2,425 tools and products — trending open source, and what gets used in AI and other work.
U-Pool is a desktop provider and account switcher for Claude Code, Claude Desktop, Codex, Hermes, OpenCode, and Cursor. It keeps endpoint URLs, API keys, models, and provider accounts in per-tool lists, then makes a selected provider or Cursor account active without manual edits to settings.json, config.toml, other tool configuration files, or Windows user environment variables. Its reachability probe sends a plain GET request to a provider’s models endpoint to measure latency without running a completion or consuming a token. The app uses a Python backend, a statically exported Next.js interface, and a native OS webview rather than Electron or a Node runtime. Its source of truth is ~/.u-pool/config.json; on each switch, an adapter changes only the keys it owns in each target file and preserves other settings such as plugins, hooks, marketplaces, themes, MCP servers, and project trust. Writes use a temporary file followed by os.replace, keep an adjacent backup, and stop rather than overwrite a configuration file that cannot be parsed. Existing provider settings can be imported on first run. The app includes provider presets, an official-vendor mode that clears U-Pool-managed settings, per-provider permission controls, cached installed Claude Code and Codex versions, and controls that erase the transcript and prompt-history files for those CLIs. The Cursor pool stores multiple signed-in Cursor accounts, accepts cookies in common formats, displays account names, email addresses, plans, and usage, and switches accounts by changing the specified Cursor authentication database rows. Claude Desktop is currently preview-only: providers can be saved and tested but are not written to its configuration. Hermes and OpenCode have dedicated configuration writers, while Codex writes its provider, model, approval, sandbox, web-search, and authentication settings. The core configuration operations are cross-platform. Windows-only integrations write owned variables to HKCU\\Environment and broadcast changes, launch the app at sign-in, and provide an in-app updater; Hermes, OpenCode, and Cursor read credentials from their own files and do not use those environment-variable writes.
Context Ontology Accelerator is an open-source semantic context layer for AWS and AI agents. It combines knowledge graphs, formal ontologies, rule-based systems, and modern AI in a Scan → Model → Serve workflow: it connects data sources, discovers schemas, enriches metadata, and ingests documents; induces and manages ontologies, defines metrics, and builds a unified semantic graph; then serves context through SPARQL federation using a Virtual Knowledge Graph, knowledge-graph traversal, queries, and MCP tools. The repository includes source-ingestion services for databases and documents, ontology induction and reasoning with HermiT and ELK, an Ontop-based Virtual Knowledge Graph, a context manager for query orchestration, and a React frontend. Access is controlled through namespace isolation and role-based authorization, with namespace-scoped roles and platform-level roles. The implementation uses Python and TypeScript, AWS CDK, Smithy-generated API contracts, and an Nx-managed monorepo; the project is licensed under Apache License 2.0.
Trace File Lineage is a local-first Python and command-line tool for tracing the origins of files, recording task outputs, and helping place new outputs in an existing workspace layout. For existing files, it reads source code, documents, image metadata, and Git history to rank possible scripts, notebooks, inputs, and runs, attaching evidence and marking results as uncertain when proof is unavailable. For future runs, it wraps a command and records verified provenance from the files changed within the task boundary. It can produce a complete manifest with a nested changed-file structure, show ranked lineage candidates, identify files affected by an input, report stale files, and suggest an output path based on workspace conventions. It is distributed as a Python package with the `trace-file-lineage` installation name and includes a demo command that writes to a local demo directory.
LingBot-Map is a feed-forward 3D foundation model from the Robbyant Team for streaming 3D reconstruction from image sequences and video. Its Geometric Context Transformer unifies coordinate grounding, dense geometric cues, and long-range drift correction through anchor context, a pose-reference window, and trajectory memory. The system uses paged KV-cache attention for streaming inference and supports interactive browser-based reconstruction with point-cloud visualization, keyframe intervals, windowed processing for long sequences, and sky masking. It also provides an offline rendering pipeline for image folders or video, along with evaluation pipelines for datasets including KITTI and Oxford Spires. The repository reports approximately 20 FPS inference at 518×378 resolution on sequences exceeding 10,000 frames, and documents PyTorch installation with FlashInfer as the recommended attention backend and native SDPA as a fallback.
