English | 中文
This repo collects awesome AI tools. Welcome everyone to recommend more awesome AI tools together! Please use the following template as a reference for your recommendations. Contribution guidelines
💎 Sponsor
A huge thank you to our sponsors! Want to appear here? Contact us.
All Categories
AI Assistants & Proprietary Models
| Name | Description | Links | Fees |
|---|
| ChatGPT | 🌟 OpenAI's AI assistant. Current flagship: GPT-6 Astra; GPT-6.1 Sol from the Sep 29 DevDay and GPT-6 Luna cut API prices ~50% ($2/$10 and from $0.10 input per M tokens) and are free within consumer limits. Starting Oct 7, 2026, GPT-6 (Sol/Luna) with Intelligent UI is rolling out globally to all ChatGPT users: paid tiers default to GPT-6 Sol, Free/Go tiers get GPT-6 Luna, and responses can automatically render interactive charts, forms, and visual layouts.Differentiation: persistent memory and user profile — remembers context across conversations and feels the most personalized; best general-purpose assistant for coding, writing, and daily tasks.More Info | 1. URL2. API | Free/Paid |
| Claude | 🌟 Anthropic's AI assistant. Current flagship: Claude Fable 5.1 (general) / Claude Mythos 5.1 (trusted access); Claude Opus 5.5 matches Fable 5.1 on most tasks at ~40% lower cost, Sonnet 5.5 shipped Sep 28, and Haiku 5.5 launched Oct 7 at $0.10/$0.50 per M tokens for prompts up to 100k — roughly 1/10 the price of Haiku 4.5 and 1/20 of Sonnet 5.5. Sonnet 5.5 cache reads were also cut 50%, making most agentic work ~20% cheaper.Differentiation: Cowork mode turns the chatbot into an agent that pulls financial data, builds Excel forecasting models, and executes workflows; strongest at coding, long-context reasoning, safety, and enterprise use.More Info | 1. URL2. API | Free/Paid |
| Gemini | 🌟 Google's AI assistant combining native multimodality, Deep Research, and Google Workspace integration. Gemini 4 Argon is now available through the API, AI Studio, and Gemini Enterprise, with Gemini app access for Google AI Pro/Ultra subscribers; its . Gemini 3.8 Flash remains the fast option. Fairwind provides separate controlled access for trusted cyber defenders; Gemini Spark handles background tasks across Gmail, Calendar, and Tasks. |
Decision Models
| Name | Description | Links | Fees |
|---|
| Jev | 🌱 TypeSafe AI's "System One" decision model (early access) — it never generates text, returning typed answers (Choice/Score/Noul) with calibrated probabilities so confidence matches accuracy. Officially 20-200x faster and 1/40-1/400 cheaper than frontier LLMs on structured tasks;input $0.042/M tokens, output free, 70-500ms latency. Note: official figures, not yet independently verified. More Info | URL | Free/Paid |
| SemIf (formerly OpenJev) | 🌱 An MIT-licensed independent open-source project (explicitly unaffiliated with Jev or TypeSafe) that turns runtime semantic decisions into a probability readout: no training, no fine-tuning — it reads typed option probabilities directly from a frozen Qwen3.5-4B, generating no text and needing no JSON parsing, aimed at the small decisions agents make (route this, retry that, does the evidence hold?). On 21 yes/no judgments the direct readout has a median of 1.02s vs 5.33s for generating a JSON array token by token (~5.2x); agreement with TypeSafe's published 102-row subset is 84.5% (closed-source Jev reports 88.3%). Runs on a single RTX 3090, Apple Silicon (MLX/MPS), or CPU-only via llama.cpp, plus a browser-only WebGPU demo with no waitlist. | GitHub Site/Demo | Free |
| OpenAI Decisions API | OpenAI's dedicated decision endpoint (POST /v1/decisions) in public beta. Returns typed answers — predicate (0–1 probability), choice (selected value + per-option probabilities), or score (probability-weighted mean across ordered levels) — based on gpt-6-luna. Input $0.10/M tokens; cache read/write and output tokens are free. About 10× faster than the same call through Responses API. | API Docs | Free/Paid |
| Microsoft-Decision-1 | Microsoft's fast decision-scoring model, post-trained from Qwen3.5-9B. Returns calibrated probabilities over fixed yes/no, multiple-choice, or rating options instead of generating text. Available through Microsoft Foundry and OpenRouter; 32K context, input $0.042/M tokens, output free. |
Open Source LLMs
| Name | Description | Links | Fees |
|---|
| Kimi K3 | 🌟 Moonshot AI's flagship open-weight model — the first open-source model in the 3-trillion-parameter class, putting near-frontier capability fully in the open.Modified MIT license; 1M-token context with native visual understanding, aimed at software engineering, knowledge work, and long-document reasoning. More Info | Technical Blog Hugging Face | Free |
| DeepSeek models | 🌟 DeepSeek's open-weight model family for reasoning, coding, and agent tasks. Current V4 models use the MIT license and support self-hosting and commercial use; V4.1-Flash-1017 offers native multimodal understanding, 1M-token context, and improved complete-project development and task efficiency, alongside V4-Pro. R1 (reasoning) and V3 (general-purpose MoE) remain available as earlier releases for research and existing deployments.More Info | V4 modelsEarlier releases: R1, V3 | Free |
| Qwen3 / Qwen3.8 | Alibaba Cloud's open-weight LLM/VLM families — the most complete open model lineup, strong in coding, multilingual, and agentic use. Qwen3.8 adds a dense vision-language model (image/video input) and Qwen3.8-Flash-Next, an ultra-cheap high-throughput variant previewing the Qwen4 architecture. | GitHub Hugging Face | Free |
| GLM-5.3-Flash |
LLM Leaderboard
| Name | Description | Links | Fees |
|---|
| LMArena (Chatbot Arena) | 🌟 LMArena (formerly LMSYS Chatbot Arena; renamed Arena in 2026) is a crowdsourced open platform for LLM evals, born from UC Berkeley's SkyLab (LMSYS, with Stanford/UCSD/CMU/MBZUAI). Collected over 1,000,000 human pairwise comparisons to rank LLMs with the Bradley-Terry model and display the model ratings in Elo-scale.More Info | URL | Free |
