Tools

Microsoft's automated red teaming framework for AI systems

PyRIT (Python Risk Identification Toolkit) is Microsoft's open-source framework for automated red teaming of generative AI systems. It enables security researchers to probe LLMs for jailbreaks, prompt injection, content safety bypasses, and harmful output generation using multi-turn attack strategies, scoring engines, and orchestrated adversarial workflows. Supports multiple target models and integrates with Azure AI services.

Modern test management with AI organization

QA Sphere is a modern, clutter-free test management system that uses AI to organize test cases and track coverage across complex projects. It streamlines the management side of QA that is often handled through messy spreadsheets, providing structured test case repositories, execution tracking, and coverage analytics for technical project managers and QA leads.

AI-generated E2E tests, managed QA service

Fully managed QA service that uses AI to generate and maintain Playwright-based E2E tests. QA Wolf engineers write, run, and maintain tests on your behalf, targeting 80% coverage with custom pricing based on test volume. A unique hybrid approach combining AI test generation with human QA expertise, eliminating the burden of test maintenance that slows most engineering teams.

On-device hybrid search engine for your docs and notes

QMD is an on-device search engine built by Tobi Lütke (Shopify CEO) that indexes markdown notes, meeting transcripts, and documentation locally. It combines BM25 full-text search, vector semantic search, and LLM-powered re-ranking into a single hybrid pipeline. Ships with a built-in MCP server for seamless integration with Claude Code, Cursor, and other AI editors. All processing happens on your machine via node-llama-cpp with GGUF models — zero cloud dependency.

Agentic coding platform by Alibaba Cloud

AI IDE with Quest Mode for semi-autonomous long-running development tasks. Features context engineering that automatically surfaces relevant code, documentation, and project knowledge. Supports Claude, GPT, and Gemini models, letting developers delegate complex multi-step coding workflows while maintaining oversight through structured task tracking and progress reports.

Optimize and deploy AI models on Snapdragon devices

Qualcomm AI Hub is a platform for optimizing and deploying AI models on Snapdragon-powered devices with NPU acceleration. It provides pre-optimized models, profiling tools, and the SNPE SDK for compiling models to run efficiently on Qualcomm's Hexagon DSP and AI Engine. Supports hundreds of model architectures with on-device benchmarking across real Snapdragon chipsets for mobile, IoT, and XR applications.

Programmable Markdown typesetting for docs, books, and slides

Quarkdown is a Turing-complete Markdown typesetting system that compiles a single source into print-ready books, academic papers, knowledge bases, or interactive presentations. It extends Markdown with a built-in scripting language featuring functions, variables, and a standard library for full document control. Supports HTML, PDF, and plain text output with live preview and real-time reloading during authoring.

Governed analytics with a unified semantic layer

Querio turns plain English into SQL queries with a focus on governed analytics, connecting to live data warehouses and enforcing a unified semantic layer across the organization. It ensures that AI-generated queries remain consistent with business logic definitions, preventing the common problem where different teams get different answers to the same question from the same data.

Production RAG engine with hybrid search and knowledge graphs

R2R is a production-grade RAG engine from SciPhi AI that combines hybrid search with knowledge graph extraction and agentic retrieval capabilities. It provides a complete pipeline from document ingestion through retrieval and generation, supporting vector, keyword, and graph-based search strategies. The managed API and self-hosted options make it accessible for both rapid prototyping and production deployments requiring advanced retrieval beyond simple vector similarity.

All-in-one multimodal RAG framework

RAG-Anything is an all-in-one multimodal RAG framework from the University of Hong Kong that processes text, images, tables, and equations through a unified pipeline built on LightRAG. It constructs multi-modal knowledge graphs by extracting multimodal entities and establishing cross-modal relationships. The VLM-Enhanced Query mode integrates visual content into large language models for deeper document understanding beyond plain text retrieval.

Deep document understanding RAG engine

RAGFlow is an open-source RAG engine with 76K+ GitHub stars that provides deep document understanding for building knowledge-based AI applications. Optimizes chunking for 20+ document types including PDFs, Word docs, presentations, and images using layout-aware parsing. Features template-based chunking strategies, citation with source references, multi-recall retrieval combining keyword and semantic search, and a visual knowledge base management interface with drag-and-drop document upload.

Unstyled, accessible React component primitives for building design systems.

Radix UI is an open-source library of unstyled, accessible React component primitives. Provides fully functional components (dialog, dropdown, tooltip, tabs, accordion, etc.) without any styling, letting developers apply their own design. The foundation behind shadcn/ui. WAI-ARIA compliant with keyboard navigation built in.