Lila is the open-source server software that powers lichess.org, developed by Thibault Duplessis (ornicar) and community contributors. The codebase is written in Scala (Play Framework) and runs on the JVM, implements real-time and correspondence chess, tournaments, puzzles, studies, user accounts, forums and a JSON API, and integrates with chess engines via the UCI protocol (commonly Stockfish) for computer play and analysis. The source is published under the GNU AGPLv3 on GitHub.
Glassnode is a commercial blockchain analytics platform that provides on-chain data, derived metrics, charts and research for digital-asset markets. It ingests blockchain and market/exchange feeds and publishes time-series indicators (for example, long-term-holder metrics that count coins unmoved for roughly six months), charting, alerts, and a REST API/CSV exports for institutional and retail customers. The service is distributed as a tiered SaaS product with free and paid plans and enterprise data access.
Binance is a centralized cryptocurrency exchange and digital-asset platform founded in 2017 by Changpeng Zhao and operated by Binance Holdings Ltd. It accepts fiat and crypto deposits and provides spot trading, margin, derivatives (futures and options), staking, savings, P2P trading, an NFT marketplace, OTC services and custody/wallet features; it also operates the BNB Chain (formerly Binance Smart Chain) and issues the BNB token. The platform is delivered via web and mobile apps, exposes REST and WebSocket trading APIs and SDKs, and maintains regional subsidiaries (for example Binance.US) to address local regulatory requirements.
WhatsApp Business API, marketed as part of the WhatsApp Business Platform and provided by Meta, is a REST API and webhook-based messaging platform for businesses to send and receive customer messages at scale. It supports text, media (images, audio, video, documents), interactive message types and approved message templates, is available as Meta-hosted Cloud API or a self-hosted/on‑premises deployment, requires a verified Business Account and phone number, and is intended for integration with CRMs and customer-service automation under WhatsApp Business policies and per-message pricing.
MusicBrainz is an open, community-maintained music metadata database and "open music encyclopedia" operated by the MetaBrainz Foundation that assigns persistent MusicBrainz Identifiers (MBIDs) for artists, releases, recordings, works, labels and release-groups. It publishes regular database dumps and offers a public webservice (JSON/XML REST API) and search endpoints, and ships an official tagging client (MusicBrainz Picard). MusicBrainz integrates with audio-fingerprint services such as AcoustID/Chromaprint for identification and is used for tagging, synchronization, cataloging and lookup by media players, taggers and content services.
A web-based DevOps platform developed by GitLab Inc. that provides Git repository hosting, issue tracking, merge requests (code review), CI/CD pipelines, container and package registries, and security and compliance scanning. It is available as a hosted SaaS at gitlab.com and as self-managed Community (open-source/open-core) and Enterprise editions, and integrates with Kubernetes and scalable CI runners for automated workflows.
IGDB (Internet Games Database) is an online database of video-game metadata and a developer-facing API, maintained by Twitch (acquired 2019). It provides structured information on games — including titles, platforms, release dates, genres, themes, companies, cover art, screenshots, videos and external IDs — and exposes that data via a REST API that uses Twitch developer authentication and terms of use.
ScreenScraper is a community-run database and media repository for retro video games that collects and redistributes game metadata and media assets under Creative Commons. It provides downloadable media and metadata intended for multi-system gaming front-ends and community projects.
MobyGames is an online, community-maintained database of video game metadata and credits, established in 1999. It aggregates release dates, platforms, developer and publisher credits, cover art, screenshots, genre tags, system requirements, and user-contributed reviews and trivia, and provides a searchable web interface and browseable game pages.
A browser-based emulator embedding toolkit that lets websites run supported game titles in the browser. Distributed from emulatorjs.org, it provides JavaScript code for loading emulator cores and ROM files (local upload or hosted) and for playing games in modern web browsers.
RetroAchievements is a community-run website and service that adds modern-style achievements and tracking to classic video games by monitoring in-memory game state via supported emulator clients. It maps achievements to specific game ROMs (checksums), provides per-game achievement lists, user profiles, leaderboards and unlock records, and exposes an online API used by emulator integrations (examples of supported clients include BizHawk and RetroArch).
