AI Apps

Watch an AI use a sandbox desktop beside a chat, including screenshots, clicks and shell commands.

• Agent application development
• Tool and API integration

Explore voice-driven browser demos for architecture diagrams, interface generation and live translation.

• Tool and API integration
• App and website builder

Watch step-by-step function explanations alongside code, variables and a connected React app in VS Code.

• Code quality and comprehension

Generate UiPath test cases from workflow descriptions and analyse results with Claude.

• Software testing

An open-source platform for building AI agent skills with visual workflows, each skill with its own versions.

• Agent application development
• Workflow automation

Alibaba's open-source AI code review CLI, which pairs rule-based checks with an LLM to review code changes and files.

• Code quality and comprehension

An open-source long-term memory platform for AI agents that organises documents, code and chats into a searchable knowledge graph.

• Knowledge management
• Agent framework

Uses LLMs to pull facts out of documents into structured data with sources, as a library developers call from their own code.

• Data and content transformation
• Source citation

NVIDIA's open-source scanner that checks an AI skill for malicious patterns, data exfiltration and supply-chain risks before you install it.

• Code security audit

Turn content written by AI or by people into a shareable web page through MCP or an API, from a service that AI built and runs day to day.

• Developer deployment
• Tool and API integration

Google's quality agent for production ADK agents that reads their telemetry and uses AI to review conversations and diagnose failures.

• Agent monitoring
• Application observability
• Model evaluation

A daily roundup of new AI terms, models, products and repos that uses a small model to tell which ones are real new names worth following.

• Information monitoring
• Research assistance

Pollen Robotics' open-source software for a tiny biped robot that walks using reinforcement learning policies, with a simulation you can run on a computer.

• Robotics

A directory of 253 open-source SEO and GEO tools for Claude Code, Codex and other AI agents, sorted into 8 groups.

• SEO and GEO optimization
• Tool and API integration

An open-source desktop and mobile AI agent that brings Claude Code, Codex and several models into one assistant that works in your projects and apps.

• General AI assistant
• Multi-agent orchestration
• Tool and API integration

An open-source multilingual text-to-speech model from k2-fsa that its makers say covers over 600 languages, with voice cloning and voice design.

• Text-to-speech
• Voice cloning
• Voice design

Read long texts in folded layers, from the full text down to a one-line gist, and ask AI about any passage with every answer citing the paragraph it rests on.

• Summarization
• Research assistance

Qwen's open-source text-to-speech models, which can design a voice from a description or clone one from a few seconds of reference audio, in 10 languages including Chinese and English.

• Text-to-speech
• Voice cloning
• Voice design

Different AI models each build a web page from the same prompt under the same limits, shown side by side to compare, with a Chinese interface.

• Model evaluation
• App and website builder

A local proxy that sits between an AI coding agent and its model API, compressing long sessions and letting the model recover details when needed.

• Context management

A research-preview sandbox tool Anthropic built for Claude Code; Anthropic says it enforces filesystem and network restrictions on any process at the OS level, without a container.

• Sandboxing and permission isolation

A Chrome extension that clips web pages and video or podcast transcripts into Obsidian and lets you ask AI about the whole text or a passage.

• Web clipping
• Knowledge management
• Research assistance

Train a small language model of about 64M parameters from scratch, with open-source code and a tutorial, for developers who want to see how large language models are built.

• Model training
• Interactive learning

Compresses logs, files and conversation history on your machine before they reach the LLM, so coding agents use fewer tokens.

• Context management

An open-source AI coding agent that reads, edits and runs your project from the terminal or a desktop app, using the model you choose.

• AI coding

An open-source foundation model for financial candlestick (K-line) data that forecasts price movements, for research use, not investment advice.

• Financial model research

A desktop workbench for running several coding agents side by side, each in its own worktree, then comparing results and merging the best.

• Multi-agent orchestration
• AI coding

Generates command-line interfaces for desktop software so AI agents can drive tools like GIMP, Blender and LibreOffice.

• Tool and API integration
• Workflow automation

A local search engine that indexes your code, docs and logs so a coding agent can search them instead of reading files one by one.

• Code search
• AI search

Turns your Claude Code, Codex and Mistral Vibe sessions into an animated stand-up call, so you can see which agent is working, stuck or burning tokens.

• Agent monitoring
• AI coding

An open-source engine for running and serving large language models, turning Hugging Face models into an API you can call.