| Artificial Analysis | 🌟 Independent AI benchmarking for choosing models and API providers. Compare capability, cost per task, output speed and latency, with dedicated evaluations for coding agents, images, video and speech. Published methods and capability–cost charts help you shortlist models before testing your own tasks. Public leaderboards and a free data API are available, alongside commercial data services. More Info | Website | Free/Paid |
| LiveCodeBench | LiveCodeBench is a holistic and contamination-free evaluation benchmark of LLMs for code, built by UC Berkeley + MIT + Cornell, that continuously collects new problems over time. Particularly, LiveCodeBench also focuses on broader code-related capabilities, such as self-repair, code execution, and test output prediction, beyond mere code generation. | URL | Free |
| StructEval | StructEval is a TMLR 2025 benchmark and public leaderboard by University of Waterloo-led TIGER-AI-Lab for evaluating LLM structured-output generation and conversion across 2,035 examples, 18 text and renderable formats, and format-specific structural and visual checks. | Leaderboard Paper GitHub |
AI Agent
| Name | Description | Links | Fees |
|---|
| Claude Code | 🌟 Anthropic's AI agent for code, file, and terminal tasks. Available in the terminal CLI, VS Code/Cursor/JetBrains IDE plugins, desktop app, and web.Built on the Claude model family, it offers long-context codebase understanding, multi-file editing, shell command execution, MCP extensions, skills/hooks/subagents, CLAUDE.md project rules, and automatic memory. Supports Remote Control to continue local sessions from your phone or browser. More Info Comparison | GitHub | Free/Paid |
| Codex | 🌟 OpenAI's open-source (Apache-2.0) AI agent with a terminal interface, written in Rust. Supports the terminal CLI, VS Code/Cursor/Windsurf IDE extensions, Codex App/desktop app, and Codex Web cloud tasks.It can understand and modify code directly, with kernel-level sandboxing, MCP, skills/plugins/hooks, subagents, and Remote SSH. Active sessions sync across phone/desktop/web via the ChatGPT relay. More Info Comparison | GitHub | Free/Paid |
| Kimi Code | 🌟 Moonshot AI's AI agent CLI that runs in your terminal — stands out with native video input and first-class Chinese-language support.Reads and edits code, runs shell commands, searches files, fetches web pages, and plans next steps based on feedback. Supports AI-native MCP configuration, subagents, lifecycle hooks, and ACP editor integration (Zed, JetBrains). More Info Comparison | GitHub |
Coding Agents
Coding editors, IDEs, and app builders with AI assistance and agentic development workflows.
| Name | Description | Links | Fees |
|---|
| Cursor | 🌟 The leading AI coding editor: switch between OpenAI, Anthropic, Gemini, Grok and Cursor's own Composer models, and run parallel agents across desktop, CLI, Slack and GitHub. A wholly owned SpaceX (SpaceXAI) subsidiary since Aug 2026. More Info | URL | Paid/Free Trial |
| Trae | ByteDance's AI coding IDE built around agentic programming: AI Q&A, code auto-completion, and autonomous multi-step coding tasks. More Info | URL | Free |
| GitHub Copilot | GitHub's code writing assistant, now a multi-vendor model picker (OpenAI, Anthropic, Gemini and more) chosen per task More Info | URL | Free/Paid |
| Antigravity | Google's agent-first AI coding platform, available as a desktop app, IDE, terminal CLI (agy), and SDK. Supports Gemini 4 Argon and Gemini 3.8 Flash, alongside third-party models such as Claude and GPT-OSS; model access depends on the plan. Editor/Manager views coordinate multiple agents with a browser, terminal, verifiable Artifacts, subagents, hooks, and scheduled tasks. More Info | URL | Free/Paid |
| Bolt.new | StackBlitz's browser-based AI full-stack app builder — describe an app in plain language and the AI agent scaffolds, runs, and deploys it in the browser via WebContainers (real Node.js at near-native speed, no local setup or cloud VM).Free / Pro $25/mo / Teams $30 per member / Enterprise plans; open-source sibling bolt.diy supports bring-your-own-key. One of the fastest-growing dev tools ($40M ARR within 5 months of launch; Microsoft Azure partnership since May 2026). |
Code Review & Development Utilities
Code review, debugging, development conventions, configuration, and companion tools.
| Name | Description | Links | Fees |
|---|
| git-lrc | Free, Unlimited AI Code Reviews That Run on Every Commit | GitHub | Free |
| alibaba/open-code-review | Open-source AI code-review CLI/agent by Alibaba. Reviews Git diffs with deterministic pipelines plus an LLM agent, supports line-level comments, configurable OpenAI/Anthropic-compatible endpoints, custom rules, JSON CI output, WebUI session viewer, and Claude Code/Codex integrations. | GitHub | Free |
| Kodus | Open Source Code Review Agent | GitHub | Free/Paid |
| AI-Codereview-Gitlab | GitLab automatic code review tool based on LLMs (DeepSeek, OpenAI, etc.). Supports DingTalk/WeCom/Feishu notifications and daily reports generation. Docker deployment supported with visual Dashboard. | GitHub | Free |
| code-review-graph | Builds a structural code graph with Tree-sitter, tracks incremental changes, and exposes precise review context to AI coding assistants via MCP to reduce redundant codebase reads. | GitHub | Free |
| dbForge AI Assistant | AI-powered tool that generates, optimizes, and troubleshoots SQL code; indispensable for developers, DBAs, and analysts | URL | Paid/Free Trial |
| scalene | Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals | GitHub | Free |
| OpenChamber | Desktop and web GUI for the OpenCode AI agent. Provides session management, diffs, and workspace control on top of OpenCode. |
Agent Workspaces & Collaboration
Manage and schedule existing agents, tasks, sessions, workspaces, and team collaboration.