Monolith is a command-line tool and library for archiving complete web pages as a single HTML5 file. It retrieves a target document and embeds its CSS, images, JavaScript, and other assets as data URLs, allowing the saved page to render without a network connection. It accepts URLs or HTML from standard input and provides options for excluding asset types, setting a base URL, controlling domain access, reading cookies, handling network errors, isolating documents, and producing MHTML instead of HTML. The project is written for cross-platform installation through Cargo, package managers, containers, and pre-built binaries.
Open Food Facts is a collaborative, free and open database of food products, ingredients, nutrition facts, and related information. It lets users search products or scan barcodes, and provides open data that can be reused for food-choice, fitness, and nutrition-tracking applications. The non-profit project is developed by volunteers worldwide and is available through a website, mobile apps, and an API.
Grafana is an open-source observability and data visualization platform for querying, visualizing, alerting on, and understanding metrics, logs, and traces from multiple data sources. It provides client-side graphs and panel plugins, reusable dashboards with template variables, ad hoc metric queries and drilldowns, log search with preserved label filters, and alert rules that can send notifications to systems such as Slack, PagerDuty, VictorOps, and OpsGenie. Queries can combine different data sources in the same graph, including Prometheus, Loki, Elasticsearch, InfluxDB, PostgreSQL, and other custom data sources. The project is distributed under AGPL-3.0-only, with Apache-2.0 exceptions documented in its licensing files.
Loki is an open-source log aggregation system developed by Grafana Labs that indexes and queries logs using Prometheus-style labels instead of full-text indexing. It ingests log streams via shippers such as Promtail, Fluentd, or other collectors, stores data in local or object-storage backends, and is queried with the LogQL language; it integrates with Grafana for visualization and is available for self-hosting or via Grafana Cloud.
An open-source distributed tracing backend developed by Grafana Labs. Tempo ingests traces via Jaeger, Zipkin and OpenTelemetry (OTLP), stores trace data in scalable object stores (Amazon S3, Google Cloud Storage, Azure Blob Storage, MinIO) using a chunk-based, low-index architecture, and exposes query APIs compatible with Jaeger/OTLP with tight integration into Grafana for visualization. It is available under the Apache 2.0 license and can be run self-hosted (Docker, Kubernetes/Helm) or used as a managed service on Grafana Cloud.
Lunr.js is a small, browser-based full-text search library developed in the olivernn/lunr.js project. It indexes JSON documents locally and provides a search interface that returns matching document references, relevance scores, and match metadata; it can generate the search index used by static sites such as microblogs. It supports field-specific searches, query-time term boosting, document-level index boosting, wildcard and edit-distance fuzzy matching, and full-text search in 14 languages. The library can be included directly in a web page or installed through npm, and is intended for client-side searching without a server-side search service or network connection.
A serverless AI inference platform from Cloudflare that runs machine-learning models on Cloudflare's network and exposes them through the Workers platform. It supports tasks such as text generation, image generation, speech recognition, and text embeddings, making it usable for applications including semantic search.
VIOFO is a manufacturer and retailer of vehicle dash cameras offering 4K UHD units built around Sony STARVIS 2 sensors. Its product line includes 1- to 4-channel systems with buffered parking mode for continuous and event video capture, producing recorded dashcam footage used for driving and parking evidence. VIOFO devices and accessories are sold through the VIOFO official store and third-party retailers and are distributed with firmware and support from the company.
MariaDB Server is an open-source relational database developed by a global community with the MariaDB Foundation and MariaDB plc. It began as a fork of MySQL led by members of the original MySQL team and maintains substantial MySQL wire-protocol and syntax compatibility, making it a database backend for applications such as the Magic application builder. The server supports pluggable storage engines including InnoDB, Aria, MyRocks, ColumnStore, Spider, and S3; asynchronous, semi-synchronous, and parallel replication; and Galera synchronous multi-primary clustering. Its SQL features include vector search with a built-in VECTOR type and HNSW indexing, common table expressions, window functions, temporal tables, sequences, JSON functions, GIS, full-text search, role-based access control, pluggable authentication, encryption at rest, and TLS connections. It is licensed under version 2 of the GNU General Public License.
A declarative, interpreted programming language designed for controlled execution of generated code. Its function-invocation model can restrict which functions code is permitted to call.
