All AI Tools

AI assistant by OpenAI for text generation, coding, data analysis and more

AI assistant by Anthropic, excels at long-context understanding and safe conversation

Google's multimodal AI model for text, image, and code understanding

AI assistant by xAI with real-time X integration, strong reasoning and live search

Open-source LLM by DeepSeek with strong reasoning capabilities and excellent cost efficiency

Alibaba Cloud's LLM supporting multilingual, long-context, and multimodal understanding

Baidu's AI assistant powered by ERNIE LLM, integrating chat, search, and creation

ByteDance's AI assistant powered by Doubao LLM for intelligent conversation and creation

Zhipu AI's chatbot based on GLM model, supporting bilingual Chinese-English and code generation

Moonshot AI's assistant known for ultra-long context processing capabilities

Tencent's AI assistant based on Hunyuan LLM, deeply integrated with WeChat ecosystem

Top-tier AI image generation tool known for artistic style and quality

OpenAI's image generation model, accessible through ChatGPT

Open-source AI image generation model with rich community ecosystem

AI coding assistant integrated in VS Code for real-time code completion

AI-native code editor with multi-model support, redefining programming experience

AI search engine providing real-time answers with cited sources

Built-in AI writing assistant in Notion for summarizing, translating, and generating content

Enterprise AI marketing content platform with brand voice customization

AI video generation and editing tool, supports text-to-video and video editing

Leading AI voice synthesis and cloning platform with multi-language support

AI music generation tool that creates complete songs from text descriptions

Largest open-source AI model community for hosting, training and deploying models

Open-source framework for building LLM-powered applications quickly

AI frontend code generator that creates React components from natural language

AI-powered workflow automation platform connecting 5000+ apps

The early autonomous-agent phenomenon, now rebuilt as a low-code AI agent workflow platform (AutoGPT Platform)

Started as AI copywriting, now a GTM AI platform automating sales and marketing workflows end to end

AI video and podcast editor that edits video like a document

Online AI coding platform with integrated code generation, debugging and deployment

Built-in AI design assistant in Canva for generating posters, presentations and more

AI image generation platform focused on game assets and creative design materials

AI video generation tool supporting text/image to video with simple operation

World-leading AI translation tool with superior translation quality

AI code completion tool supporting multiple IDEs with code privacy focus

Platform for creating and chatting with AI characters with custom personalities

OpenAI's open-source speech recognition model for multi-language speech-to-text

Meta's open-source LLM series, deployable locally with commercial use allowed

Cross-platform AI agent by Nous Research with unified memory across Telegram, Discord, Slack and more

ByteDance's AI image and video creation platform (China version), deeply integrated with Jianying ecosystem for text-to-image and text-to-video creation

Kuaishou's AI video and image generation platform with bilingual CN/EN support

AI code editor (rebranded as Devin Desktop by Cognition in 2026) with Cascade agent that deeply understands your codebase

OpenAI's former AI video generation model, discontinued in April 2026

Europe's leading open-source LLM company, Le Chat product, Mistral Large 3 excels in multilingual tasks

Open-source platform for running LLMs locally, run hundreds of models like Llama, DeepSeek, Qwen with one command

Browser-based full-stack AI dev platform by StackBlitz, generates complete web apps from natural language with one-click deploy

AI avatar video platform supporting 100+ languages for virtual presenter videos, ideal for enterprise marketing and training

Google's free AI development platform to explore and call Gemini and other latest models with API integration

Enterprise AI platform specializing in RAG, embeddings and conversational models, Command R+ excels in multilingual

Chinese AI company with Hailuo AI chat product, excels in speech synthesis and long-context processing

AI image generation tool known for precise text rendering, excels at posters and logo design with text

AI search engine for developers that provides direct technical answers with code examples, more efficient than traditional search

Built-in AI design features in Figma including one-click prototyping, auto layout, smart layer renaming and more

AI assistant by iFlytek powered by Spark X2 LLM, supporting 130+ languages with fully domestic computing power