| Name | Description | Links | Fees |
|---|
| OpenDots | 🌱 CopilotKit's open-source self-hosted agent workspace template (open alternative to OpenAI Dots). Gives each Dot its own computer with browser/file/terminal permissions, MCP tools, Slack/calls, Spaces document collaboration, background tasks, and human-in-the-loop approval. Requires self-hosting and connecting CopilotKit Intelligence + an OpenAI-compatible model.More Info | GitHub | Free |
| Multica | Open-source managed agents platform to integrate AI coding agents (Claude Code, Codex, Cursor, Copilot, OpenCode, OpenClaw, Hermes, Gemini, Pi, Kimi, Kiro CLI, and more) into dev teams as first-class teammates. Features task assignment, progress tracking, reusable skills, and local daemon auto-detection of installed agent CLIs. | GitHub | Free/Paid |
| Paperclip | Open-source AI agent orchestration platform that models AI operations as a company. Define org charts, reporting lines, budgets, and governance policies, then let agents work autonomously within that structure. Supports OpenClaw, Claude Code, Codex, and other agent backends. Heartbeat-based execution with cost controls and audit trails. | GitHub | Free |
| Symphony | OpenAI's open-source project-to-delivery harness. Turns project requirements into isolated, autonomous implementation runs; agents monitor boards like Linear, open PRs, and merge code with proof-of-work (CI status, review feedback, demo videos). Currently in engineering preview. | GitHub | Free |
| QM | YC open-source multi-agent harness for organizations. Runs on Slack and Web with scoped workspaces (memory, files, credentials, permissions) per employee/project/channel; headless core with replaceable models/harnesses and self-hostable via Docker/Fly/AWS. | GitHub |
Agent Frameworks & Runtimes
Build agents, define execution workflows, and provide agent runtimes.
| Name | Description | Links | Fees |
|---|
| Microsoft Agent Framework | Microsoft's MIT-licensed framework for production AI agents and multi-agent workflows, and the recommended successor to archived AutoGen. Supports Python and .NET, multiple model providers, graph-based orchestration, checkpointing, human approval, and OpenTelemetry observability. Suitable for teams that need durable, inspectable workflows from local development to cloud deployment; model and hosting costs depend on the chosen services. | GitHub | Free |
| LangGraph | LangChain's low-level orchestration framework for building stateful, multi-agent LLM applications as graphs. Models workflows as nodes and edges with persistent state, checkpointing, and human-in-the-loop interrupt/resume, making long-running, fault-tolerant agents easier to build, debug, and observe. Ships graph/state primitives, a Studio visual debugger, and LangGraph Platform for durable execution, persistence, and streaming at scale. Works with any model provider; Python and JS/TS.More Info | GitHub Website | Free |
| MastraAI | Mastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations and evals | GitHub | Free |
| agentscope | Agent-Oriented Programming for Building LLM Applications, Open-sourced by Alibaba | GitHub | Free |
| FlowGram.AI | An extensible visual AI workflow development framework with built-in canvas, form engine, variable scope chain, and ready-to-use materials (LLM, Condition, Code Editor, etc.) for building AI workflow platforms faster. | GitHub |
Browser & Computer Automation
Automate web, desktop, and mobile interactions with supporting browsers and sandboxes.
| Name | Description | Links | Fees |
|---|
| browser-use | Open-source (MIT) Python library that lets AI agents control web browsers: natural-language tasks, DOM extraction, form filling and multi-step navigation, with any LLM. Browser Use Cloud adds hosted stealth Chromium you can drive over CDP (also from Playwright or Puppeteer), residential proxies, CAPTCHA solving, persistent profiles, a browser-agent API and a remote MCP server, billed per browser-hour with no subscription. More Info | GitHub Website | Free/Paid |
| Cua | Open-source infrastructure for Computer-Use Agents (CUA). Provides sandboxes, drivers, and SDKs for macOS, Windows, Linux, and Android, enabling AI to control full desktops just like a human. | GitHub | Free |
| ARTEMIS | Google's open-source framework that turns natural-language instructions into reliable Android automation: cross-app task execution, multimodal targeting, and Flash (fast reactive) / Pro (multi-agent planning) execution modes. Ships a Web UI console, MCP server, Python SDK, and CLI for integration with Claude Code, Codex and other agents.More Info | GitHub | Free |
| Obscura | Open-source (Apache-2.0) headless browser engine written in Rust for AI agents and web scraping. A drop-in replacement for headless Chrome via the Chrome DevTools Protocol, compatible with Puppeteer/Playwright: ~30 MB memory, instant startup, and a built-in stealth mode with anti-fingerprinting and tracker blocking. | GitHub | Free |
| Steel Browser | Open-source browser sandbox and automation infrastructure for AI agents and apps with session-backed workflows, screenshots, PDFs, proxies, and anti-bot tooling. |
Agent Memory & Context
Store and retrieve historical memory, and build context from codebases and knowledge sources.
