Coding & Development
87 tools in the n3os directory.
Mermaid Online
Mermaid Online is a free browser editor for Mermaid diagrams, with live preview, templates and SVG or PNG export, plus paid credits for AI-made diagrams.
Glow Security
Glow Security is an endpoint platform that inventories and controls every piece of software running across a fleet, not only what an agent looks for.
Arcade
Arcade provides the layer between an agent and the tools it calls: a catalogue of integrations, built-in OAuth to act for a user, and observability.
Curie
Curie applies generative AI to enterprise IT engineering, positioned around raising productivity for internal technology teams.
Tessl
Spec-driven AI development from Snyk founder Guy Podjarny: write what the software must do, and the specification stays the source of truth.
Galileo
Galileo tests, monitors and guardrails generative AI applications: evaluations before release, tracing in production and blocking output at runtime.
Manufact
An open-source SDK and zero-config hosting for Model Context Protocol servers, so an MCP tool is a deploy rather than an infrastructure project.
StrongestLayer
StrongestLayer analyses email with several language models to judge intent and business context, targeting phishing and business email compromise.
Reflex
Reflex is an open-source Python framework for building web applications without writing JavaScript. You define the interface and the logic in Python.
Gray Swan AI
Gray Swan AI builds Cygnal for automated red-teaming and Shade for jailbreak defence. Founded by Carnegie Mellon researchers, it works with frontier labs.
Starseer
Starseer is an AI security and interpretability platform. It scans models you did not train for vulnerabilities, then monitors activations at runtime.
WorkOS
WorkOS provides enterprise-readiness features — single sign-on, SCIM directory sync, audit logs, user management — through a small set of APIs.
Graphite
Graphite combines a stacked pull request workflow, a chain of small dependent PRs, with Diamond, an AI reviewer that comments before a human does.
DSPy
DSPy is an open-source framework from Stanford that treats model interactions as programmable modules, with optimisers that generate and refine prompts.
vFunction
vFunction analyses running applications to expose their real architecture, what depends on what, and tracks how that structure drifts over time.
Zencoder
Zencoder plans, writes, tests and reviews code across VS Code, JetBrains IDEs, a command line and a web app, working across multiple frontier models.
Revenium
Revenium meters AI spend in real time across models, agents, providers and tools, and attributes cost to the feature, customer or team that caused it.
Figma Make
by Figma
Figma Make turns a prompt, or an existing Figma frame, into an interactive working web app that you can iterate on, share and ship.
8090
8090 is a software development platform that turns plain-English business intent into production code, with humans and AI agents in one governed workspace.
Horizon3.ai
Horizon3.ai runs NodeZero, an engine that continuously executes real attack techniques against production environments to find exploitable weaknesses.
Adaptive Security
Adaptive Security simulates AI-powered social engineering, such as deepfake voice calls and SMS phishing, against a company's staff, then trains them.
Prophet Security
Prophet Security automates the investigation stage of security operations: taking alerts, gathering context and presenting analysts with a conclusion.
Picsellia
Picsellia covers the lifecycle of a computer vision project: managing and versioning image datasets, tracking experiments and deploying models.
WitnessAI
WitnessAI sits between users and language models, showing which AI tools employees use and what is sent to them, and enforcing policy on that traffic.
Virtue AI
Virtue AI is a security and compliance platform for enterprise AI, pairing an automated red-teaming engine with a real-time filter for output.
Arthur
Arthur monitors machine learning models in production: performance, data drift, bias and fairness metrics, and explainability for individual predictions.
Temporal
Temporal runs long-lived workflows reliably. You write the logic as ordinary code and it records every step, so a process survives crashes and outages.
Freeplay
Freeplay covers prompt management, batch evaluation, experiments and production monitoring for teams shipping AI features.
Daily
Daily provides APIs and SDKs for building real-time voice and video into applications, handling the underlying WebRTC infrastructure as a service.
baro
by jigjoy
baro runs autonomous coding agents in parallel on your repository. You state a goal and it produces a branch, a diff and a pull request. It is free.
Magic Patterns
Magic Patterns generates React components from natural-language prompts or from pasted images — a screenshot, a mockup, a competitor's page.
Anima
Anima turns Figma files into front-end code in React, Vue or plain HTML and CSS, with recent AI work aimed at cleaner and more component-like output.
Traversal
Traversal is an AI site reliability agent that investigates production incidents, using causal machine learning to find the change that broke something.
Versoly
Versoly builds landing pages and CMS-driven sites without code from a library of design blocks, with an emphasis on page speed and SEO for SaaS sites.
Payload CMS
Payload is a headless CMS and application framework built with TypeScript and React. You define collections in code. It is open source and self-hostable.
Resolve AI
Resolve AI connects to observability data, logs, traces and source code, then works through them when an alert fires to propose a likely root cause.
MCP360
MCP360 is a gateway and marketplace for the Model Context Protocol. You point any MCP client at a single connection and get the whole catalogue of tools.
Distributional
Tests AI applications by watching the distribution of their behaviour over time, rather than checking individual outputs against expected answers.
Future AGI
Future AGI is a platform for finding out whether an LLM application works, bundling simulation, evaluation, tracing and guardrails. It is self-hostable.
TensorFlow
by Google
TensorFlow is an end-to-end open-source machine learning platform for building and training models, deploying to mobile, browsers and production pipelines.
Sourcegraph
Sourcegraph indexes an organisation's code and lets you search it as one body - by pattern, by symbol, or in natural language - then act on what you find.
Cognition
Cognition operates Devin, an agent that takes an engineering task end to end, planning, writing code and opening a change in an existing codebase.
Webflow
Webflow builds websites visually while producing real HTML and CSS, with a CMS for structured content, hosting, localisation and team permissions.