AI chat and search assistant by Kunlun, integrating LLM with real-time search engine, supporting multimodal interaction

Open-source LLM series by 01.AI (founded by Kai-Fu Lee), Yi-Lightning offers fast inference and excellent multilingual capabilities

LLM by Baichuan AI (founded by Wang Xiaochuan), excelling in vertical domains like healthcare and finance, open-source available

AI chatbot by SenseTime powered by SenseNova LLM, with strong multimodal understanding and image generation capabilities

LLM startup founded by former Microsoft VP, Step series models excel in multimodal and long-context processing

AI chatbot by 360, combining security capabilities with LLM technology, supporting multi-turn conversation and long-context processing

Meta's AI chat product powered by Llama 4 LLM, supporting text and image understanding and generation, open-source and free

Microsoft's small yet powerful LLM, 14B parameters with performance rivaling much larger models, deployable locally and on cloud

AWS's LLM series covering Micro, Lite, Pro tiers, deeply integrated with AWS ecosystem, ideal for enterprise applications

Xiaomi's AI LLM, MiMo on-device model runs efficiently on smartphones, supporting AI assistant and various AI scenarios

Adobe's AI image generator deeply integrated with Creative Cloud, commercially safe

Open-source AI image generation model by Black Forest Labs with exceptional image quality, supports local deployment

Google DeepMind's AI video generation model with high-fidelity text-to-video and realistic physics simulation

Luma AI's video generation tool creating high-quality videos from text and images with realistic physics

AI video generation tool by Shengshu Technology, supporting text-to-video and image-to-video, China's original video LLM

AI music generation tool that creates complete songs from text prompts, supporting various music genres

Anthropic's AI coding assistant for terminal, supporting code generation, debugging, and refactoring

AI full-stack web app builder that creates complete applications from natural language with one-click deployment

Open-source LLM app development platform with AI workflows, RAG pipelines, agent capabilities and model management

ByteDance's AI bot development platform with custom plugins, knowledge base, workflows, one-click multi-channel publishing

General-purpose AI agent platform that autonomously completes complex tasks like data analysis, resume screening, travel planning

Ultra-fast AI inference platform with LPU architecture for millisecond responses, supporting Llama, Mixtral and other open models

Unified AI model API gateway, access 200+ models through a single interface with pay-as-you-go pricing and model comparison

OpenAI's AI coding agent desktop app (macOS), supporting multi-agent parallel collaboration, code generation, PR management, code review, also available as CLI

AI coding assistant supporting code generation, debugging, and project management with intelligent development experience

Qoder Chinese version, AI coding assistant optimized for Chinese developers with Chinese language interaction and localized development experience

Open-source personal AI assistant that runs on your own devices. Supports AI automation and task execution across WhatsApp, Telegram, Discord, and 12+ platforms

Tencent Cloud's full-scenario AI office workbench (International), with multi-agent parallel collaboration for document processing, data analysis, content creation and more

Tencent Cloud's full-scenario AI office workbench (China version), with multi-agent parallel work for document processing, data analysis, content creation, deeply integrated with Tencent ecosystem

ByteDance's AI video generation platform (International version), the international version of Jimeng AI, supporting high-fidelity text-to-video and image-to-video with realistic physics simulation

ByteDance's AI bot development platform (China version), with custom plugins, knowledge base, workflows, deeply integrated with Volcano Engine ecosystem

Agentic creative studio by Tencent Design with image/video/UI/3D generation and persistent memory

AI coding agent and CLI by Moonshot AI (global), powered by Kimi K3 with up to 1M-token context, compatible with mainstream dev workflows

Kimi Code China edition by Moonshot AI, for domestic developers, with a high-performance CLI and VS Code extension powered by Kimi's latest flagship model

AI-native IDE by ByteDance (international), built on VS Code, integrating top models like Claude and GPT, generating code from natural language

ByteDance's AI-native IDE China edition, free and no VPN required, deeply integrating Doubao-1.5-pro and DeepSeek models, optimized for Chinese developers