| Name | Description | Links | Fees |
|---|
| MemPalace | Open-source AI memory system that stores full conversations and project data locally without cloud dependencies. Organizes memories into a hierarchical "palace" structure, achieves 96.6% recall on LongMemEval — the highest published score for a fully local setup that calls no APIs, supports MCP integration and works offline with local LLMs. | GitHub | Free |
| TencentDB Agent Memory | Tencent Cloud's open-source memory infrastructure for agent teams. Provides Memory Hub for cross-session/cross-agent memory sharing, Chat Memory with L0–L3 distillation, Skill library for reusable expertise, and Wiki/CodeGraph for docs/code knowledge maps. Works with Claude Code, CodeBuddy, and other agents. | GitHub | Free |
| Screenpipe | Searchable screen-text and audio history for recall, meeting notes, and work summaries via MCP or a local API. Raw history stays local by default; configured cloud AI, transcription, sync, and integrations can process context off-device.Source-available under the Screenpipe Commercial License. macOS, Windows, and Linux. | GitHub | Limited free plan; paid subscriptions |
| codesight | CLI token optimizer and AI context generator with built-in MCP server. Scans codebases to extract routes, schema, components, and dependencies, reducing AI context tokens by 9x–13x. Profiles for Claude Code, Cursor, Copilot, Codex, and Windsurf. Zero runtime dependencies. | GitHub | Free |
| Understand Anything | AI-powered codebase and knowledge base analysis tool that builds interactive visual knowledge graphs. Features multi-agent analysis, architecture guided tours, and semantic search for large codebases. Works as a plugin for Claude Code, Cursor, and more. | |
Agent Skills
| Name | Description | Links | Fees |
|---|
| anthropics/skills | Official skills repository for Claude Code skills, providing reusable tool integrations and extensions for Claude Code AI assistant | GitHub | Free |
| openai/skills | Official skills repository for OpenAI GPT models, providing reusable tools and extensions for OpenAI's AI assistants | GitHub | Free |
| skills.sh | Community-driven skills registry and marketplace for AI assistants, providing a curated collection of reusable skills for various AI platforms including Claude Code, OpenAI GPT, and other LLM assistants, with download usage statistics and trending popularity rankings for all skills | Website | Free/Paid |
| BrowserAct Skills | Directory of reusable AI-agent skills and browser automation workflows for research, ecommerce, social/search extraction, video platforms, maps, and operational automation. | Website | Free |
| JimLiu/baoyu-skills | Community skills repository for Claude Code, providing practical Chinese-language and region-specific skills including Weibo posting functionality | GitHub | Free |
| ClawHub | A fast skill registry for AI agents, with vector search capabilities. Provides a centralized platform for managing and discovering agent skills. | URL | Free/Paid |
| garrytan/gstack | An opinionated collection of Claude Code skills that transform the AI agent into a specialized team of experts (CEO, PM, QA, DevOps). Adds custom slash commands and automated quality checks. | GitHub | Free |
| addyosmani/agent-skills |
AI News & Information
| Name | Description | Links | Fees |
|---|
| SemiAnalysis | 🌟 Independent research on semiconductors, AI hardware, and the compute supply chain (founded by Dylan Patel, 2020). Builds proprietary data models — Accelerator/HBM, datacenter models, ClusterMAX GPU-cloud ratings, and the open-source InferenceX benchmark (called out by Jensen Huang at GTC 2026) — alongside long-form industry reports (some free, most subscription).More Info | X, Official Site | Free/Paid |
| World Monitor | AI-powered real-time global intelligence dashboard with 435+ curated feeds, geopolitical monitoring, infrastructure tracking, AI summaries, 21 languages support, local AI runtime and cross-platform native desktop apps | GitHub , Official Site | Free |
| Prismix | AI hub aggregating real-time status of 75+ AI services (OpenAI, Anthropic, Groq, Cursor, etc.), curated news from 55+ AI sources with a personalized feed, and 500+ MCP server directory with bundles. Email/webhook alerts on outages. | Official Site | Free/Paid |
| AI Weekly | Independent AI news newsletter, 3x/week since 2015, read by 44,000+ professionals. The few AI stories that matter, solo-edited. Proprietary AI Weekly Index, quarterly State-of-AI recap, Who's-Who-of-AI graph (2,335 figures), and an 11-year archive. | Official Site | Free |
| ArtificialWatch | Alerts the minute a new AI model is released, across labs. Sweeps provider APIs every 60 seconds and fires only when a model answers a real API request; a public track record logs first-seen and confirmed times. Free email + push; paid SMS and phone call. | Official Site |
AI Security & Reverse Engineering
| Name | Description | Links | Fees |
|---|
| REA | 🌱 Open-source MCP toolkit that turns AI coding agents into reverse-engineering assistants. REA connects Claude Code, Codex, Cursor, Gemini CLI, and Grok Build to local analysis engines for native binaries, JavaScript/Electron, .NET assemblies, websites, Android APKs, firmware, and network captures. The agent inspects a target feature without source code, receives evidence-backed findings, and reconstructs a working implementation for your project.More Info | GitHub | Free |
| Security Audit Skill | Cloudflare's open-source (MIT) skill that turns a coding agent into a rigorous security auditor. Its six-phase audit — reconnaissance, coverage-led hunting with isolated sub-agents, adversarial validation (verifier is never the finder), independent verification, and reporting — spans memory safety, prompt injection, supply chain, and cloud IAM. Findings go to machine-readable findings.json with strict confirmed/needs_validation/rejected verdicts, checked by zero-dependency validators. Installs via Skills CLI; it seeded Cloudflare's vulnerability harness. Free; needs Node.js and an OS sandbox. | GitHub | Free |
