-based low-latency streaming. It is distributed as beta software, is free without session or connection limits, and does not require an account on the target machine; the web client has feature and performance limitations compared with native applications.
PortalJS is an open-source, AI-native framework maintained by Datopian and its community for building data portals. Its agentic skills advise on storage, compute, catalog, access, hosting, and metadata, then scaffold the result as plain, editable Next.js code. Claude Code skills can create a portal, add CSV or JSON datasets, connect to backends such as CKAN, and deploy it; generated portals include a home page, catalog, and dataset showcase, with support for configurable data providers, charts, maps, and schemas. A bare template is also available without the AI skills, and the project presents Git, object storage, Parquet, and DuckDB as an optional modern architecture while retaining traditional datastores as supported choices.
Kandev is an open-source, self-hostable AI Kanban and development environment for orchestrating coding agents and reviewing their work. It organizes tasks in Kanban and pipeline views, supports parallel execution and multi-step agentic workflows, and isolates concurrent work with Git worktrees. Its integrated workspace combines a file editor, file tree, terminal, browser preview, chat, and Git changes for reviewing and iterating on agent output. Agents can run through local, Docker, SSH, or cloud runtimes, with support for multiple agent providers; the project also provides configurable workflows, agent profiles, prompts, review gates, scheduled or webhook-triggered automations, and no telemetry.
deja-vu is a local memory and search layer for AI coding agents. Its Go binary indexes session histories already stored on a machine by Claude Code, Codex, Cursor, and other supported agents, including sessions recorded before installation, without using an LLM or embeddings. It provides natural-language and direct search, session inspection, context retrieval, JSON output, redaction, usage statistics, and MCP-based cross-agent recall; the index strips keys and tokens as it is built and can synchronize append-only memory between machines over SSH. Recall can be injected automatically at session start and before prompts, file edits, or commands, and a post-command hook can retrieve what followed a matching failure when the agent supports those hooks. It also indexes files opened during each turn, executed commands and exit statuses, and exact spans replaced by edits, rather than only conversation text. Decisions can be marked as accepted or rejected with notes, and results can report when indexed files have changed since a session. The repository reports sub-millisecond lookups over 5 GB of history, with benchmark harnesses for LongMemEval-S and LoCoMo. The project is distributed as a local binary with installation options including a shell script, Homebrew, Go, npm, Scoop, release archives, and agent-specific plugin or MCP bundles. Its optional installation wiring configures supported agents for MCP and session-start recall.
The GitHub Copilot SDK is a multi-platform SDK from GitHub for embedding the agent runtime behind Copilot CLI in applications and services. It provides SDKs for Node.js/TypeScript, Python, Go, .NET, Java, and Rust, allowing applications to invoke Copilot agent workflows while the runtime handles planning, tool invocation, file edits, and related orchestration. Applications can also define custom agents, skills, and tools. Each SDK communicates with Copilot CLI running as a server over JSON-RPC. The SDK manages the CLI process lifecycle automatically and can connect to an externally run CLI server. The repository provides package-specific installation and API instructions; the CLI is bundled automatically for Node.js, Python, and .NET, while Go, Java, and Rust generally require a separately available CLI, with application-level bundling features available for Go and Rust. Standard use requires a GitHub Copilot subscription, and usage follows the Copilot CLI billing model, with prompts counted toward the applicable allowance. A BYOK mode supports API keys from supported providers without GitHub authentication.
Chatwoot is an open-source, self-hosted customer support platform and omnichannel support desk. It centralizes conversations from website live chat, email, Facebook, Instagram, Twitter, WhatsApp, Telegram, Line, SMS, and other channels in a shared inbox, with tools for assignment, automation, labels, canned responses, teams, internal notes, contact management, segmentation, and reporting. It includes a Help Center Portal for publishing help articles, FAQs, and guides, and Captain, its AI support agent, which automates responses and handles common queries. The platform also provides integrations including Slack, Dialogflow, Shopify, Google Translate, and Linear, and is distributed as an open-source, self-hostable alternative to Intercom, Zendesk, and Salesforce Service Cloud.
Instatic is an open-source, self-hosted visual CMS that combines a canvas editor, content engine, media management, authentication, forms, plugins, and publishing in one Bun server. It supports SQLite or Postgres and generates plain semantic HTML and compact CSS without a framework runtime, builder attributes, or editor machinery in the published pages. The project can be deployed through Railway, Render, Docker, or a VPS, and is distributed under the MIT license. It is designed to manage the full site-building workflow, including users, roles, content, and databases, rather than serving only as a page editor.