AI coding agent by Zhipu AI (Z.ai, international), officially tuned for GLM models, embedding AI agents into planning, coding, review and shipping

ZCode China edition by Zhipu AI, officially tuned for GLM models, simple and fast, working with existing toolchains for planning, coding, review and shipping

OS-level personal AI assistant by Tencent with on-device LLMs, offering local file/image AI search, remote PC control from your phone, and one-sentence system settings

Google's Gemini image generation and editing model (codename "Nano Banana", i.e. Gemini 2.5 Flash Image), known for character consistency, natural-language editing and multi-image fusion

SenseTime's SenseNova large-model platform offering native multimodal models, image generation, code generation and chat, with API access and a developer console

Open-source AI agent desktop app supporting 50+ LLMs, browser automation, and team collaboration — the open-source Claude Cowork alternative

xAI's official terminal AI coding agent powered by Grok 4.5, with parallel sub-agents, Plan Mode, fullscreen terminal UI, and 256K context

Tencent's full-stack foundation model family covering language, image, video and 3D generation, with API access via Tencent Cloud and several open-source releases

Huawei Cloud's industry-focused foundation model family spanning NLP, CV, multimodal, prediction and scientific computing, served via ModelArts Studio for enterprises

NVIDIA's open model family with open weights, training data and recipes, optimized for agentic AI, with free NIM API playground at build.nvidia.com

IBM's enterprise-grade open model family under Apache 2.0, efficient and trustworthy, runnable locally via Hugging Face and Ollama or served through watsonx.ai

Apple's on-device LLM framework for developers: a native Swift API accessing the same model powering Apple Intelligence, with offline inference at zero cost

Autonomous AI software engineer by Cognition; parallel cloud agents complete coding tasks end-to-end, paired with the Devin Desktop IDE (formerly Windsurf)

Open-source platform for cloud coding agents by All Hands AI (formerly OpenDevin); model-agnostic, self-hostable, automates real engineering work

Open-source multi-agent orchestration framework with role-based Crews and event-driven Flows; its AMP enterprise platform is used across the Fortune 500

Open-source library and cloud service that lets AI agents control browsers: web automation, form filling, data extraction, with stealth browsers and CAPTCHA handling in the cloud

All-in-one AI workspace with a Super Agent: generate slides, docs, sheets, images and video from a prompt, plus an AI-native browser for Windows and Mac

Stateful agent orchestration framework by LangChain: graph-based workflows, durable memory and human-in-the-loop, with the LangGraph Platform for one-click deployment

Microsoft's open-source agent framework, the official successor to AutoGen and Semantic Kernel: multi-agent workflows in .NET/Python/Go with native MCP and A2A support

Type-safe Python agent framework by the Pydantic team: validated structured output, model-agnostic, deeply integrated with Logfire observability

Open-source TypeScript agent framework: agents, workflows, memory, RAG and evals in one stack, with an interactive playground and Mastra Cloud deployment

Open-source visual AI agent builder: three visual orchestrators (Assistant/Chatflow/Agentflow), drag-and-drop building, self-hosted or cloud

Agent-native software development platform: Factory Droids automate coding, testing and deployment; its droid CLI tops Terminal-Bench

Open-source on-machine AI agent from Block (now under the Linux Foundation's AAIF): desktop app + CLI + API, built in Rust, connects to 70+ extensions via MCP

AI executive assistant and agent platform: runs your inbox, calendar, meeting notes and follow-ups, reachable via iMessage/SMS, 100+ integrations

Multiplayer no-code AI agent and workflow builder: any AI model, any integration, with IT-controlled access; raised a $50M Series B led by Benchmark

Open-source AI browser automation platform (AGPL-3.0, 20K+ stars): computer vision + LLMs instead of brittle selectors, handles logins/2FA/CAPTCHAs natively

AI agent capabilities of the Make visual automation platform: transparent, controllable agents orchestrating complex workflows across 3,000+ apps