| PentAGI | Open-source, self-hosted multi-agent system for autonomous penetration testing: give it a target and a goal; agents plan and run 20+ professional tools (nmap, Metasploit, sqlmap) in an isolated Docker sandbox, then return a vulnerability report. Runs on 10+ cloud LLM providers or local Ollama/vLLM; findings persist in PostgreSQL + pgvector (optional Neo4j graph), plus REST/GraphQL APIs and a web UI. Free self-hosted (MIT); Enterprise adds agent profiles, plugins/MCP and attack-chain views. For authorized testing only.More Info | URL GitHub | Free/Paid |
| Codex Security | OpenAI's open-source CLI and TypeScript SDK (alias ) for finding, validating and fixing security vulnerabilities in code. Scans whole repositories, selected paths or Git diffs — deep scans fan out parallel discovery workers — then validates findings, generates patches and re-checks existing fixes. It also drafts a SECURITY.md policy, scores and deduplicates findings against your own rubric with owners inferred from Git history, exports SARIF/JSON/CSV and publishes to Linear. Runs across repositories, in CI and in containers. Free; needs an OpenAI API key or sign-in. |
General LLM Applications
| Name | Description | Links | Fees |
|---|
| Google AI Studio | Google's web workspace for prototyping with Gemini models, including Gemini 4 Argon. Experiment with prompts and multimodal inputs, then create an API key for applications. Model access, quotas, and API billing depend on the selected model and account; using the studio does not make every model's API usage free. Available regions | URL | Free/Paid |
| Gemini Notebook (formerly NotebookLM) | Google's AI research assistant, formerly NotebookLM. Upload PDFs, websites, YouTube videos, audio files, Google Docs, or Google Slides, and Gemini Notebook will summarize them and make interesting connections between topics. Audio Overview feature can turn your sources into engaging “Deep Dive” discussions with one click. | URL | Free |
| Poe | Quora's multi-model AI chat platform. Access GPT, Claude, Gemini, Grok, Kimi, DeepSeek, and many other chat/image/video models through a single interface with a points-based subscription. Supports custom bots, group chats, side-by-side model comparison, and an OpenAI-compatible API. | URL | Free/Paid |
| Perplexity | The citation-first AI answer engine, built on its own flagship Sonar 2 model. In 2026 it has grown from a search engine into a full research assistant: Comet, its AI browser with Perplexity wired into the address bar; Deep Research; Labs project spaces; file/app generation; and Model Council, which auto-picks the best model per query.Differentiation: multi-lab model aggregation — a single Pro/Max subscription covers models from OpenAI, Anthropic, Google, Moonshot, Z.ai, xAI and NVIDIA, and every answer carries verifiable source citations, making it the default pick for fact-checking and quick research into unfamiliar topics. | 1. URL2. API | Free/Paid |
Office Collaboration CLI / MCP
| Name | Description | Links | Fees |
|---|
| Parallel Search MCP | Hosted web search and page extraction for AI agents, with source URLs and relevant Markdown excerpts. Its anonymous endpoint provides Fast mode search and page fetching without an account, API key, or local server. Connect https://search.parallel.ai/mcp using a Streamable HTTP MCP client such as Claude Code, Cursor, or VS Code; setup guides are available for each. Free access is intended for exploration and light use, with rate limits. | Website Setup | Free (rate-limited); paid access for higher limits |
| Google Workspace CLI | Community-built unofficial command-line tool for Google Workspace that provides unified access to all Google Workspace APIs including Drive, Gmail, Calendar, Sheets, Docs, Chat. Features 40+ built-in AI agent skills, structured JSON output perfect for AI agents, and multiple authentication options. | GitHub | Free |
| OpenConnector | Open-source connector gateway for AI agents. Connect user app accounts once, then expose a shared catalog of 1500+ SaaS providers to agents via SDK, CLI, MCP, HTTP, and OpenAPI. | GitHub | Free |
AI Finance & Quant Investment
| Name | Description | Links | Fees |
|---|
| TradingAgents | A multi-agent LLM financial trading framework that mirrors the dynamics of real-world trading firms. It uses specialized AI agents to collaboratively evaluate market conditions and inform trading decisions through structured debates. | GitHub | Free |
| VNPy | A comprehensive open-source quantitative trading framework in Python, supports strategy backtesting, live trading across multiple exchanges, and integrates AI/LLM capabilities for financial market analysis and strategy development. Widely used by quant traders in China. | GitHub | Free |
| TimesFM | Google Research's open-source pretrained time-series foundation model for time-series forecasting. Supports long context (16k) and long-horizon forecasting up to 1k steps, which is widely used for financial and quantitative investment predictions. | GitHub | Free |
| Dexter | Autonomous financial research agent designed to perform deep analysis by thinking, planning, and learning through iteration. Specialized for the financial domain. | GitHub | Free |
| yfinance | Open-source Python library for accessing Yahoo Finance data. Provides stock, ETF, and crypto historical prices without API key. Essential data source for AI-powered quantitative trading and financial analysis. | GitHub | Free |
| OpenBB | Open-source investment research platform that integrates multiple financial data sources (Yahoo Finance, Alpha Vantage, etc.) with unified API. Features built-in MCP server for AI agent integration, enabling Claude and other LLMs to query financial data directly. | GitHub | Free |
| Fincept Terminal | Native C++20 financial terminal (Qt6 + embedded Python), AGPL-3.0 and free for personal/study/academic use, with the commercial Enterprise edition at $15/$30/$45 per user per month with 100+ data connectors, 37 AI agents for trading/investing/economic/geopolitics analysis, multi-asset analytics, real-time trading across 16 brokers, and MCP workflow integration.Note: public version moved to monthly updates in June 2026 as team focuses on private edition. |
AI Image Creation and UI Design
| Name | Description | Links | Fees |
|---|
| GPT Image | 🌟 OpenAI's image generation model GPT Image 2.5 (Sep 2026). ~50% faster, more photorealistic rendering, precise region editing, and a Sketch feature that turns hand-drawn drafts into finished images; API offers GPT-Image-2.5 Flare and Sunburst.More Info | URL | Free/Paid |