• Model inference and serving
• Developer deployment

A Go library that analyses AI coding sessions, PRs and issues to show teams how much code AI writes and what kind of work it goes into.

• Agent monitoring
• Code quality and comprehension

OpenAI's official command-line tool for generating images, uploading files, submitting batches and checking API results from the terminal.

• Tool and API integration
• Image generation
• Workflow automation

A 360M-parameter model that runs locally in your browser and imagines a terminal screen frame by frame, without running any real commands.

• Local model runtime
• Interactive digital experience

An open-source Python framework for building AI agents from language models, MCP tools, memory, human approval and tracing.

• Agent framework
• Agent monitoring
• Tool and API integration

Recursive's local inference engine for running its language models on a high-end Mac, with pi and OpenCode built in and an OpenAI-compatible API.

• Local model runtime
• Model inference and serving

A DeepSeek Harness plugin that lays out the context, tool calls and attachments inside each AI coding agent session.

• Context management
• Agent monitoring

Speeds up large language model inference with speculative decoding, for teams that host their own models.

• Model inference and serving

DeepSeek's open-source high-performance inference framework, the one behind its own large-scale production services, for GPUs and NPUs.

• Model inference and serving
• Developer deployment

A guide and template kit for building with AI coding agents, with three paths: set up your machine, start a new app, or take over an existing one.

• AI coding

A decision-model API for AI agents: ask a question with set options and get back a probability for each.

• Agent decision model

A shared workspace layer for AI coding agents, giving each one its own writable space with branching, merging and rollback.

• Context management
• Multi-agent orchestration

A model quality-check plugin for the Magpie gateway: it gives your main model a reasoning test and holds requests until you confirm when it fails.

• Model evaluation

A plugin for the LLM command-line tool that lets a model query a Datasette instance you point it at, read its tables and run SQL.

• Data and database querying
• Tool and API integration

A pre-push quiz for AI-written code: a separate model asks you about the change so you know you understand it before it ships.

• Code quality and comprehension

An open-source observability platform for AI agents that records every run and flags the problems you describe in plain English.

• Agent monitoring
• Application observability

A Google Research framework that improves an agent's prompts, tools, memory and skills while it works, without changing the model itself.

• Agent framework
• Model evaluation
• Tool and API integration

An open-source app for running large models on your own computer to chat, code and read images, and to serve local models to Claude Code and Codex.

• Local model runtime
• General AI assistant
• AI coding

An open-source toolkit from Cloudflare, with an SDK, a CLI and a platform, for building Vite apps with a backend and deploying them to Cloudflare.

• Developer deployment
• Tool and API integration

A command-line tool that searches code and docs by words and meaning, all on your own machine.

• Code search
• AI search

An experiment that rewrites ordinary JavaScript into a neural network, with no training and exactly the same results.

• Model training

An AI evaluation metric in DeepEval: you write the questions, the Jev model returns probabilities, and a fixed formula gives the score.

• Model evaluation

An open-source tool that makes AI coding agents answer in fewer words; we recommend its caveman Skill, which leads with the answer and keeps code and errors exactly as they are.

• AI coding
• Context management

An open-source, self-hostable observability platform that puts logs, traces, errors, session replays and AI call tracing in one place.

• Agent monitoring
• Application observability

A command-line tool that searches, installs and updates Skills for 45 AI coding agents, including Claude Code and Cursor, from one place.

• Tool and API integration
• App and service management

Turns your AI coding tools' token usage into a macOS wallpaper that redraws itself every 30 minutes.

• Usage and cost tracking
• Agent monitoring

Open-source text-to-speech models from Resemble AI: give them a short reference clip and they read your text in that voice, in 23 languages including Chinese.

• Text-to-speech
• Voice cloning

A companion that lives in your Mac's notch, shows what your coding agents are doing and lets you approve or deny their permission requests on the spot.

• Agent monitoring
• AI coding

A lightweight Python runtime for AI agents where every stage can be swapped out with a plugin.

• Agent framework
• Tool and API integration

A self-hosted personal dashboard for managing apps, AI agents and knowledge on your own dev machine.

• App and service management
• Multi-agent orchestration
• Knowledge management

A slimmed-down AI assistant for Chromebooks and low-power devices, focused on electronics and hardware design.

• General AI assistant
• Hardware and engineering learning

Describe an idea in plain language and Lovable builds a full-stack website or app ready to ship.

• App and website builder
• Developer deployment

An AI code editor from Anysphere that can hand whole development tasks to agents.

• AI coding