Salesforce's enterprise AI agent platform: build a digital labor force for customers and employees, deeply integrated with CRM data and business workflows

Microsoft's low-code AI agent building platform: create agents graphically or with natural language, publish to Teams/websites/M365, deeply integrated with Power Platform

Open-source AI coding agent for VS Code and CLI with Plan/Act modes, MCP marketplace, and bring-your-own-key model support; free for individuals

AI pair programming in your terminal: free and open source, model-agnostic, repo-map codebase understanding, automatic git commits, 100+ languages

Agentic Development Environment: modern terminal, multi-agent orchestration, and code editing in one app; runs Claude Code, Codex, Gemini CLI and more

Enterprise AI coding platform for large codebases with a Context Engine that structurally maps your repos; flat team pricing and SOC 2 Type II certified

Minimal open-source terminal coding agent with just 4 tools and a one-page prompt, reshaped into your own workflow via TypeScript extensions; model-agnostic and reuses your Claude/ChatGPT/Copilot subscriptions

AI image platform for professional designers with in-house V4 model, native vector generation, brand style controls, icon sets and mockups; founded by the creator of CatBoost

AI image generation and editing platform with in-house models, known for text rendering and prompt adherence; combines natural-language edits with a drag-and-drop editor, founded by an ex-Adobe/Stability AI product VP

AI graphic design platform by Mixpanel's founder, aggregating GPT Image 2, Nano Banana Pro and Seedream for template-driven logos, T-shirts and social media designs; 13M+ creators

MiniMax's AI video and image generation platform. The Hailuo 2.3 model is known for physically realistic human motion and industry-leading cost-effectiveness, supporting text-to-video and image-to-video

AIsphere's AI video generation platform (International version). The V6 model supports multi-shot storytelling, camera control and native audio; over 100 million users worldwide with rich, easy-to-use templates and effects

PixVerse China edition 'Paiwo AI', free to start and no VPN required. The V6 model powers text-to-video and image-to-video with smart lip-sync, cinematic camera moves and effect templates, available on web and mobile apps

A leading Chinese AI search engine by Metasota. Ad-free with direct answers, it auto-generates outlines, mind maps and cited sources, supports academic search and deep research modes, and offers an open API

A multilingual AI search engine by Japan's Sparticle. It searches global sources across languages with cited answers, and also generates presentations, mind maps and documents, with a generous free tier

A premium, ad-free search engine fully funded by its users. Zero tracking, customizable result ranking, and the built-in Kagi Assistant aggregates flagship LLMs; highly praised in Western tech communities

Voice generation platform from the team behind the open-source TTS star Fish Speech. Clone a voice from just 10-30 seconds of audio; the S1/S2 models deliver natural, expressive speech with commercial use and pay-as-you-go API

MiniMax's voice generation platform. The Speech model family delivers hyper-realistic TTS in 40+ languages with 10-second voice cloning, controllable emotion and sound-effect tags, and a free web trial

Leading AI avatar video platform with 230+ avatars and voiceovers in 140+ languages. Turn text into training, marketing and product videos — used by over half of the Fortune 100

Israeli AI avatar pioneer that turns a single photo into talking avatar videos. V4 Expressive Visual Agents connect to any LLM for real-time face-to-face interaction, backed by a mature API ecosystem

Developer platform for real-time conversational video AI (CVI). Its Phoenix, Raven and Sparrow models let avatars see, hear and hold face-to-face conversations — built API-first for video agents

The AI Native Cloud: serverless inference across 200+ open models (DeepSeek, Llama, Qwen and more), plus fine-tuning and GPU clusters. Pay per token with 50% off batch inference

Generative AI platform built for the fastest inference: serverless pay-per-token with zero cold starts, OpenAI/Anthropic-compatible APIs, 50% off batch inference, plus dedicated deployments and fine-tuning

The pioneer of open-source model hosting: run thousands of community and official models with one line of API, billed by the second so you only pay for what you use. Package and deploy your own models with Cog