AI testing and evaluation for agents and LLM apps

RagaAI Catalyst is a comprehensive Python SDK for observability, monitoring, and evaluation of LLM and agentic applications. Provides agent tracing with execution graph visualization, self-hosted dashboard with analytics, synthetic data generation, multi-metric evaluation framework, and guardrail management. Built for teams running production RAG systems and AI agents who need systematic testing, debugging, and performance optimization workflows.

Container-native local AI model serving with Podman

RamaLama is an open-source tool that containerizes AI model inference using Podman or Docker, eliminating host system configuration complexity. It auto-detects GPUs (NVIDIA, AMD, Intel, Apple Silicon), pulls models from HuggingFace, Ollama, and OCI registries, and runs them in isolated rootless containers with read-only mounts and network isolation. Developed under the Containers project (Red Hat ecosystem), it brings familiar container workflows to local LLM serving.

World's largest API hub and marketplace

RapidAPI is the world's largest API hub and marketplace connecting developers to thousands of public and private APIs through a single platform. Provides a unified interface for discovering, testing, and managing API connections with standardized authentication, billing, and monitoring. Features an API testing playground, code snippets in multiple languages, team workspaces, and analytics dashboards. Used by millions of developers to integrate third-party services with a single API key.

Version control for AI coding-agent actions

Re_gent is an open-source version-control layer for AI coding-agent activity. Instead of only reviewing the final Git diff, it records what the agent attempted, changed, and executed along the way so teams can trace, undo, and govern autonomous coding work. It fits Claude Code, Codex, Cursor, and multi-agent teams that need an audit trail between prompt and pull request.

Inspect React component trees

Official browser extension by Meta for inspecting and debugging React component trees, props, state, hooks, and context in real-time. Features component highlighting on hover, profiler for measuring render performance and identifying bottlenecks, and component search/filtering. Supports React 16+ including Suspense, error boundaries, and concurrent features. Available for Chrome and Firefox. Essential for debugging re-renders, state management issues, and understanding component hierarchies.

On-device AI inference for React Native apps

Declarative framework for running AI models on-device in React Native applications, powered by Meta ExecuTorch runtime. Supports LLMs including Llama 3.2, computer vision, OCR, embeddings, and vision-language models on iOS 17+ and Android 13+. Developed by Software Mansion with pre-built optimized models, custom model export support, and privacy-first inference without any cloud dependency for mobile AI development.

Automatically detect and fix slow React re-renders

Open-source tool that highlights unnecessary and slow React re-renders directly in your app — as a browser extension, CLI, or drop-in package, with no code changes required.

Beautiful, personalized API docs

Developer hub platform for creating interactive API documentation with try-it-now API explorer, auto-generated references from OpenAPI specs, custom landing pages, changelog, guides, and usage analytics. Features personalized docs that show API keys and example responses based on the logged-in user. Tracks which endpoints developers actually use. Integrates with GitHub for syncing docs from repos. Used by companies like Twilio and Shopify for their developer portals.

DeepSeek-native terminal coding agent with a Go rewrite and MCP support

Reasonix is an open-source terminal coding agent built around DeepSeek workflows, with a newer Go-based 1.0 line, MCP integration, repository-aware code understanding, and BYOK model usage. It fits developers who want a DeepSeek-first CLI agent rather than a Claude- or OpenAI-native workflow.

Cursor for business workflow automation

Rebolt is a Y Combinator W25 company marketed as Cursor for business workflow automation, focusing on generating the business logic and internal UIs needed for complex company operations. It targets the internal tooling problem with an agentic automation approach, helping teams build custom workflow applications that connect existing business systems without traditional development cycles.

Window management for macOS

Free, open-source window management app for macOS that snaps and resizes windows via keyboard shortcuts and edge drags. Rectangle is the spiritual successor to Spectacle, rebuilt in Swift with halves/thirds/quarters/centering layouts, multi-monitor support, configurable gaps, position restore, and Windows-style snap-to-edge. Rectangle Pro adds extra layouts, groups, and automation.

In-memory data store

In-memory data structure store used as database, cache, message broker, and streaming engine. Supports strings, hashes, lists, sets, sorted sets, streams, geospatial indexes, and HyperLogLog. Features pub/sub messaging, Lua scripting, transactions, persistence (RDB/AOF), replication, and Redis Cluster for horizontal scaling. Redis Stack adds JSON, search, time series, and graph capabilities. Sub-millisecond latency. Available as open-source or managed (Redis Cloud, AWS ElastiCache).

OpenAPI-powered developer portals

OpenAPI documentation renderer with a clean three-panel layout that generates beautiful, responsive API reference pages from your OpenAPI spec. Available as open-source React component or CLI-generated static site. Supports code samples in multiple languages, search, and deep linking, making it the go-to choice for teams who want polished API docs without custom development.