| Nano Banana | 🌟 Google's image generation and editing model family — among the top-ranked families on the LMArena text-to-image and image-edit leaderboards. Current flagship Nano Banana 2.1 (Oct 6, 2026) delivers best-in-class editing quality — mask-based local edits and cross-turn subject consistency for multi-image storytelling — at ~half the output price of Nano Banana 2 (retiring Oct 29, 2026). More Info | URL | Free/Paid |
| Flux | Black Forest Labs' image generation model family; current lineup FLUX.2 — photorealistic output and multi-reference editing, with open-source [klein] 4B for on-device use (Apache 2.0, sub-second on 8GB VRAM); FLUX 3 is the image/video/audio multimodal direction. flux-2-max tops LMArena text-to-image overall at 1162±3. Per-megapixel billing, [pro] ~$0.03/MP.More Info | URL GitHub | Free/Paid |
| Grok Imagine | xAI's image generation model (formerly Grok Image / Aurora; listed as SpaceXAI on LMArena), integrated in Grok and X. Grok Imagine Image 2.0 (released Aug 7, 2026) adds precision editing, multi-reference blending, and smart resizing. | URL | Free/Paid |
Video Creation
| Name | Description | Links | Fees |
|---|
| Seedance | 🌟 ByteDance's video generation model family. Seedance 2.5 powers Dreamina: up to 30-second single-pass generation (up to 4K), 50+ multimodal references, text/image-to-video, start-end frame conditioning, and region-level editing.Strong subject/motion consistency and natural camera language make it well suited to short-form video and ad production. More Info / Skills | URL | Free/Paid |
| MiniMax H3 | 🌱 Open-source omni-modal generative system by MiniMax for video and audio generation. Supports text-to-video, image-to-video, first/last-frame-to-video, text-to-audio-video, and local deployment via SGLang, vLLM, diffusers, and ComfyUI. More Info | GitHub , HuggingFace | Free |
| Dreamina | AI image and video creation tool by ByteDance/CapCut. Powered by Seedance 2.5 model. Supports text-to-image, text-to-video, image-to-video with up to 4K ultra-clear output | URL | Free/Paid |
| Wan 3.0 | Alibaba's all-in-one video generation model. Supports text, image, video, audio, document, and web references; up to 20 reference inputs; up to 30-second single-pass generation; pixel-level consistency; and precise video editing. | URL | Free/Paid |
| KLING AI | AI video creation by Kuaishou — a leading Chinese video model known for high-fidelity cinematic output. Kling 4.0 (in preview since Sep 28, 2026): up to 30s native generation, 4K/1080p 10-bit HDR, up to 15 multimodal references and 10 keyframes; Kling 3.0 remains available. Supports text/image-to-video, start-end frame, and motion control. |
AI Infrastructure Platform
| Name | Description | Links | Fees |
|---|
| Hugging Face | 🌟 The leading open AI platform and community. Hosts 3M+ models, 500K+ datasets, and 1M+ demo Spaces (per the NVIDIA acquisition announcement, Sep 2026); powers model discovery, inference, fine-tuning, and deployment via the Hub, Transformers, Diffusers, and Accelerate ecosystems. More Info | URL GitHub | Free/Paid |
| Google Colab | Google's hosted Jupyter notebook environment — the de facto standard free GPU runtime for ML/AI work: the free tier includes GPU (T4-class) and TPU access with zero setup, Google Drive/GitHub integration, and shareable notebooks. Free-tier limits: ~15–30 dynamic GPU hours/week, sessions up to ~12 hours, 90-minute idle timeout, no availability guarantee. Paid Pro/Pro+ tiers unlock stronger GPUs and longer sessions. The first choice for running, fine-tuning and demoing models when you don't own hardware. | URL | Free/Paid |
| Kaggle | Google-owned ML competition and data platform: Kaggle Notebooks come with ~30 hours/week of free GPU quota, 200K+ public datasets, and a competition community that produced many of the field's classic benchmarks. The standard venue for learning applied ML and stress-testing models against real baselines. | URL | Free/Paid |
| together.ai | The AI Acceleration Cloud. Train, fine-tune-and run inference on AI models blazing fast, at low cost, and at production scale. | URL | Free/Paid |
GPU Programming
| Name | Description | Links | Fees |
|---|
| LeetGPU | GPU programming platform for learning, practicing, and competing on GPU programming challenges. Similar to LeetCode but for GPU programming, helping developers master GPU acceleration skills essential for AI model training and inference. | URL | Freemium |
| LeetCUDA | An open-source educational repository and question bank for CUDA programming and deep learning operator optimization. Includes 200+ kernels ranging from basic to advanced (e.g., FlashAttention-2) with PyTorch bindings. | GitHub | Free |
LLM Prompts
| Name | Description | Links | Fees |
|---|
| System Prompts and Models of AI Tools | The most comprehensive collection of system prompts, tool definitions, and model configurations for mainstream AI tools (Cursor, Claude Code, Windsurf, Trae, v0, etc.). Essential for studying Prompt Engineering and AI Agent architectures. | GitHub | Free |
LLM training platform
| Name | Description | Links | Fees |
|---|
| lm-sys/FastChat | An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena (renamed LMArena in Sep 2024 and Arena in Jan 2026). Note: no releases since v0.2.36 (Feb 2024). | GitHub | Free |
LLM Inference & Deployment
| Name | Description | Links | Fees |
|---|
| DeepInfer | 🌱 DeepSeek's open-source, production-grade inference framework that powers DeepSeek-V4.1-Flash at scale — high throughput and low latency, integrating DeepSeek's optimized kernels (FlashMLA, DeepGEMM, DeepEP, TileLang) with DSpark speculative decoding, SWA bounded replay, async scheduling, batch-invariant/deterministic sampling, and structured outputs. Runs on NVIDIA SM100 (Blackwell) and Huawei Ascend 950. Early release: offline inference only — a full KV cache and Prefill/Decode disaggregation are not yet packaged, and only DeepSeek-V4.1-Flash is supported. Apache-2.0, free to self-host.More Info | GitHub | Free |
| DwarfStar (ds4) | antirez's (creator of Redis) from-scratch native inference engine in C (MIT) — built to run a few near-frontier open models on consumer hardware: DeepSeek V4/4.1 Flash, V4 Pro, GLM 5.2/5.3 and Qwen3.8 Flash Next fit on a 96GB Mac or one 96GB NVIDIA GPU via aggressive 2-bit routed quantization. Serves OpenAI- and Anthropic-compatible APIs, so Claude Code, Codex, opencode and Zed can point at localhost; includes a built-in coding agent, on-disk KV cache, and layer-splitting across machines for models too big for one box. Not a general GGUF loader — only its supported models. | GitHub | Free |