Prisma ORM is an object-relational mapper and query builder for Node.js and TypeScript applications, developed by Prisma. It supports PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB, and CockroachDB. The repository's Prisma Next development line is a TypeScript rewrite with a composable core, database support built through a public extension interface, and agent skills that can be registered in a project so AI coding agents can work from a Prisma contract and workflow-specific references. Prisma Next is described as early access and not recommended for production workloads yet.
An online course and community (branded Switch Dimension AI) created by Rob Shocks that teaches how to build and ship products with AI. The offering combines instructional content on building AI-powered applications with access to a learner community and is hosted at switchdimension.com.
A Notion template created by Jeff Su that collects 15 reusable AI prompts for writing, research, ideation, and analysis. Each entry includes the prompt text, usage instructions, and a video walkthrough with examples; the template notes compatibility with ChatGPT, Claude, and Gemini and is distributed via the Notion Marketplace.
MiniMax is an artificial-intelligence company and model provider offering large language models through hosted APIs, including models designed for coding, reasoning, and tool-using agent workflows. It is used as a model provider by agent frameworks such as Hermes Agent.
PyCharm is an integrated development environment (IDE) for Python developed and distributed by JetBrains. It is available in a commercial Professional edition and a free, open-source Community edition; it runs on Windows, macOS, and Linux, is built on the IntelliJ Platform, and provides code completion, static code analysis, refactorings, debugging, test running, profiling, virtualenv/Conda interpreter management, Docker and remote-interpreter support, Jupyter notebook integration, database tools, and framework-specific support for web frameworks such as Django and Flask.
An MCP server from Zapier that connects authenticated applications so compatible AI tools can access and use them through a single integration layer. It supports clients including Cursor, Claude Code, and Codex.
pandas is an open-source Python package for working with relational and labeled data through mutable DataFrame and related data structures. It supports missing-data handling, automatic or explicit label alignment, group-by split-apply-combine operations, indexing and slicing, merging and joining, reshaping and pivoting, hierarchical labels, and time-series operations such as date-range generation, frequency conversion, and rolling-window statistics. Its I/O tools load data from CSV and other delimited files, Excel, and databases, and support saving to and loading from HDF5; it is distributed through PyPI and Conda.
Matplotlib is a Python library for creating static, animated, and interactive data visualizations. It produces publication-quality figures in multiple hardcopy formats and interactive environments, and can run in Python scripts, Python/IPython shells, web application servers, and graphical user-interface toolkits across platforms.
Streamlit is an open-source Python framework for turning scripts into interactive web apps without separately building an API or a JavaScript and HTML application. It supports dashboards, reports, chat apps, input widgets, dataframes, charts, layouts, and multipage apps; developers run an app with the `streamlit run` command and can extend it with Streamlit Components. The project also provides Community Cloud for deploying, managing, and sharing apps. It is free software licensed under the Apache 2.0 license.
Blitzy is an enterprise AI software platform that ingests large codebases and generates coordinated code changes across them, with a focus on refactoring and modernizing legacy applications.
Claude is a family of large language models developed and hosted by Anthropic. Available through Anthropic's web chat products and a commercial API, Claude accepts text prompts (and structured inputs or file attachments via the API) and returns natural-language and code outputs for tasks such as coding, summarization, document Q&A, and general business and productivity workflows; it is used inside Anthropic products (for example Claude Code) and by third-party services via Anthropic's API and enterprise agreements.
Ether.fi Cash is a crypto-backed savings and payments product from Ether.fi that pairs a yield-bearing crypto/stablecoin account with a payment card. Users deposit crypto or stablecoins into the Cash account to earn yield and can spend via a virtual or physical card that advertises cashback; the product also advertises borrowing against deposited collateral and trading tokenized assets. The service is delivered through Ether.fi's web and mobile app and requires a verified account (KYC).
TechLead Pro is a paid private membership community operated by the creator “TechLead” and offered through the Whop platform. The community focuses on cryptocurrency and DeFi topics — including passive-income strategies, arbitrage, market making, and group strategy breakdowns — and membership provides access to the creator's gated content and member discussions.
L'Hebdo is the weekly news bulletin of Impact Centre Chrétien — Bruxelles. It is distributed as a downloadable PDF and contains church news, practical information and event schedules for the congregation.
