AI, reviewed .

AI voice platform for text to speech, voice cloning, dubbing, music and voice agents, now on its Eleven v4 models.

llama.cpp

Run models locallyC++132k stars

C/C++ engine for running LLMs locally on CPUs, Apple silicon and most GPUs, home of the GGUF model format.

Intercom Fin

Customer supportPay per use

AI customer agent that answers and resolves support, sales and ecommerce conversations, billed $0.99 per outcome.

Eleven v4 and v4 Turbo

ElevenLabsText to speech

ElevenLabs' expressive text-to-speech pair, tied for first on Artificial Analysis's speech arena; v4 Turbo is built for voice agents.

GPT Image 2.5 (Flare and Sunburst)

OpenAIImage generation

OpenAI's current image models: Flare for everyday generation and editing, Sunburst for precise multi-step edits.

GitHub MCP Server

GitHubDeveloper

GitHub's own MCP server: 93 tools for code, issues, pull requests, Actions and security alerts, hosted or self-run.

The best-reviewed tools

All tools

ElevenLabs

Audio & voiceFree plan

AI voice platform for text to speech, voice cloning, dubbing, music and voice agents, now on its Eleven v4 models.

ChatGPT

Chat assistantsFree plan

OpenAI's general-purpose assistant, now on GPT-6, with chat, deep research, ChatGPT Work and Codex in one app.

Claude Code

CodingPaid

Anthropic's coding agent that reads your repo, edits files and runs commands, in the terminal, IDE, desktop app or browser.

Hugging Face

Developer platformsFree plan

The main hub for open AI models and datasets, with app hosting, a multi-provider inference API and dedicated endpoints.

Intercom Fin

Customer supportPay per use

AI customer agent that answers and resolves support, sales and ecommerce conversations, billed $0.99 per outcome.

Canva

Design & slidesFree plan

Drag-and-drop design platform for social posts, presentations, video and docs, with Canva AI 2.0, Magic Layers and free Affinity.

Models, ranked

All models

Top-rated AI models
Model	Made by	Type	Open weights	Rating
Claude Opus 5.5	Anthropic	General purpose	No	4.7/5
Eleven v4 and v4 Turbo	ElevenLabs	Text to speech	No	4.7/5
GPT Image 2.5 (Flare and Sunburst)	OpenAI	Image generation	No	4.7/5
Claude Sonnet 5.5	Anthropic	General purpose	No	4.6/5
GPT-6.1 Sol	OpenAI	General purpose	No	4.6/5
Nano Banana 2.1	Google	Image generation	No	4.6/5
Voyage rerank-3	Voyage AI (MongoDB)	Embeddings & reranking	No	4.6/5
Claude Haiku 5.5	Anthropic	General purpose	No	4.5/5

MCP servers worth installing

All MCP servers

MCP servers let assistants such as Claude, ChatGPT and Cursor reach into other apps and data. These are the ones that earn a place in your setup, and the permissions each one asks for.

GitHub MCP Server

GitHubDeveloper

GitHub's own MCP server: 93 tools for code, issues, pull requests, Actions and security alerts, hosted or self-run.

Playwright MCP

MicrosoftBrowser & web

Microsoft's browser server: drives Chromium, Firefox or WebKit from accessibility snapshots, so agents act without vision.

Chrome DevTools MCP

Google (Chrome DevTools team)Browser & web

Google's server that hands agents a live Chrome plus DevTools: performance traces, network, console, heap snapshots.

Figma MCP Server

FigmaDesign & media

Figma's hosted MCP server: design context for coding agents, plus write tools that build frames, components and diagrams.

Stripe MCP

StripePayments & commerce

Stripe's hosted MCP server: four generic API tools reach most of Stripe, with OAuth per account and human sign-off on refunds.

Supabase MCP Server

SupabaseData & databases

Supabase's hosted MCP server: schema, SQL, migrations, Edge Functions, logs and branches, with project scoping and read-only mode.

Open source worth your time

All repos

PyTorch

Training & fine-tuningPython105k stars

4.9/5

The dominant deep learning framework: Python tensors and neural networks with strong GPU acceleration.

Hugging Face Transformers

Training & fine-tuningPython168k stars

The standard Python library for defining, loading, training and running open models for text, vision and audio.

llama.cpp

Run models locallyC++132k stars

C/C++ engine for running LLMs locally on CPUs, Apple silicon and most GPUs, home of the GGUF model format.

ComfyUI

Image & videoPython142k stars

Node-based interface and backend for running image, video and audio diffusion models locally.

LLMs from Scratch

Learning resourcesJupyter Notebook107k stars

Code for Sebastian Raschka's book on building a GPT-style LLM in PyTorch, step by step.

Qdrant

RAG & dataRust35k stars