Speech To Speech is an open-source, modular voice-agent pipeline from Hugging Face. It chains voice activity detection, speech-to-text, a language model, and text-to-speech as separate stages connected by queues; each stage has interchangeable backends. The language-model stage supports OpenAI-compatible protocols and can use hosted providers, Hugging Face Inference Providers, vLLM, or llama.cpp, while the system streams transcripts, generated text, tool calls, and synthesized audio. The project exposes the core OpenAI Realtime event set through WebSocket and WebRTC and includes commands for running a realtime server, a microphone-and-speaker client, or a local setup. It is distributed as a Python package and requires Python 3.10 or newer. The repository says the pipeline is used as the conversation backend for Reachy Mini robots.
HarkinianPad is a native iOS and iPadOS application that packages the Ship of Harkinian Ocarina of Time source port for iPhone and iPad. It uses Metal rendering, imports a user-provided supported Ocarina of Time ROM through the Files app, and provides a landscape touch controller alongside support for keyboards, pointing devices, and iOS game controllers. The repository contains the mobile integration and reproducible build scripts, but no game ROM or ROM-derived archive. Builds can target the iOS simulator or physical devices using Xcode, and the project is distributed as a developer preview or local build rather than through the App Store or TestFlight.
ntfy is an open-source HTTP-based publish-subscribe notification service that accepts messages through PUT or POST requests and delivers them to subscribed phones or desktops via named topics. It provides a hosted service at ntfy.sh, open-source Android and iOS apps, and a server that can be self-hosted; scripts can publish notifications from any computer without requiring an account or fee. Paid plans are available for the hosted service. The project is dual-licensed under the Apache License 2.0 and GPLv2.
Lichess is a free, ad-free, open-source online chess server developed as the Lila project. It supports real-time games, tournaments, simultaneous games, forums, teams, puzzles, studies, shared analysis, a search engine, a mobile app, and an HTTP API. Computer analysis is distributed through Fishnet and Stockfish running on a cluster of donated servers; rated games are published in a free PGN database. Lila is written in Scala 3 with a modified Play framework. Its asynchronous server uses Scala Futures and Pekko streams, while a separate WebSocket server communicates through Redis. MongoDB stores games indexed by Elasticsearch, and the TypeScript web client uses Snabbdom and Sass. The project is licensed under the GNU Affero General Public License version 3 or later.
Temporal Ruby SDK is Temporal Technologies' official open-source Ruby framework for authoring and running durable workflows and activities. Workflows and activities are defined as Ruby classes; clients start workflow executions, and workers execute them while communicating with a self-hosted Temporal Server or Temporal Cloud. The SDK uses a Rust core and provides workflow testing with automatic and manual time skipping, along with activity invocation, child workflows, timers, cancellation, replay, telemetry, and workflow-safety checks. It is distributed as the `temporalio` Ruby gem and supports macOS and Linux on ARM and x64.
Zinley is a personal representative service that acts on a user’s behalf in personal matters, sales, customer support, recruiting, and related interactions. It integrates with the user’s tools and communicates with people and external systems outside those tools.
Bolcho AI is an Indian company offering a voice and chat AI platform that enables organizations to build, launch, and scale conversational agents for phone calls and websites in Indian languages. The service markets itself as operating at near provider cost and targets Bharat-language use cases.
An open-source AI software-development factory provided as a Vercel template and implemented by Foreman. It takes tasks from GitHub issues, GitHub mentions, Linear Agent Sessions, or a local developer TUI and moves them through four isolated agent stations: a Classifier triages task type, priority, complexity, and actionability; an Analyst creates a plan and acceptance criteria from a live repository checkout; an Implementer executes the plan in a sandbox, runs the repository's checks, and pushes a branch; and a Reviewer independently evaluates the resulting diff with evidence. The pipeline produces a reviewed draft pull request for human approval, after which people mark it ready and merge it. Foreman maintains shared repository notes between runs, can diagnose failing CI on its own factory pull requests, and posts progress to the originating GitHub or Linear task. The deployment flow configures GitHub and Linear connectors, Vercel Blob storage, a target repository, and an issue label.