An AI governance and compliance platform from IBM's watsonx suite that provides audit trails, bias detection, prompt monitoring, policy enforcement, and reporting for enterprise AI deployments. It ingests models, prompts and usage telemetry and produces audit logs, explainability and bias reports, and configurable controls to support regulatory and internal compliance processes.
Hotplate is a hosted SaaS platform for independent chefs, bakers and food entrepreneurs to create customer-facing storefronts and accept online orders. It provides menu and product listings, preorder and order management, pickup coordination, and customer-facing tools such as reminders and order notifications via a web dashboard and storefront. The service is offered by Hotplate through its website as a managed online-ordering and business-management solution for small food businesses.
Overlap is a web-based AI platform for automated video clipping and short-form content production, marketed to creators, podcasts, and media organizations. It ingests uploaded long-form video or podcast audio and uses agentic AI workflows to find high-interest moments, produce clips and shorts, generate captions and on-screen graphics (or B-roll), and export or publish social posts for distribution.
A downloadable list of 30+ "unsexy" or blue-collar business ideas compiled and published by the My First Million podcast. The resource aggregates business concepts mentioned on MFM episodes and is distributed as a free lead magnet via the podcast's HubSpot offers landing page.
An annual ticketed, in-person conference produced by the All-In podcast and its community, featuring live conversations with the podcast hosts, panels, special guests, entertainment, and networking. The event is marketed to listeners and community members and runs multi-day programming; the 2026 edition is scheduled for September 13–15 in Los Angeles.
An open-source research simulation for computational agents that model believable human behavior in an interactive game environment. The repository includes a Django-based environment server and a separate agent simulation server; the two run concurrently, with the simulation using an OpenAI API key and the browser-based environment providing the interactive view and replayable demo animations. The project was tested with Python 3.9.12 and includes setup instructions, required packages, and predefined simulation scenarios.
A marketed guide and sales landing page hosted at communityboardplaybook.com that offers instruction on earning money with direct-mail / community-card advertising; the landing page headline reads "Want an Easy Way To Make $1,000 With Direct Mail?". The site title uses "Community Card Playbook" while the domain name uses "communityboardplaybook.com" and the front page does not clearly identify an author or publisher.
Big Sky Automation Services is a local-marketing and automation agency run by Rachel and her husband that builds websites and provides reputation management, review-generation, chat widgets, AI receptionist services, and other automation for local businesses. Its website (bigskyautomationservices.com, presented on-page as SkyHigh Reviews) advertises done-for-you Google Business Profile management and review generation for home-service businesses, including a free website via a subscription (listed at $397/mo + $300 one-time setup).
MoneyPrinterTurbo is an AI short-video generation tool that turns a topic or keyword into a high-definition video. Its automated workflow generates or accepts a script, extracts search keywords, matches footage from local materials or supported stock sources, synthesizes narration, creates configurable subtitles, adds background music, and renders the result. It provides WebUI, API, CLI, and AI-agent interfaces; supports batch generation, multiple languages, portrait and landscape formats, adjustable clip durations, and multiple text-to-speech and large-language-model providers. It can also generate visual material through supported text-to-video models and automatically publish completed videos to TikTok, Instagram, and YouTube Shorts.
Career Ops is an open-source AI job-search system that runs locally through compatible AI coding CLIs. It scans Greenhouse, Ashby, Lever, and company career pages; compares listings with a CV and evaluates them in an A–H report with a global 1–5 score. The system uses Playwright to navigate career pages, can process multiple offers with sub-agents, generates ATS-oriented CV PDFs tailored to individual job descriptions, records applications in a tracker, and researches companies and potential contacts. Its separate Block G assesses posting legitimacy, including scam or ghost-job risk, while Block H drafts additional material only for highly scored roles. It is intended to filter opportunities rather than submit applications, which users review and submit themselves.
Microsandbox is a local-first microVM runtime and library for running untrusted workloads, including AI-agent tasks, user code, plugins, CI jobs, development environments, scrapers, and automation. It uses hardware-level isolation and runs standard OCI container images from registries such as Docker Hub and GHCR, with Docker-like image, command, shell, and volume workflows. The project provides SDKs for TypeScript, Rust, Python, Go, and Ruby, along with a CLI for booting and controlling sandboxes. Applications can create microVMs as child processes without a setup server or long-running daemon; sandboxes can also run detached for long-lived sessions. Agent Skills and an MCP server support agent-created sandboxes, and the project documents secret handling intended to keep keys out of the VM. It runs on Linux, macOS, and Windows, with platform-specific virtualization requirements, and is described as beta software.