Inference platform specialized in generative media: 1000+ image, video and voice models (FLUX, Seedream, Kling and more) behind one API. Blazing fast, pay-per-use with a free tier

Wafer-Scale Engine inference cloud often benchmarked as the world's fastest — an OpenAI-compatible API serving open models like Llama, Qwen and DeepSeek, with $5 free credits and pay-as-you-go pricing

Inference cloud built on custom SN40L RDU chips that serves at full 16-bit precision — an OpenAI-compatible API hosting DeepSeek R1/V3, Llama and more, with record throughput on large reasoning models and a free tier

One-stop model API plus GPU cloud: 200+ open models via an OpenAI-compatible API, with per-second rental of RTX 4090/5090, H100 and H200 GPUs and spot pricing up to ~50% cheaper; starter credits on signup

Low-cost AI cloud for developers: an OpenAI-compatible API for open models like Llama, Qwen and DeepSeek priced far below closed models, plus on-demand H100-class GPU rental with transparent up-front rates; 250k+ developers

Real-time voice AI platform: Sonic 3.5 text-to-speech frequently ranks #1 for low latency, paired with Ink-2 transcription — built for voice agents and AI phone calls on Mamba/SSM research, with a free tier of ~20k credits a month

AI-native neural search API for agents and RAG: understands meaning rather than keywords and returns clean page content directly (no scraping), plus Deep Search and structured Websets; content on the top ~10 results is free with ~$10 in starter credits

Stability AI's text-to-audio tool trained on fully licensed data for commercial safety: generates music, stems and sound effects with audio-to-audio transformation; free tier for personal use, Pro from about $11.99/month

AI-powered design-and-publish platform: design responsive sites on a canvas and ship them in one click, with AI that generates pages from prompts, localization and A/B testing, plus built-in CMS, SEO and global CDN hosting — free to start, Basic from $10/month

All-in-one generative design suite for creators: real-time image generation, text-to-image/video/3D, upscaling and LoRA fine-tuning in one place, with a visual Krea Nodes workflow builder and an API — used by 40M users, free tier of 100 units a day

No-barrier UI design tool from Miro: Autodesigner 2.0 generates multi-screen projects from a prompt, a Screenshot Scanner turns screenshots into editable mockups and a Wireframe Scanner digitizes hand-drawn sketches — usable by anyone with no learning curve, free to start, Pro $12/month

AI UI design software anyone can use: mix screenshots, text and canvas selections in one prompt to generate editable wireframes and hi-fi prototypes, with two-way Figma, code export and an MCP server — free Starter with 300 AI credits a month, Pro $11/editor/month

AI website tool for pro designers and developers: generate a full sitemap and wireframes from a prompt with AI copywriting, then export to Figma, Webflow and React in one click — backed by a 1,000+ component library and a Webflow Chrome extension, free to start

Text-to-UI design copilot: describe an app in natural language and get editable multi-screen interactive prototypes in minutes, with an Agent mode that keeps designs consistent via shared components; paid tiers give unlimited Figma and HTML/CSS export, and MCP on every plan connects Claude Code/Cursor — the free plan never expires

The industry-standard AI writing assistant: real-time grammar, rewriting and tone fixes across 500K+ apps and sites; parent company rebranded to Superhuman in 2025, folding in Coda docs and Superhuman Mail as a productivity suite — free tier with 100 AI prompts a month, Pro from $12/month billed annually

Learneo's AI rewriting and grammar toolkit: a multi-mode Paraphraser, AI Detector with Humanizer, Summarizer and translation across 40+ languages in one place, with desktop, mobile and browser extensions everywhere — free tier available, Premium works out to $8.33/month billed annually

A budget-first AI copy generator: 40+ template use cases, 20+ tones plus custom tone cloning and 35+ languages, with the Unlimited plan at just $7.50/month billed annually for unlimited generation — built for cost-sensitive marketing and e-commerce copy

An AI writing tool built for novelists: its fiction-specialized Muse model is rated best-in-class for prose by multiple reviews, and Story Bible runs a full long-form workflow from outline and character cards to chapter-by-chapter drafts — you keep the copyright, from $10/month billed annually