Kafka-compatible streaming platform, no JVM required

Redpanda is a Kafka-compatible streaming data platform written in C++ using the Seastar framework. It eliminates the need for ZooKeeper and the JVM, delivering up to 10x lower tail latencies and significantly reduced operational complexity. Redpanda ships as a single binary with a built-in schema registry, HTTP proxy, and message broker. It supports the Kafka wire protocol, so existing producers, consumers, and tools work without code changes. Backed by $165M+ in funding with 12.0K GitHub stars.

Time-travel debugging for Redux

Browser extension for inspecting and debugging Redux state management in React applications. Features time-travel debugging to replay actions step-by-step, state diff viewer showing exactly what changed, action log with payload inspection, state import/export, and ability to dispatch actions manually. Supports Redux Toolkit and legacy Redux. Available for Chrome, Firefox, and as a standalone Electron app. Essential for debugging complex Redux state flows in production and development.

React meta-framework for enterprise CRUD apps

Refine is an open-source React meta-framework for building data-intensive enterprise applications like admin panels, dashboards, and internal tools. Its headless architecture separates business logic from UI, supporting Ant Design, Material UI, Mantine, and Tailwind CSS. Connects to 15+ backends including REST, GraphQL, Supabase, Firebase, Strapi, and Hasura with built-in authentication and role-based access control. Deploys on Next.js, Remix, React Native, and Electron.

Hundreds of GitHub UI enhancements

Open-source browser extension with hundreds of small UX improvements to GitHub: cleaner diffs, one-click PR merging, reaction avatars, linkified commit SHAs, and much more. Fixes dozens of long-standing GitHub UI annoyances that power users encounter daily, making the GitHub web experience feel polished and efficient without waiting for official feature updates.

DRM and IP protection for AI model weights

RefortifAI is a Y Combinator P2026 batch company that provides DRM and intellectual property protection for AI models by obfuscating model weights so they only run inside a hardened runtime. It solves the critical problem of model weight protection for companies distributing custom LLMs to untrusted environments, preventing IP theft while maintaining inference performance.

Test generation from real user behavior sessions

Relicx uses generative AI to conduct visual and functional testing based on real user behavior captured from production sessions. It prioritizes the user experience in testing rather than just code coverage, generating regression suites from actual user journeys to ensure that the flows real people use most frequently are always covered by automated tests.

AI website wireframe and design generator

Generate complete website sitemaps and wireframes with AI in minutes. Relume outputs Figma and Webflow-ready component libraries, with a built-in library of 1000+ components and style guides. Ideal for designers and agencies who need to rapidly prototype client projects without starting from scratch every time.

Create videos programmatically with React

Remotion is a React framework that enables developers to create videos programmatically using familiar web technologies. Build videos as React components, leveraging CSS, Canvas, SVG, and WebGL for rendering. The framework includes Remotion Studio for browser-based preview with timeline scrubbing and fast refresh. Render locally, on servers, or via AWS Lambda for scalable video production. Ideal for automating social media content, data visualizations, and personalized marketing campaigns.

Cloud for the new default

Unified cloud platform for deploying web services, static sites, background workers, cron jobs, and managed databases with automatic scaling and zero DevOps. Auto-deploy from Git with preview environments, built-in DDoS protection, free TLS, and global CDN. Native runtimes for Node.js, Python, Go, Rust, Ruby, Elixir plus Docker. Managed PostgreSQL and Redis with daily backups, private networking, and infrastructure-as-code via Blueprints. Modern Heroku alternative with a free tier.

AI-powered production incident resolution

Resolve AI automates production incident investigation, diagnosis, and remediation acting as an AI SRE that participates in every on-call rotation. Autonomously investigates incidents pursuing multiple hypotheses in parallel, validates against real evidence, creates code snippets and drafts PRs, generates post-mortems, and onboards new teammates with instant answers about code and infrastructure. Drives 5x faster MTTR and 87% faster incident investigations.

Responsive web development tool

Open-source browser for responsive web development that shows multiple device viewports simultaneously with synchronized scrolling, clicking, and navigation. Preview your site on phone, tablet, and desktop sizes side by side in real-time. Features screenshot capture for all viewports, element inspector, network monitoring, and hot-reload support. Built on Chromium. Free alternative to Polypane for developers who need quick responsive testing without paid subscriptions. 23K+ GitHub stars.

