AI tool directory

Anthropic's agentic coding tool — understands your codebase, edits files, runs commands, and helps you ship faster.

An AI coding agent for building ambitious software — agents turn ideas into code so you can hand off tasks.

A unified TypeScript SDK for building AI apps with modern streaming, fallbacks, and multi-model support.

Create lifelike speech with an AI voice generator and voice agents platform — 5,000+ voices in 90+ languages with APIs and SDKs.

OpenAI's coding agent across ChatGPT, your editor, and the terminal — runs many agents in parallel and keeps going in the cloud.

Build production-grade applications with a Postgres database, Authentication, instant APIs, Realtime, Functions, Storage and Vector embeddings.

Chat to build websites and web apps — an AI software engineer that lets anyone build for the web with no technical knowledge needed.

Agentic infrastructure — the autonomous stack for every app and agent.

Deploy serverless functions globally in seconds — no cold starts, 330+ cities, pay only for CPU time.

Pull up-to-date, version-specific documentation and code examples for any library directly into Cursor, Claude Code, Codex and other AI coding tools.

The reactive backend platform that keeps up with you and your agents.

Black Forest Labs' FLUX models for image generation and editing, available via API, in-browser playground, and open weights you can run and fine-tune on your own infrastructure.

Works every step of the way, from an open issue to reviewing and merging a pull request — in your editor, terminal, desktop, and on GitHub.

Design guidance for AI coding agents: one skill with 24 commands (polish, audit, critique, distill and more), live browser iteration, and 62 deterministic detector rules that flag AI-generated design tells.

Postgres backends for apps and agents: Lakebase Postgres, Auth, Functions, Storage, and an AI Gateway — instant, branchable, serverless.

The open source AI coding agent — write code in your terminal, IDE, or desktop with free models included or any provider.

Describe what you want. Replit builds it. Get a working app or website in minutes. No coding required.

AI image and video generation and editing, built on Runway’s foundation models for creators and teams.

Your collaborative AI assistant to design, iterate, and scale full-stack applications for the web.

Voice AI platform with speech-to-text (pre-recorded and realtime), speech understanding, an LLM gateway and now text-to-speech — models, APIs and infrastructure to build voice into any product, including voice agents.

Build and scale high-performing websites & apps using your words.

Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows.

Manage fleets of local and cloud agents from one surface. Plan, delegate, review, and ship without leaving your editor.

Search the largest index of public web and private information: search, contents, deep research and monitoring APIs built for AI agents.

Google's developer API for its Gemini models, now led by Gemini 4 Argon, a flagship reasoning model with a 1M-token context window and decodes up to 1M tokens, alongside Flash, Live (voice), TTS, Nano Banana image and video models. Usable from Google AI Studio.

An AI research tool and thinking partner that analyzes your sources and turns complexity into clarity.

AI video and image generator from Kuaishou, with Kling 4.0 video, Kling Image 3.0, an agent-driven Canvas, and MCP/CLI access for batch generation.

Creative AI suite to generate, edit, and enhance images and videos — including Krea's own models (Krea 2, Krea 3) plus third-party image, video and 3D models in one app.

Agent orchestration framework: durable execution, memory, streaming, and human-in-the-loop.

Mistral's flagship open-weight model ('Le Chonk'): a 1-trillion-parameter natively multimodal Mixture-of-Experts model (about 52B active) with a 1M-token context, built for agentic coding and defensive cybersecurity, with low/medium/high reasoning modes. Weights on Hugging Face; also served on the Mistral API as mistral-large-4.

Create with AI or code, deploy instantly on production infrastructure. One platform to build and ship.

A lightweight framework for building agentic apps with agents, tools, handoffs, guardrails, sessions and tracing.

A full-stack cloud for deploying web apps, servers, databases, and more with automatic scaling, monitoring, and security.

Build, test, and deploy advanced voice AI agents in minutes — the platform for developers creating conversational voice AI.

A coding-agent skill that turns your agent into a security auditor, orchestrating isolated agents through reconnaissance, coverage-led hunting, candidate validation, independent verification and reporting. It seeded Cloudflare's own vulnerability discovery harness.