The deep style-analysis 'Storyteller's Toolkit': 25+ writing reports diagnose style, pacing and readability, with AI Chapter Critique, a Virtual Beta Reader and manuscript marketability analysis for novelists, integrated across Word, Scrivener and browsers — free tier available, Premium at $120/year or a $399 lifetime license

AWS's spec-driven AI coding IDE: write requirements and design docs first, then get task lists with acceptance criteria; Agent Hooks automate on events, and one subscription covers IDE, CLI and web — free tier with 50 credits/month, Pro from $20/month

Google's asynchronous AI coding agent: hand it a task and it clones your repo in a cloud VM, plans, executes on its own and delivers a GitHub PR, with a cross-platform CLI and open API — free tier of 15 tasks a day, higher limits bundled with Google AI Pro/Ultra subscriptions

The official AI for JetBrains IDEs: AI Assistant (completion, chat, refactoring) and the Junie coding agent share one subscription, with a standout free tier of unlimited local models and unlimited code completion — AI Pro at $10/month, AI Ultimate at $30/month recommended for heavy Junie use

The radically fast-moving agentic coding tool spun out of Sourcegraph in late 2025: Orbs run parallel agents on cloud machines, The Dial sets four effort levels with multi-model scheduling, all in a CLI + web form factor — subscriptions from Megawatt at $20/month (the free tier is closed to new signups for now)

Microsoft's consumer AI assistant: GPT-5-family models free for everyone via Smart auto-routing, with long-term Memory, Copilot Vision for screen/camera understanding and Edge's Copilot Mode woven deep into Windows — Copilot Pro at $20/month adds peak priority and Copilot inside Office apps

Quora's multi-model aggregator: one subscription switches between a thousand-plus models — GPT-5.5, Claude, Gemini, Grok — plus image/video generation, a mature creator economy for custom bots and an OpenAI-compatible API; free tier of 300 points/day, subscriptions from $4.99/month with the mainstay at $19.99/month

Google's AI research and note-taking assistant (renamed Gemini Notebook in July 2026): upload PDFs, web pages and videos for grounded Q&A with inline citations, plus the much-loved Audio Overviews podcast mode, Video Overviews and Deep Research auto-reports — generous free tier, higher limits bundled with Google AI subscriptions

The AI academic search engine for researchers: semantic search over 200M+ peer-reviewed papers, a Consensus Meter that visualizes the evidence split, and Deep Search that delivers a cited literature review in about two minutes — used by 2.5M monthly researchers across 5,000+ universities, free tier available, Pro from $8.99/month billed annually

An enterprise-grade AI voiceover and TTS platform: the Gen2 model delivers broadcast-quality voices in 20+ languages with fine-grained control over tone, pauses and emphasis, plus 200+ voices, voice cloning, multilingual dubbing and a developer API — free trial, Creator at $19/month billed annually

The de-facto standard in AI noise cancellation: removes background noise and echo both ways across 800+ calling apps, takes AI meeting notes without a bot joining, and its 2025 flagship real-time Accent Conversion targets call centers, with an SDK for developers — free tier of 60 minutes a day, Pro around $8/month billed annually

The leading AI tool for turning long videos into shorts: it auto-finds highlights, scores each clip's virality, and adds ClipAnything multimodal prompt clipping, agentic Agent Opus packaging and AI B-Roll, with one-click publishing to TikTok/Shorts/Reels — 10M+ creators served, free tier of 60 minutes a month, paid from $15/month

ByteDance's international CapCut, a first-tier consumer video editor: multi-track timeline, AI cutout, auto captions and text-based editing, with Seedance 2.0 text-to-video built in from 2026 for 4K cinematic generation — free tier available, Pro at $19.99/month (prices rose after the 2025 Standard/Pro split)