Retool
Retool assembles internal applications from prebuilt components wired directly to your databases, APIs and model providers.
Elementor
Elementor is a drag-and-drop builder for WordPress. It edits pages visually, generates whole pages from a prompt and builds WooCommerce stores.
Draftbit
Draftbit builds native iOS, Android and web apps through a drag-and-drop editor with a live preview, backed by React Native.
Bubble
Bubble builds complete web and mobile applications without code, with its own database, visual workflow logic, per-record privacy rules and hosting.
Softr
Softr builds portals and internal applications on top of data you already have, such as Airtable or Google Sheets, with user accounts and permissions.
Keras
Keras is a high-level deep learning API. Since version 3 it runs on TensorFlow, PyTorch or JAX as the backend, so the same model code is portable.
Ray
by Anyscale
Ray is an open-source framework for distributed computing in Python. It runs training, data processing and model serving across a cluster of machines.
FlutterFlow
FlutterFlow builds applications visually on top of Flutter and produces genuine Flutter source you can download, extend and publish to the app stores.
OpenAI Codex
by OpenAI
Codex is OpenAI's coding agent. You describe a task and it plans, edits across files, runs the code and comes back with a change to review.
Relume
Relume is a library of marketing-site components designed by people rather than generated, plus a builder that assembles them into complete pages.
Roboflow
Roboflow covers computer vision end to end: labelling images with AI assistance, managing datasets, hosted training and deployment to a device or an API.
Augment Code
Augment Code runs coding agents that review pull requests, raise test coverage and handle migrations, on a context engine that indexes an entire codebase.
Visual Studio Code
Visual Studio Code is a free, open-source code editor from Microsoft. It is the editor most AI coding assistants plug into, and has AI features of its own.
OpenCode
OpenCode is an open-source coding agent that runs in the terminal. It reads a project, plans and makes multi-file changes. You bring your own model key.
Claude Code
by Anthropic
Claude Code is Anthropic's coding agent. It runs in your terminal and also in an editor extension and a desktop app.
Playcode
Playcode builds working applications from a description and runs them on its own infrastructure, providing the database, hosting and file storage.
Snyk
Snyk finds security problems in software. It scans dependencies for known vulnerabilities, checks your code for insecure patterns and examines containers.
CodeRabbit
CodeRabbit reviews pull requests automatically. It reads the diff, comments line by line with suggested changes, and summarises the pull request.
Qodo
Qodo is a code quality platform built around review and testing. It generates tests for existing code, reviews pull requests and applies your standards.
Devin
by Cognition
Devin is an autonomous coding agent. You assign it a task and it works in its own environment, planning, running code and producing a pull request.
Kilo
Kilo is an open-source coding agent that runs in an editor, from the command line or in the cloud. It plans and carries out multi-file changes.
Kiro
Kiro is an AI development environment built around specifications. You work from a written spec, which it turns into tasks and then into code.
Pieces
Pieces saves and organises the fragments of a developer's day: code snippets, links, terminal output and screenshots.
Aider
Aider is an open-source AI pair programmer that runs in the terminal and edits files in your git repository, committing each change so you can undo it.
Cline
Cline is an open-source coding agent that runs inside VS Code. It plans a change, edits files and runs commands, showing each step for approval.
Zed
Zed is a code editor written in Rust for speed. It handles very large files, supports real-time collaborative editing and builds in AI agent work.
Greptile
Greptile indexes a whole codebase so questions can be asked about it in plain language, and reviews pull requests with knowledge of the surrounding code.
Supermaven
Supermaven is a code completion tool built for speed and a very large context window, so its suggestions take account of more of your codebase.
Tabby
Tabby is a self-hosted coding assistant. You run it on your own hardware and it serves completion and chat to editors across your network. Open source.
Continue
Continue is an open-source assistant for VS Code and JetBrains. It provides completion, chat and in-editor editing, with your choice of model for each.
Bolt.new
Bolt.new builds working web applications from a description, in the browser. It writes the code, runs it in a live preview and can deploy the result.
Firebase Studio
Firebase Studio is a browser-based workspace for building full-stack applications, with AI help for code and direct connections to Firebase services.
GitHub Copilot
by GitHub
GitHub Copilot is an AI assistant for writing code. It works inside editors like VS Code, suggesting the next lines as you type, with a chat panel.
Lovable
Lovable builds web applications from a description in a chat. It generates the interface, wires up a database and authentication, and can publish it.
Devin Desktop
Devin Desktop is an agent-native code editor from Cognition, previously known as Windsurf. It combines editing with agents that make multi-file changes.
Warp
Warp is a terminal that behaves like a modern application. Commands and output are grouped into blocks you can search, and AI explains commands.
Replit
Replit is a coding environment that runs entirely in the browser, with an editor, terminal, hosting and an AI agent that builds an app from a description.
Cronlet
Cronlet is a scheduling service for AI agents. An agent creates its own recurring tasks in plain language and receives a callback with the result.
JetBrains AI
JetBrains AI is the assistant built into JetBrains editors such as IntelliJ and PyCharm. It offers completion, chat, test generation and agent work.
Cody
Cody is Sourcegraph's coding assistant. It answers questions, writes code and explains unfamiliar code, using context from the entire repository.
Tabnine
Tabnine is a coding assistant with completion, chat and agents across most editors. It can be deployed privately and is explicit about its training data.
Amazon Q Developer
Amazon Q Developer is AWS's coding assistant. It completes code in your editor, answers questions about a codebase and runs as an agent for larger changes.
v0
by Vercel
v0 is Vercel's interface generator. Describe a screen or paste a screenshot and it returns working React components styled with Tailwind and shadcn/ui.
Cursor
Cursor is a code editor with an AI assistant built into it. It is a fork of VS Code, and it can answer questions about a file or edit several at once.