Low-cost API for DeepSeek's models (OpenAI- and Anthropic-compatible) plus standalone Search and Fetch APIs that give agents live web content.

Factory's model-independent coding agent for planning, building, reviewing and shipping software across desktop, terminal (CLI), web and SDK, with cloud and local background agents, an auto model router and PR code review.

Turn ideas into reality with AI-powered design tools — generate, iterate, and build faster, all in one creative space.

Google’s mobile and web app development platform that helps developers build apps and games users love.

Expressive, emotionally controllable text-to-speech and voice cloning, with speech-to-text, voice agents, a 2M+ voice library and developer APIs.

Open-source GitHub Next project: write agent automations in Markdown and compile them to GitHub Actions so Copilot, Claude, Codex or another coding agent can triage issues, investigate CI failures, update docs and open pull requests, with guardrails.

AI image generation known for strong text rendering — great for logos, posters and marketing assets.

Moonshot AI's assistant, coding agent (Kimi Code) and API, now powered by K3.1 Pro: a 3T-class open-weight model with a 1M-token context, strong at coding, game/3D creation and agentic work.

Turn prompts into executable specs, validate code correctness, and build across large codebases with parallel agents.

Open-source headless browser built from scratch in Zig for automation, crawling and AI agents: runs JavaScript with no graphical rendering, plugs into Puppeteer and Playwright over CDP, and includes MCP and agent modes. Self-host it or use Lightpanda Cloud.

Ship AI agents that reason, remember, and act in TypeScript — memory, tools, MCP, and observability from prototype to production.

The documentation platform for agents: self-updating documentation for startups, enterprises, and agents.

Mistral's speech-to-text and text-to-speech models plus a voice agent SDK that combines listening, reasoning, tool calling and speaking in one real-time pipeline, in 50+ languages.

The safe, private runtime for fleets of autonomous AI agents: each agent runs in an isolated sandbox with kernel-level policy enforcement on files, syscalls and network, and credentials are injected only for approved endpoints.

The agent development environment: run Claude Code, Codex and other coding agents in parallel, each in its own worktree, with terminals, diffs, a browser and a CLI in one app.

NVIDIA's open-source security scanner for AI agent skills: checks a repo, URL, zip or folder against 71 vulnerability patterns (prompt injection, data exfiltration, MCP tool poisoning and more) and gives a 0-100 risk score before you install a skill.

The open-source control plane for coding agents: orchestrate Claude Code, Codex, Cursor, OpenCode, Grok and Antigravity from one desktop, web and mobile app, using your own subscriptions.

A high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

A no-code AI development platform that turns builders’ ideas into fully functional apps and websites — no coding required.

Open-source, local-first memory and telemetry layer for coding agents: captures sessions across Claude Code, Cursor, Codex, OpenCode and 20+ harnesses and turns reviewed lessons into reusable skills via MCP or Agent Skills.

A design skill for Claude Code, Codex, Cursor and OpenCode that refuses to look AI-generated: it deals themes from a catalog of 48, lays out the page around what visitors came to do, and lints the result in a real browser for AI-slop tells.

MiniMax's developer platform for its language, video, speech and music models, with OpenAI- and Anthropic-compatible endpoints.

Open-source managed agent platform: one API to deploy and run durable agents on any model and any machine, with tools, secrets, permissions and streaming built in. A self-hostable alternative to Claude Managed Agents.

The leading AI models in one place for creative production and game assets — image, video, 3D and audio pipelines.

Open-source, fully local voice studio: voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation in 646 languages.

AI pair programming in your terminal — pair program with LLMs to start a new project or build on your existing codebase.

The leading multi-agent platform — an enterprise agent build & runtime for business and technical teams.

Google DeepMind's real-time world model: create an interactive world from text or images, walk around it with keyboard controls, and steer it live with prompts (change the weather, move the camera, add characters), with native audio including music and reactive dialogue.

A native, open-source home for Claude Code, Codex and any terminal coding agent: spaces per repo, tabs per task, a sidebar showing which agent needs you, agents that start and steer helper agents, and remote machines over SSH. Agents keep running in herdr-core when the window closes, and the whole UI is plain files your agent can rewrite.