Embabel is an open-source framework for authoring agentic flows on the JVM. Written in Kotlin with a natural Java usage model and built on Spring, it combines LLM-prompted interactions with manually written code and strongly typed domain models. Flows are expressed through actions, goals, conditions, and domain objects; they can be authored with Spring-style annotations such as @Agent, @Goal, @Condition, and @Action, or with an idiomatic Kotlin DSL. The framework dynamically formulates plans toward goals using a pluggable, non-LLM planning step. Its default approach is Goal Oriented Action Planning (GOAP), while Utility AI is also supported for selecting actions by utility scores rather than strict preconditions and postconditions. Conditions are reassessed after each action, and the system replans based on new information and observed effects, allowing known actions to be combined in novel orders and enabling runtime decisions such as parallelization. The planning model is independent of the actions, goals, and plans themselves, and can extend application capabilities by adding domain objects, actions, goals, and conditions without changing finite-state-machine definitions. Execution is provided through an AgentPlatform with focused, closed, and open modes. Focused mode runs a requested agent from application code; closed mode classifies user intent or an incoming event to select an agent; and open mode searches across available goals and actions to build a custom agent, while allowing developers to restrict goal selection. Open mode can find paths not explicitly envisioned by developers and combine functionality from multiple providers, but individual steps must still be defined by the application. Embabel supports mixing language models, including local models for selected tasks, separates the programming model from platform internals for local or production execution, and integrates with Spring dependency injection, AOP, persistence, transactions, and testing. The framework is designed for unit and end-to-end agent testing.
Decagon is an enterprise AI customer-support platform with autonomous agents for handling customer inquiries and operational workflows across support channels. Its agents resolve issues using connected business systems, escalate cases to human support staff when needed, and provide business-process logic, integrations, testing, monitoring, compliance support, and deployment capabilities.
ANYmal is a four-legged autonomous inspection robot developed by Swiss company ANYbotics. It is designed for industrial inspection and monitoring in indoor and outdoor environments, carrying sensors and payloads for navigation and perception and used in sectors such as energy, oil & gas, and manufacturing.
Apple Intelligence is Apple's branded set of generative AI features and on-device models introduced in 2024 to enhance Siri, system capabilities, and apps across iPhone, iPad, and Mac. The initiative covers local model execution, iCloud integration for personal context, and tools for developers to use Apple-provided and on-device intelligence.
GQA is a dataset for visual question answering and visual reasoning that provides grounded, compositional questions and answers over real-world images, built from scene graph annotations (derived from Visual Genome). It is used to train and evaluate models on compositional, spatial and relational reasoning in images.
Palantir Technologies builds software for organizations to integrate data, decisions, and operations.
Waymo Driver is an autonomous driving system developed by Waymo (a subsidiary of Alphabet Inc.) that enables vehicles to operate without a human driver. It combines lidar, radar, cameras and machine-learning based perception and planning software and is used in Waymo's robotaxi services and commercial vehicle programs.
A feature of Anthropic's Claude platform that packages reusable instructions, scripts, and reference files into skills that Claude can apply to specific tasks. Skills can be used in Claude applications and through Anthropic's agent-development tools.
ChatPRD is an AI platform for product managers that helps teams create product requirement documents, offers expert coaching, and integrates with common workflows. The service is presented on chatprd.ai and the site states it is used by more than 100,000 product managers.
Higgsfield Supercomputer is an AI creative tool that turns a user's description into a finished render. It plans the work, selects models, and produces the result within a single chat interface, aiming to remove prompts, presets, and separate tool switching. It is offered by Higgsfield at higgsfield.ai.
Mellea is a Python framework for developing generative AI applications, with abstractions for composing language-model programs and controlling their execution.
WormGPT is a named AI chatbot reported to be designed and marketed for cybercriminal use, offering guidance and code related to malware, phishing, and intrusion techniques. It emerged in reporting from late 2023 and was discussed by cybersecurity firms and in underground forums as an illicitly purposed generative AI service.
Nanostack is a lightweight IPv6/6LoWPAN network protocol stack for low-power IoT devices, developed for use with Arm Mbed OS. It implements IPv6 networking, 6LoWPAN adaptation, and related mesh networking features for constrained devices.
camelAI is an AI coding assistant platform built on Cloudflare Workers and Durable Objects. Each chat thread runs a coding agent in its own persistent workspace, retaining chat state and project files while providing workspace-aware tools. The platform connects to APIs, databases, email, Slack, Discord, and other services; supports application builds, notebook analysis, and SQL execution in isolated short-lived sandboxes; and provides previews and publishing through Workers for Platforms. Its agent harness is built on pi's lower-level agent-loop and state-management libraries. The agent uses native file tools and writes JavaScript rather than shell commands; Code Mode executes that JavaScript in fresh V8 isolates with explicit platform and connection methods. Project files are stored in WorkspaceFilesystem Durable Objects, using Durable Object SQLite for small files and R2 for larger ones, while Cloudflare Artifacts provides Git history. Linux sandbox containers are reserved for jobs requiring them, including builds, notebook analysis, and database queries, and credentials remain outside the execution sandbox. The platform can use Anthropic, OpenAI, OpenRouter, Bedrock, and custom model endpoints. Its repository is released under the MIT License and includes local development setup using Node.js, Bun, and a Cloudflare account.