Durable execution engine for workflows and AI agents

Restate is a durable execution engine that provides reliable workflow orchestration for AI agents and backend services. It runs as a single binary with no external dependencies, delivering sub-50ms latency and 94K+ actions per second. Supports TypeScript, Python, Go, Java, and Kotlin SDKs with built-in retries, sagas, and virtual object state. MIT licensed with 3,700+ GitHub stars.

Build internal tools remarkably fast with a visual builder and code when needed.

Retool is the leading low-code platform for building internal tools, admin panels, and dashboards. Used by 27,000+ companies including Amazon and DoorDash. Drag-and-drop UI components connect directly to databases, APIs, and services. Supports custom JavaScript and Python for complex logic. Reduces internal tool development time from weeks to hours.

Automated PR workflow with AI review and labeling

ReviewPad automates the pull request workflow by applying team-defined rules for labeling, assigning reviewers, and providing AI-powered feedback on code changes. Its open-source GitHub repository supports custom automation scripts that standardize the review cycle, making it essential for mid-to-large teams enforcing governance without sacrificing development velocity across multiple repositories.

Build modular, scalable LLM applications in Rust

Open-source Rust library for building scalable, modular, and ergonomic LLM-powered applications. Rig unifies 20+ model providers (OpenAI, Anthropic, Mistral, DeepSeek, Ollama, and more) and 10+ vector stores behind one trait-based interface, supports completion and embedding workflows, multi-turn streaming, and transcription/audio/image generation, with full GenAI Semantic Convention compatibility and WASM-ready core library — production agentic infra for Rust teams.

Visual AI agent builder by Ironclad

Rivet is an open-source visual AI programming environment and TypeScript library by Ironclad for building, debugging, and deploying AI agents through a node-based graph editor. Complex LLM prompt chains become visual networks with real-time data flow inspection at every node, team collaboration on agent graphs, and a TypeScript library for embedding finished graphs in any application. Transforms agent development from text-editing into visual engineering.

AI model validation and risk management platform

Robust Intelligence is an AI risk management platform that validates ML models for security, fairness, and reliability before and after deployment. It provides automated stress testing, bias detection, data drift monitoring, and model risk scoring for enterprise compliance. Serves Fortune 500 customers in financial services, healthcare, and insurance with continuous AI validation aligned to regulatory frameworks.

Rust-powered JavaScript bundler for Vite

Rolldown is a high-performance JavaScript and TypeScript bundler written in Rust, built as the next-generation bundler for Vite. Created by Evan You and VoidZero, it offers a Rollup-compatible plugin API with 10-30x faster builds. It combines esbuild-level speed with full Rollup ecosystem compatibility, supporting tree-shaking, code splitting, and advanced optimizations natively. With 13K+ stars and MIT license, it is set to become the default bundler for Vite 8.

Intelligent model router that balances cost and quality across LLM providers

RouteLLM by LMSYS routes LLM requests to the most cost-effective model that can handle each query's complexity. It uses learned routing models to classify whether a query needs a powerful expensive model or can be handled by a cheaper alternative, reducing costs by up to 85% while maintaining quality. Supports OpenAI, Anthropic, and other providers through an OpenAI-compatible API.

Agentic AI for software teams by Atlassian

AI-powered coding agent from Atlassian, deeply integrated with Jira, Bitbucket, and Confluence so it can validate code changes against acceptance criteria and plan multi-step development workflows aligned with team goals. Achieved 41.98% on SWE-bench full leaderboard at release. Available as both CLI and IDE integration, connecting project management and development within the Atlassian ecosystem.

Open-source AI coworker with persistent memory and tool use

Rowboat is an open-source AI coworker platform that provides persistent memory, tool use, and multi-agent orchestration in a chat-based interface. It enables teams to build AI assistants that remember context across sessions, access internal tools and databases, and coordinate specialized sub-agents for complex workflows. Over 9,300 GitHub stars.

Extremely fast Python linter and formatter written in Rust

Ruff is a Python linter and code formatter written in Rust by Astral that runs 10-100x faster than existing tools like flake8, isort, and Black. It implements over 800 lint rules from dozens of popular plugins in a single binary, handles auto-fixing for most violations, and includes a built-in formatter compatible with Black. Adopted by FastAPI, Hugging Face, Pandas, and Apache Airflow, Ruff has over 38,000 GitHub stars and processes entire codebases in milliseconds.

Cross-platform on-device AI inference SDK

RunAnywhere SDK is a production-ready toolkit for running AI models entirely on-device across iOS, macOS, Android, Web, React Native, and Flutter. It provides a unified C++ core with platform-specific bindings for LLM text generation via llama.cpp, vision-language models, Whisper speech-to-text, Piper text-to-speech, and on-device image generation. All processing stays local with zero cloud dependency, ensuring privacy and low latency for mobile and edge AI applications.