Diffusion-based LLMs that generate many tokens in parallel for very low latency; Mercury 3 runs at 1,000+ tokens per second with a 1M-token context.

Meituan's new flagship model for long-horizon agentic tasks: a 1.6-trillion-parameter MoE (about 48B active per token) with native visual understanding and stronger agentic coding, served on the LongCat API Platform with OpenAI- and Anthropic-compatible endpoints and a 1M-token context.

The open standard for generative UI — lets AI agents respond with charts, forms, cards and dashboards built from your own components, in React, Vue, Svelte and more.

A cross-platform AI app builder for iOS, Android & web — publish to the App Store & Google Play in hours.

JetBrains' open-source agentic IDE built around the pi coding agent: every task gets its own git-worktree workspace, with Monaco editor tabs, terminals, diffs, and a living spec graph the agent reads and maintains.

Your AI agent for turning ideas into apps — build sites, apps, tools, products and more just by describing what you want.

AI-native video editor that edits a real timeline while you watch: ask in plain words, edit the transcript like a document, press Tab to accept suggested next edits, or connect it to Claude, ChatGPT or Grok and edit from the chat.

Autonomous backend for AI coding agents: your agent builds Postgres, auth, storage, functions and realtime over MCP, then a self-healing loop fixes what it can verify and undo and holds anything risky for your approval.

"A production before production": rebuilds your whole app on its own machines, grows production state at 4,000x speed, lets synthetic users and agents use it, and hands back reproducible bugs with traces and draft fix PRs.

Free, open-source CLI and GitHub Action that tells whoever approves a pull request how risky the merge is (fast track, quick or careful review, plus a 0-100 score) and which files carry the risk, using static analysis rather than an LLM.

Build real apps from inside Claude, ChatGPT or Cursor: add Floot as a connector, describe what you want, and it builds the whole app with backend, database, user logins and hosting, then publishes it to the web and app stores. No git, terminal or build credits. Backed by Y Combinator.

Free, open-source desktop app that runs AI entirely on your own computer: it picks the best open-weight model your machine can handle (Qwen, Gemma, GPT-OSS), then reads and edits your files, runs code in a sandbox, draws charts and fills in PDFs, offline.

Liquid AI's family of six open-weight 2B-class models (text, vision, audio, omni and two 'decision' models) on one shared backbone, built to run on phones and laptops and to be fine-tuned on a single GPU. The text model has a 256K context and native tool calling and fits in about 1 GB at 4-bit.

Open-source sandbox that runs coding agents (Claude Code, Codex, Gemini CLI, opencode, Aider or any command) in a Linux micro-VM on a copy-on-write clone of your project with network limited to hosts you allow, then lets you review and apply the changes like a pull request.

Open-weight mixture-of-experts coding model (40B total, ~2.5B active) built for fast agentic coding on local hardware; plugs into OpenCode, Pi, Cline and OpenHands.

Create playable games with AI prompts — describe your idea or choose a template, then build and deploy your game.

Sandboxed Platform for Agentic Code Execution: open-source sandboxes that run agent and user code in isolated Firecracker microVMs, managed over an HTTP API.

Stitch generates UIs for mobile and web applications, making design ideation fast and easy.

Persistent memory for coding agents: captures what your agent does during sessions, compresses it with AI and injects relevant context into future sessions. Installs with npx claude-mem install for Claude Code, plus OpenCode, T3 Code, Codex, Antigravity CLI, OpenClaw and more.

A tmux-style terminal multiplexer built for running coding agents: see which of your Claude Code, Codex, Pi or OpenCode sessions are working or need you, track token use, and review every file each agent touched.

Lightweight open-source coding and automation agent in one CLI binary for macOS, Linux and Windows: run it locally or over SSH, cut token use with a decision model, and automate CI and cron jobs with durable, resumable workflows.

Prompt-to-game builder: describe a game, vibe code it in the browser with no coding, play it on your phone, remix community games, and add multiplayer, in-app purchases and ads to monetize.

A Git hook for agent-assisted development: before your agent's code ships, it quizzes you on what that code actually does.

Turns a coding-agent session into one shareable link (prompts, every step, what broke, what fixed it and the diff) that people can read and other agents can pull to continue where it ended.