Agentic desktop IDE for designers and programmers — edit a running app visually, drive an AI agent inside the repo, and manage Git without leaving the editor.
Coding & Development AI Tools
AI assistants for programming and development. Compare features, pricing models, and use cases across the tools in this category.
Top coding & development AI tools
An open-source Mac app that gives Claude Code a real browser, a live iOS Simulator and its own git worktree per chat.
A local, keyboard-driven diff viewer built for the huge changes coding agents produce - and it remembers what you have already seen.
Write an agent as a TypeScript function and deploy it in seconds onto KVM-isolated Linux microVMs, with the loop, sessions, streaming and versioning managed for you.
Open-source inference engine that runs LLMs, vision and speech models fully on-device — no API keys, no cloud calls, from Swift to Godot.
Audit-grade fact-checking API for AI products — eight models across five stages, adversarial debate, and a full citation trail behind every verdict.
Browser panel with 70 diagnostics that names a page's stack, extracts its design tokens and scores how much of it reads as AI-generated.
An orchestration layer for Claude Code that keeps Jira, GitHub, Slack and Notion context in the agent so tasks finish without constant babysitting.
Run Claude Code, Codex or OpenCode in the cloud from a single HTTP call — no SDK, no daemon, no infrastructure on your side.
Vercel Labs' tiny open-source coding agent: a ~6MB Zig binary that cold-starts in microseconds and embeds anywhere.
An open-source layer that lets your customers describe a feature and get a working micro-app inside your product — sandboxed to their own permissions.
One API for meeting bots across Zoom, Google Meet, Teams and Webex — join, record, stream and speak in real time, billed at $0.35 an hour.
Block's open-source desktop workspace for AI agents — one native app for Goose, Claude Code, Codex, Copilot, Amp and Cursor.
Real-time mobile observability with unsampled on-device logs, session replay and AI agents that triage and investigate app issues autonomously.
Autonomous QA agents that generate, run and self-heal Playwright end-to-end and API tests on every pull request, as code you own.
Cursor's Git forge for the agentic era — host repos, review pull requests and let coding agents work in the same place.
AI review agents that QA a website against your own checklist, then route the findings for client approval.
Turns backlog tickets into reviewed pull requests — background triage, a task board wired to live agent sessions, and MCP control from your own terminal.
One API for agent harnesses — run Codex, Claude Code or Hermes behind your product with shared sessions, streaming, files and cost controls, and swap harness with a config change.
Cloud coding agents that work in isolated sandboxes, run your tests, preview the app in a browser and open a pull request you can review like any other.
Ad-supported coding agent suite — CLI, parallel desktop workspaces, cloud IDE and a prompt-to-deploy web builder, with no subscription or API key.
AI code review that builds and runs your app on every pull request, then attaches a failing test, video and repro steps to each bug it finds.
Describe a browser or mobile test in plain English and run it from your terminal — Kane CLI drives real Chrome, no selectors or test scripts required.
A shared DevOps workspace where AI agents investigate incidents and operate AWS, GCP and Kubernetes under IAM scoping, approval gates and a full audit trail.
Open-source desktop app to run, serve and fine-tune text, image, video and audio models entirely on your own machine.
Spotify's vendor-neutral workspace for running dozens of Claude Code, Codex and Gemini CLI sessions in parallel with shared context.
A coding agent tuned for latency: routes easy work to fast models, pulls only the code it needs, and fans out tool calls in parallel.
Run agent evals and private benchmarks in sandboxed cloud environments — compare Claude Code, Codex, Cursor and Copilot on the same real tasks.
An open-source proxy that sits between your coding agent and the model, compressing tool schemas, file reads and stale history to cut token bills.
A GPU-accelerated code editor written in Rust, with collaborative editing and coding agents built into the core.
Microsoft's open-source optimizer that trains an agent's SKILL.md like a model parameter — epochs, learning-rate budgets and a held-out validation gate, with frozen weights.
Meta's terminal coding agent for long-horizon work in large repositories, running the Muse Spark 1.2 model with parallel subagents and a replayable event log.
Alibaba's agentic coding platform — a desktop IDE where a lead agent dispatches specialist sub-agents, backed by an auto-generated wiki of your repository.
Open-source AI agent from the Agentic AI Foundation — a native desktop app, CLI and API that runs tasks locally with 70+ MCP extensions.
Free, open-source local MCP gateway: register each server once, share it with every AI client, and cut tool-definition tokens by up to 91%.
Agentic IDE that runs coding agents, self-healing QA tests and production monitoring in one workspace so fixes reach a PR automatically.
An AI on-call agent that drops read-only probes into running production code, capturing live variable snapshots and stack context without a redeploy or a restart.
A hosted LLM gateway from ngrok: one base URL and one key for public providers, your own keys and self-hosted models, with failover, scoped access and cost analytics.
Cloud-hosted long-horizon AI agents: pick a harness like Claude Code or Codex, pick a model, and reach the same agent from Slack, WhatsApp, iMessage, the web or a CLI.
Kube-DC.cloud is a fixed-price Kubernetes cloud for developers - with VMs, containers, managed databases, observability, backups, and unlimited traffic included.
A browser canvas where Claude Code, Codex, Kimi and other coding agents work the same repository at once without overwriting each other.
A shared memory layer for AI coding tools — tell Claude Code something once and Cursor, Codex and Claude Desktop already know it.
Free, open-source macOS menu bar app that shows live status for every parallel Codex task, so you can see which agent needs you without reopening Codex.
Watch and approve Claude Code, Codex and OpenCode sessions running on your Mac from an iPhone, with live transcripts and push notifications.
Local-first memory hub that reads your existing AI chat history and gives every agent you use the same long-term context.
