What's new

Private, local-first AI assistant that connects to Telegram, Discord and WhatsApp

Fast search on object storage

AI diff review for VS Code — see what an AI change actually touches before you merge it

State-of-the-art embedding models and rerankers purpose-built for retrieval and RAG.

Agent-first AI video editor that cuts, captions, and reframes footage from a prompt

Private, local-first AI meeting notetaker for macOS

AI-native distributed SQL database with built-in vector search, agent memory, and RAG pipelines

AI translation workspace with shared glossaries, styleguides, and decision-context memory

Token-level citation and attribution API for AI-generated answers

Conversational video AI — build real-time face-to-face agents with a developer API

Stripe's official SDK and MCP server for wiring AI agents into payments, billing, and customer operations.

Open-source sandbox infrastructure for long-running AI agents

Open-source, self-hosted AI coding assistant

Shared project memory for AI coding agents across Claude Code, Cursor, Codex, and Copilot

The SDK for browser agents

Reference MCP server for querying and analyzing SQLite databases through Claude and other MCP clients.

Industrial-strength natural language processing in Python.

Prompt-first AI web app builder that turns a URL or description into a live, hosted full-stack app.

AI office assistant that turns your documents and connected apps into a cited, agentic knowledge base

Conversational AI agents for enterprise customer experience.

Reference MCP server for structured, revisable step-by-step reasoning in any MCP host.

Enterprise-grade document parsing and extraction with citation-grounded structured output

4K image model with direct-editing, sketch-to-image and reference-driven generation, built for design pros.

The deep learning framework for professional AI researchers and ML engineers

Physics-based calculator that predicts LLM decode speed, memory fit, and quantization quality on any hardware.

An agentic AI browser from Perplexity that reads, reasons over, and acts on the pages you're viewing.

Turn casual selfies into studio-quality AI headshots in about 90 seconds.

Visual feedback for AI coding agents

Microsoft's official Model Context Protocol server for browser automation via Playwright.

A lightweight spec-driven framework for AI coding agents

AI that turns long videos into short viral clips ready to post everywhere

Describe a UI in natural language and see it rendered live in HTML, React, Svelte, or Web Components

An agentic browser from Opera built to act on the web, not just render it.

Open-source PWA for drafting manga storyboards (ネーム) with LLM-ready prompts and a structured OMNY data format.

Cursor for Designers — visually edit your React codebase with AI.

The official Notion MCP server: give Claude, Cursor, and Copilot typed access to your Notion pages, databases, and comments.

AI-scored async video interviews for SMB hiring teams

Real-time infrastructure observability with embedded AI anomaly detection and an AI co-engineer for root-cause analysis.

A cited-answers notebook that turns links, PDFs, audio and video into podcasts, flashcards, mindmaps and textbooks.

Market access skill that lets AI agents monitor and trade real markets

Interactive maps and embeddings for unstructured text, image, and multimodal data.

Turn a single topic or keyword into a finished HD short video, end-to-end.

Official TypeScript SDK for building Model Context Protocol servers and clients.

Open-source, lightning-fast search engine with built-in hybrid and vector search for RAG

100 models, 100 prompts, 30,000 answers — an interactive look at AI defaults

Reference MCP server that lets any LLM read, search, and manipulate local Git repositories.

Match LLMs to GPUs and plan multi-model AI stacks by VRAM, bandwidth and precision.

The kitchen-sink reference MCP server that exercises every corner of the Model Context Protocol

Python framework for building composable AI agents on the Model Context Protocol

One API, 200+ models, transparent pricing, and no vendor lock-in.