Remocn is a copy-paste component library for building videos with Remotion. It provides animations, transitions, backgrounds, scenes, fades, wipes, and kinetic titles as Remotion code that developers add to their projects through the shadcn component registry and can modify directly. Its components use Remotion's `useCurrentFrame()`, `interpolate()`, and `spring()` APIs. Component pages provide live previews using `@remotion/player`, allowing frame-by-frame scrubbing. Remotion is required as a prerequisite, and the project also provides an optional agent skill for setting up and working on Remotion video projects.
E2B is a cloud sandbox service for securely running AI-generated code, tools, and agents. It provides infrastructure for executing agent workloads in isolated environments.
Venice AI is a private AI service for generating text, images, characters, and video, with access to AI inference without the intermediary markup associated with services such as OpenRouter.
Google for Developers is Google's developer-focused resource and media platform, providing documentation, guides, tools, and technical content for Google technologies and APIs. It also operates an official YouTube channel for developer announcements, tutorials, and event content.
Modern Software Engineering is an organization and content platform focused on practices for producing better software faster. Its LinkedIn page features work and talks from software engineering leaders including Dave Farley, Trisha Gee, Steve Smith, Emily Bache, Kevlin Henney, and Kent Beck.
TransFICC is a financial-technology provider of low-latency connectivity and workflow automation for fixed-income and derivatives trading. Its platform provides a unified API connecting banks and asset managers with multiple electronic trading venues and supports automated trading workflows.
Mu is a self-hosted personal-agent platform that provides one home for agents, tools, services, and collected data. Its server can be accessed through a web app, email, MCP, HTTP, and a command-line interface, and supports bringing your own model. Mu exposes services for mail, chat, news, video, markets, search, files, calendars, and small web applications. These services are available through APIs, the CLI, the web, or as MCP tools. Data collected by the services is archived locally so it can be searched across sources. Users can define agents by name, prompt, and permitted tools, then chat with them through the web, mail, or XMPP. The platform also provides a unified inbox for email and chat threads, including access through IMAP.
Scandinavian Design is a Cursor agent skill for applying a restrained Scandinavian visual system to an existing codebase. It can redesign or review an interface, prototype visual directions, and inspect a complete flow while preserving useful brand and accessibility decisions. Its stated design rules use a black-and-white foundation, sans-serif typography, generous spacing, and purposeful product imagery. The repository includes ten demo sites restyled through a CSS-override fallback, with desktop and mobile before-and-after captures, and can be installed with npx skills add ericzakariasson/scandinavian-design.
Marketing OS is a Markdown-based agent skill that turns Claude, Codex, or Cursor into a structured marketing workspace. Its 14 modules cover website and funnel audits, AI-search citability, copy, hooks, paid ads, email, social posts, launches, positioning, pricing, competitor research, app-store optimization, analytics, and prose-quality checks. The skill routes each task to the relevant module and can fan out multidimensional work across subagents when the host supports it. It produces scored reports, prioritized fixes, diagnostic briefs, marketing copy and sequences, launch plans, and other finished artifacts rather than advice alone; its reports are designed to identify what could not be determined and label scores as heuristics. It is distributed as pure Markdown under the MIT license and can be installed through Claude Code, uploaded to Claude, or copied into the skills directory of compatible agents.
Zoetrope is a terminal and browser visualization tool for Claude Code sessions. It reads Claude Code's local JSONL transcripts and renders the main agent, spawned subagents, workflow groups, and their tool calls as a live flow graph, updating as a session runs or replaying a completed session from its recorded timestamps. Its event-indexed timeline supports scrubbing, pausing, stepping between prompt eras, following the live edge, and seeking backward to view the graph at an earlier state; agent cards show status, current tools, tool counts, and output tokens, while tool calls resolve to success or failure. The browser version uses the same engine compiled to WebAssembly, and the README states that sessions remain local and read-only. It is distributed through Homebrew, Cargo, prebuilt binaries, source builds, and the browser interface; its command-line executable is `zoe`.