The London-built online AI video platform: signature auto-subtitles with unlimited multilingual translation, its own Fabric 1.0 talking-head model (60x cheaper than rivals, per Veed), AI avatars and text-to-video aggregating Veo 3.1 — free tier available, Lite from $18/month billed annually

The Paris-built AI background removal and product photo tool, the benchmark on mobile: one-tap cutouts, AI scene generation, Virtual Model and Ghost Mannequin e-commerce tools (powered by gpt-image-1), batch processing for hundreds of product shots and a mature API — free tier available, Pro works out to $7.50/month billed annually

The lowest-barrier desktop app for running LLMs locally: download and run open models with a GUI (llama.cpp + Apple MLX engines), a built-in OpenAI-compatible local API server and MCP client — free for personal and commercial use since 2025, with the new Bionic agent app launched in 2026

AI21 Labs' AI English rewriting assistant: multiple rewrite suggestions, tone switching, shorten/expand, summaries and AI generation in one, available everywhere via Chrome extension and iOS keyboard — free tier offers 10 rewrites/day, Unlimited works out to $6.99/month billed annually

Workflow automation platform for technical teams: visual editor plus JS/Python code nodes plus AI agent workflows, priced per execution instead of per step, with a free self-hosted Community Edition and nearly 200k GitHub stars

Professional-grade JavaScript animation library powering 11M+ websites, known for blazing performance and ScrollTrigger scroll animations — free to use with commercial licensing based on user count

Open-source AI voice studio running locally — voice cloning, TTS across 7 engines, dictation, and agent voice in one app. A free alternative to ElevenLabs and WisprFlow, supporting 23 languages.

Design intelligence skill for AI agents — 45+ design styles, 8 tech stacks, 39 website demos, color palettes, typography, and UX guidelines

DeepSeek-native AI coding agent for your terminal. Cache-first architecture with 90%+ prefix cache hit rate. CLI/TUI/Desktop/Web UI/ACP editor.

The missing design vocabulary for AI agents. Strips the slop from AI-generated interfaces. Works with Codex CLI, Claude Code, Copilot, Cursor, Gemini CLI, and more.

Make videos programmatically with React. Use React to create real MP4 videos, motion graphics, and animations.

Write HTML. Render video. Built for AI agents. An HTML-to-video rendering engine for AI agents.

The API to search, scrape, and interact with the web at scale. Turn web content into clean Markdown or structured data for AI agents.

Open-source theming tool that skins the Codex desktop app — local CDP injection without modifying the official installer. Supports macOS and Windows, with the official DreamSkin.cc theme gallery for one-click skinning.

Microsoft's lightweight Python utility that converts files to Markdown for LLM use — supports PDF, PowerPoint, Word, Excel, images (EXIF+OCR), audio (transcription), HTML, YouTube URLs, EPUBs and more.

AI content marketing agent for one-person companies (OPC): automatically creates, publishes and monetizes content across 13 platforms including Douyin, Xiaohongshu, Kuaishou, Bilibili, TikTok, YouTube, Instagram and X.

Local-first web intelligence for AI agents: search, fetch, crawl, extract, cache, find-similar, research, and autonomous gather loops — no API keys, no metered bill. Serves agents via MCP, REST, and SDKs.

OpenBMB's tokenizer-free Text-to-Speech system: directly generates continuous speech representations via diffusion autoregressive architecture. 2B parameter model, 30 languages, Voice Design, controllable voice cloning, 48kHz studio-quality audio.

A data framework for LLM-based applications (RAG): connect data sources (APIs, databases, PDFs, docs) to LLMs with indexing, querying, retrieval, and agent orchestration.

A multiplayer agent harness for work: each team member gets their own isolated agent workspace with Slack and Web collaboration, shared memory, files, skills, cron jobs, and web app deployment.

An open-source monetization platform for developers: subscriptions, payments, donations, and license management for open-source projects — an all-in-one commercialization toolkit.

Open-source agent harness by DeepSeek built on the Cordis plugin system. Everything is a plugin — models, tools, skills, sessions, sandboxes, storage, scheduling, and UI are all composable and replaceable