Free, fully on-device voice loop for AI coding agents — talk to Claude Code, Cursor or Codex and hear them answer back out loud.
Open-source, repo-native project memory for coding agents, stored as plain Markdown.
OpenHands — the leading open-source coding agent platform, self-hostable or run in the cloud.
Agent observability and evaluation that scores every production run for quality, drift and risk — and can pause or block a risky action before it executes.
Reviews every pull request against your product specs, catching business-logic, compliance and scope drift that code review alone misses.
Database and application server in one, pitched as a glue-free backend an AI agent can build end to end.
Reactive TypeScript backend platform built so AI coding agents can ship features without breaking things.
Minimal, MIT-licensed terminal coding agent that adapts to your workflow via TypeScript extensions.
Describe a Chrome extension in plain English and get a store-ready Manifest V3 build.
One API and one bill for hundreds of language models, with automatic failover between providers.
The open-source AI hub: over a million models, hundreds of thousands of datasets, and hosted demo Spaces.
Google's browser workbench for prototyping with Gemini models, then shipping the same prompt as production API code.
An open-source coding agent for VS Code and JetBrains that plans before it edits and asks before it acts.
Anthropic's agentic coding tool — a terminal-native agent that reads your codebase, edits files, runs tests, and opens PRs.
AWS's spec-driven IDE: prompts become requirements, design docs, and tracked tasks before any code is generated.
A memory layer for AI agents — remember user preferences and past interactions without stuffing the context window.
Secure cloud sandboxes where AI agents can run untrusted code safely, starting in milliseconds.
Production inference for open and custom models — fast, autoscaling, and deployable into your own cloud.
Serverless GPUs from a Python decorator — deploy models and batch jobs with no containers or cluster to manage.
Document parsing and retrieval built for agents — turn messy PDFs into structured, queryable context.
The framework and observability platform most teams use to build, debug, and ship LLM agents.
AI copilot for technical design — generate architecture diagrams, sequence diagrams, and ERDs from prompts or code.
An open-source terminal coding agent that works with any model and shares sessions across devices.
Sourcegraph's frontier coding agent for the terminal and editor, built to use the strongest models without limits.
Describe an app in plain language and get a working full-stack product — database, auth, and hosting included.
Cursor's automated PR reviewer, tuned to find genuine logic bugs with a low false-positive rate.
Code integrity tooling — AI review, test generation, and an agentic IDE assistant grounded in your repository.
Stacked pull requests plus AI review — a workflow built around small, fast-moving changes.
Code review that reads your entire codebase, so it catches the bugs a diff-only reviewer cannot see.
AI pull request review that leaves line-by-line comments, suggests fixes, and learns your team's preferences.
AI pair programming in your terminal, with git-aware edits and a sensible commit for every change.
Agent-native software development: Droids that plan, code, review, and ship across your existing toolchain.
A coding agent built for very large codebases, with a context engine that indexes millions of lines.
Google's agent-first development platform, where you manage a fleet of coding agents across editor, terminal, and browser.
An AI-native IDE with a builder mode that takes a project from prompt to running application.
Google's asynchronous coding agent: hand it a GitHub issue, walk away, and come back to a reviewed pull request.
A self-hosted, feature-rich chat interface that puts a polished front end on Ollama and any OpenAI-compatible API.
An open-source, offline-first ChatGPT alternative that runs models on your own computer.
Inference, fine-tuning, and GPU clusters for open models — the full stack for teams building on open weights.
Run thousands of open models with one API call, and deploy your own without touching Kubernetes.
A polished desktop app for discovering, running, and chatting with local language models — no terminal required.
Run open language models on your own machine with a single command — no cloud, no API key, no data leaving the laptop.
Inference on custom LPU hardware, built for latency — open models served at speeds general-purpose GPUs struggle to match.
Continuous automated QA for voice and chat AI agents, from pre-launch simulation to live call monitoring.
Open-source GUI coding agent whose sessions are branching, resumable documents instead of a linear chat transcript.
Build real native Mac apps by describing them to an AI agent — local-first, offline, and yours to keep.
A free, local, open-source AI app builder that runs on your own machine — a privacy-first alternative to v0, Lovable, and Bolt with no vendor lock-in and bring-your-own API keys.
v0 converts natural language descriptions into code and UI. Build landing pages, full-stack apps, and more.
Everything you need, right where you code
The AI visual builder for Next.js & Tailwind
Lovable is an AI-powered platform designed to enable users, regardless of their coding expertise, to build full-stack web applications quickly using natural language prompts.
Windsurf is an AI-powered IDE designed to keep developers in a "flow state" by deeply integrating artificial intelligence into the coding process.
Cursor is an AI-powered IDE built to significantly speed up software development.
Bolt.new is an AI-powered tool that helps you build complete web applications directly in your web browser.
Stenography explains code and APIs with AI.
Mintlify AI helps generate and maintain documentation.
Pieces organizes code snippets and context with AI.
Supermaven is a blazing-fast AI code completion tool.
Continue is an open-source copilot for VS Code and JetBrains.
GitLab Duo brings AI to the DevSecOps platform.
CodeWhisperer suggests code in real time.
AI Assistant integrates deeply with JetBrains IDEs.
Codeium provides AI autocomplete and chat for developers.
Cody is a powerful AI coding assistant by Sourcegraph.
An agentic terminal and development environment where you drive coding and DevOps tasks in natural language.
An autonomous AI software engineer that plans, writes, tests, and ships code in its own cloud development environment.
Browser-based coding platform whose AI Agent builds, edits, and deploys full-stack apps from natural-language prompts.
Free, local, open-source AI app builder ✨ v0 / lovable / Bolt alternative
CodeWP is an AI code assistant for WordPress.
Highly personalized AI that fits how you work · Context-aware suggestions based on your code and patterns