| AirLLM | A Python library that reduces LLM inference memory usage by loading one layer at a time, enabling 70B models on 4GB GPUs, 405B on 8GB, and 671B DeepSeek-V3 on ~12GB. Supports 4-bit/8-bit quantization and a wide range of open models via a single AutoModel interface. | GitHub | Free |
Writing
| Name | Description | Links | Fees |
|---|
| Notion AI | AI-assisted note-taking software | URL | with certain free AI trials, AI features $10/month |
| Obsidian | Powerful local-first markdown note-taking tool with extensive AI plugin ecosystem - supports AI summarization, RAG, and intelligent note processing via community plugins | URL | Free/Paid |
| Deep L Write | English and German writing tools to fix writing errors and rewrite sentences promptly. | URL | Free version to use with text word limit / paid upgrade available |
Translation
| Name | Description | Links | Fees |
|---|
| Google Translate | Support text, picture, document and URL | URL | Free |
| Deep L | Accurate and instant translation tool, supporting 30+ languages for text and speech, and 100+ languages for document translation | URL | Free/Paid |
| immersive-translate | Open source project. Immersive bilingual web translation extension | GitHub | Free |
| openai-translator | Open source project. Crossword translation browser plugin and cross-platform desktop application based on ChatGPT API | GitHub | Free, requires OpenAI API key |
| RTranslator | RTranslator is an open-source, free, and offline real-time translation app for Android. | GitHub | Free |
Speech Recognition & Subtitles
| Name | Description | Links | Fees |
|---|
| whisper | OpenAPI open source robust speech recognition model through large-scale weak supervision | GitHub | Free |
| whisper.cpp | Port of OpenAI's Whisper model in C/C++ | GitHub | Free |
| buzz | Open-source offline transcription and translation app for Windows, macOS (Apple Silicon), and Linux. Transcribes audio/video files, YouTube links, and live microphone input; supports GPU acceleration through multiple Whisper backends, speaker identification, and TXT/SRT/VTT export. Includes a transcript viewer and watch-folder automation. | GitHub | Free |
| whisperX | WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization) | whisperX | Free |
| whisper-ctranslate2 | Free, open-source local transcription CLI powered by faster-whisper/CTranslate2. Compatible with OpenAI Whisper CLI workflows; adds batched inference, live microphone transcription, subtitle export, and optional speaker diarization. Basic transcription does not require PyTorch. | GitHub | Free |
Text to Speech (TTS)
| Name | Description | Links | Fees |
|---|
| IndexTTS | Bilibili's open-source industrial-grade controllable zero-shot text-to-speech system. Current flagship: IndexTTS-2.5 supports Chinese, English, Japanese, Spanish, and Arabic with emotion control, speaking-speed control, and Pinyin/CMU/Japanese-Kana pronunciation control. Faster inference than 2.0; deployable via vLLM.Online Demo: https://huggingface.co/spaces/IndexTeam/IndexTTS-2.5-DemoPaper: https://arxiv.org/abs/2601.03888 | GitHub | Free |
| Azure Text to speech | Microsoft's cloud text-to-speech service (now Azure Speech in Foundry Tools, part of Azure AI Foundry) | URL | Paid / 500,000 characters per month free |
| Hailuo AI Text to Speech | Offer over 300 voices in 17 languages and multiple accents, covering a wide range of styles and age groups to provide the voice effects you need. | URL | Limited-time Free |
| elevenlabs | Intelligent AI Text to Speech. Current flagship Eleven v3 (generally available). | URL | Free/Paid |
| ChatTTS | ChatTTS is a text-to-speech model designed specifically for dialogue scenario such as LLM assistant. It supports both English and Chinese languages. Our model is trained with 100,000+ hours composed of chinese and english. Website：https://chattts.com/ | GitHub | Free |
Voice Cloning & Conversion
| Name | Description | Links | Fees |
|---|
| ElevenLabs | Industry-leading AI voice synthesis and voice conversion tool. Current flagship Eleven v3 is generally available; offers highly realistic text-to-speech, voice cloning (with just a few minutes of audio), and voice changing capabilities. Supports multiple languages and emotional speech. | URL | Free/Paid |
| Gemini 3.8 TTS | Google DeepMind's native multimodal text-to-speech (Gemini 3.8 TTS): multi-speaker synthesis with emotion and prosody control and low latency, callable via the Gemini API; playground available for free tuning of voice, speed and emotion.Also ships as Live Avatar for real-time interactive virtual avatars. Live Avatar | URL | Free/Paid |
| RVC (Retrieval-Based Voice Conversion) | Open-source voice conversion model that can transform any voice into another with high quality. Popular for singing voice conversion and voice cloning. | GitHub | Free |
Speech Processing & Translation
| Name | Description | Links | Fees |
|---|
| shazam | Download the Shazam app for music recognition, which is pretty fast | URL | Free |
| Seamless | Seamless is a family of AI models that enable more natural and authentic communication across languages.Official development stopped around Nov 2024; the pinned fairseq2 0.2.x dependency cannot be installed on Python 3.12+.Online Demo | GitHub | Free |
| VibeVoice | Open-source voice AI framework from Microsoft. Microsoft removed the TTS code on Sep 5, 2025 over misuse concerns (online generation for TTS-1.5B is disabled), so the mainline is now ASR. ASR supports 60-minute long-form audio with speaker diarization and 50+ languages; TTS generates natural long-form multi-speaker or real-time streaming speech. | GitHub | Free |
| Voicebox | Open-source, local-first AI voice studio (a self-hosted alternative to ElevenLabs + WisprFlow). Combines voice cloning, speech generation (multiple TTS engines, 23 languages), Whisper-based dictation/transcription, and a local LLM for text refinement.Ships an MCP server so agents like Claude Code or Cursor can speak in cloned voices. All models and voice data stay on your machine; runs on macOS/Windows/Linux/Docker with GPU acceleration. | GitHub | Free |
| VoiceStudio | Open-source, local-first AI voice workbench (an ElevenLabs alternative): zero-shot voice cloning (3–15s samples), video dubbing, dictation/transcription, and audiobook production across 646 languages. No account or API key required; models and audio stay on your machine; a local OpenAI-compatible API and MCP server work with Claude Desktop and Cursor.Note: AGPL-3.0, default engine weights CC-BY-NC, output watermarked. | GitHub |
AI Music & Sound Effects
| Name | Description | Links | Fees |
|---|
| suno.ai | The AI music creation tool Suno can generate custom songs based on text prompts in mere seconds. Current generation Suno v6 — the first family trained on licensed catalogs from Warner, BMG and Believe, with revenue sharing.More Info | URL | Free/Paid |
| udio | AI music platform that pivoted from instant song generation to licensed remixing and a creator community after settling with UMG, Warner, Merlin, and Kobalt (Sony's suit continues). Note: audio, video, and stem downloads have been disabled for all tiers since late Oct 2025. | URL | Free/Paid |
| mureka.ai | AI music creation tool by Kunlun Wanwei. Current flagship Mureka V9.5; the more advanced O3 has been previewed but not yet released. | URL | Free/Paid |
| elevenlabs/sound-effects | Imagine a sound and bring it to life, or explore a selection of the best sound effects generated by the community. | URL | Free |
| audiocraft | Meta's open-source audio/music generation library with two models: MusicGen (text-to-music) and AudioGen (text-to-sound). Unmaintained since early 2025; code is MIT, model weights CC-BY-NC 4.0 (non-commercial). MusicGen Online Demo | GitHub | Free |
| Stable Audio | AI music and sound-effect generation by Stability AI — full-length tracks and SFX from text prompts. Current generation Stable Audio 3.0 (released May 20, 2026). | URL |
Video Content Summary
| Name | Description | Links | Fees |
|---|
| Claude Video | Open-source tool that lets AI agents watch and summarize videos. Extracts frames, transcripts/captions from YouTube, TikTok, or local files and answers questions grounded in both visual and audio content. Works with Claude Code and 50+ agent hosts. | GitHub | Free |
Academic research
| Name | Description | Links | Fees |
|---|
| Lean 4 | An interactive theorem prover and functional programming language, serving as the core infrastructure for formal AI research and automated theorem proving (e.g., AlphaProof, DeepSeek-Prover). | GitHub | Free |
| AMiner | AI-powered academic research and tech intelligence platform providing paper search, patent search, literature tracking, and scholar profiling | URL | Free |
| alphaxiv | An open academic discussion community based on the arXiv platform that allows users to comment line-by-line, ask questions, and interact in real-time by replacing the paper's linking domain (arxiv.org for alphaxiv.org) directly on the paper's page. And provides AI features such as Ask AI and AI-generated article blogs | URL | Free |
OCR
| Name | Description | Links | Fees |
|---|
| Umi-OCR | Comes with a highly efficient offline OCR engine. As long as the computer performance is sufficient, it can be faster than online OCR services. | GitHub | Free |
| light-ocr | Fast, offline OCR for Node.js and C++ with bundled PP-OCRv6 models and cross-platform runtimes. | GitHub | Free |
| allenai/olmocr | A toolkit for training language models to work with PDF documents in the wild. Online demo: https://olmocr.allenai.org/ | GitHub | Free |
AI Detection
| Name | Description | Links | Fees |
|---|
| SynthID Detector | Google DeepMind's official portal for verifying AI-generated media — expanded in October 2026 with OpenAI, NVIDIA and Kakao (Apple joining soon) into a cross-vendor coalition for content provenance. Upload images, audio, video or text to check for SynthID invisible watermarks; partial matches highlight the watermarked region. Watermarks are embedded in pixels/waveforms rather than metadata, surviving screenshots, compression and crops. Detects watermark-carrying content only — not a generic AI-content detector. Free, available globally in English. | URL | Free |
| Content Credentials Verify | Free C2PA provenance inspector from the Content Authenticity Initiative. Displays signed Content Credentials, including available creator, tool, editing-history, and AI-generation disclosures, and helps inspect whether credentials validate. Results depend on the credentials attached to the file: missing credentials do not establish whether media is human-made or AI-generated, and valid credentials do not prove the depicted claim is true. | VerifyHow it works | Free |
Humanoid Robots
| Name | Description | Links | Fees |
|---|
| Figure 03 | Figure AI's third-generation humanoid robot, powered by the in-house Helix vision-language-action model. The company raised over $1B in Series C funding in 2025 at a $39B valuation; F.03 is ramping into mass production and deployed at BMW factories.More Info | URL | |
| Atlas | Boston Dynamics' new all-electric humanoid robot | URL | |
| Optimus Gen 2 | Tesla's humanoid robot | URL | |
| Apollo | Apptronik's humanoid robot, now iterated to Apollo 2, with partners including Google DeepMind, NVIDIA, Mercedes-Benz, and GXO, focused on logistics and manufacturing. | URL | |
| GR-1 | Fourier's humanoid robot | URL | |
| Digit | Agility Robotics' humanoid robot | URL | |
| NEO | 1X's consumer humanoid robot for the home, now open for pre-order ($200 deposit) | URL | |
| H1 | Unitree's humanoid robot | URL | |
| Phoenix | Sanctuary AI's humanoid robot, known for its hydraulic dexterous hands; in 2026 the company shifted its strategy toward providing Physical AI software for other robotics platforms and expanded into industrial robotics. | URL |
Embodied AI & Simulation
| Name | Description | Links | Fees |
|---|
| Genesis World | Now renamed Genesis World (v1.0 released May 2026, maintained by Genesis AI). High-performance simulation platform for general-purpose robotics and embodied AI: a unified multi-physics engine, the Nyx photo-realistic renderer and the Quadrants compiler for training AI agents in complex physical worlds. | GitHub | Free |
Become Sponsors
This list is licensed under CC BY 4.0 — free to share, translate, and reuse it with attribution.
