Ground Truth.
AI, checked against the source.
Hand-picked AI tools you can actually use today — models, apps, and open-source projects that are shipping now. Each links straight to the source.

AI assistant / coding agent

Kimi (Kimi K2.6) →

Moonshot AI's web assistant and agent, running the open-weight Kimi K2.6 model; free to use in the browser for chat and long-horizon agent tasks, with the weights also downloadable for self-hosting.

coding · ai-agents · open-weight-models · chat · free

AI compiler / runtime

Modular MAX + Mojo →

A programming language (Mojo) and compiler/runtime (MAX) for running AI models efficiently across different hardware instead of being locked to one chip vendor; now being acquired by Qualcomm but still openly available to developers.

compiler · runtime · mojo · inference · infrastructure

AI in the browser

Gemma-4 WebGPU Kernels →

A demo running Google's Gemma-4 model directly inside a web browser using your device's graphics hardware — private, on-device AI with no server and no data leaving your machine.

on-device · browser · webgpu · privacy

AI video production

OpenMontage →

An open-source system that turns an AI coding assistant into an automated video-production studio, with a large library of pipelines, tools, and agent skills for editing and assembling video.

video · agents · open-source · creative-tools

Agent / automation

Gemini 3.5 Flash computer use →

Google's fast model can now operate a browser, phone, or desktop directly as a built-in tool, with optional confirm-before-acting and auto-stop-on-attack safeguards for building automation agents.

agents · computer-use · automation · google · gemini

Agent deployment infra

Cloudflare Temporary Accounts →

Lets an automated agent deploy and run on Cloudflare before a human signs up, removing the account-creation step from agent workflows.

infra · agents · deployment · cloudflare

Agent framework

DeerFlow →

ByteDance's open-source agent harness that breaks a long task into specialist sub-agents running in parallel, executes code safely in sandboxes, keeps memory across sessions, and produces reports, slides, and pages; built on LangChain and works with multiple model providers.

ai-agents · open-source · research · developer-tools

Agent security scanner

NVIDIA SkillSpector →

A scanner that inspects agent skills for security problems before you run them -- a static safety check for the fast-growing agent-skill supply chain.

security · agents · skills · scanner

Build with your own documents

RAGFlow →

An open engine for building AI question-answering over your own files and documents.

rag · documents · open-source

Coding agent

Claude Code →

Anthropic's command-line coding agent that reads a whole codebase, edits files, runs tests and fixes failures on its own; it is the tool behind Anthropic's disclosure that Claude now authors most of its production code.

coding · ai-agents · anthropic · developer-tools

Create images & video

ComfyUI →

A visual, node-based studio for generating images and video with open models. Powerful and endlessly extensible.

image · video · open-source · creative

Cut AI agent costs

Headroom →

A drop-in proxy that sits between your coding assistant and the AI model and automatically compresses bulky tool outputs, logs, and retrieved text before they reach the model — cutting token usage sharply without changing your code.

agents · cost-optimization · open-source · developer-tools

Diffusion LLM API

Mercury 2 (Inception Labs) →

An API-only diffusion language model pitched on raw speed, claiming to out-pace open diffusion models on tokens-per-second for latency-sensitive generation.

diffusion · llm · api · low-latency

Enterprise agent platform

Claude Tag (agent identity access model) →

Anthropic's product for putting Claude to work in shared team channels, now with an access model that gives each agent its own scoped accounts in the systems it touches -- GitHub, Slack, a data warehouse -- instead of borrowing an individual user's permissions, so every action is bounded and audited.

ai-agents · enterprise · security · anthropic

Find models & datasets

Hugging Face →

The main hub for finding, downloading, and trying open AI models and datasets — the field's town square.

models · datasets · hub

Forecasting model

TimesFM →

Google's pre-trained foundation model for time-series forecasting — predicting things that change over time, like demand, traffic, or sensor readings — usable out of the box without training your own model.

forecasting · time-series · open-source · google

Give AI agents code memory

codebase-memory-mcp →

Indexes an entire codebase into a persistent, queryable knowledge graph so AI agents can understand large projects fast. Supports a huge range of programming languages, answers queries near-instantly, and ships as a single dependency-free binary.

agents · code-intelligence · open-source · developer-tools

Hosted open-model API

GLM-5.2 on Baseten →

The top trending open-weight model served as a fast hosted endpoint, reported at 280+ tokens/sec on Blackwell-class hardware -- an open model you can call like a closed one.

open-weight · llm · coding · inference · api

Local coding model

Gemma-4 12B Coder (GGUF) →

A fine-tuned, locally-runnable version of Google's Gemma-4 model specialized for programming tasks, packaged in a format that runs efficiently on everyday consumer hardware.

coding · local-ai · open-source · gguf

MCP app framework

Skybridge →

A framework for building MCP-native apps -- interactive tools an AI assistant can open and use directly, pitched as 'MCP apps are the new website.'

mcp · framework · apps · developer-tools

Model-orchestration API

Sakana Fugu →

A single OpenAI-compatible endpoint that dynamically routes each request across several frontier models, so you call one API and get a coordinated multi-model answer.

orchestration · multi-agent · api · routing

Open language model

LLaDA / iLLaDA →

An openly released diffusion language model (weights and code) that generates text by refining a whole passage at once rather than one word at a time, useful for experimenting with non-autoregressive generation and infilling.

open-weights · diffusion · language-models · research-grade

Open large language model

GLM-5.2 →

A flagship openly-available language model with a very large context window for long documents and code. Free to download and run yourself, with compressed versions for more modest hardware.

open-source · llm · long-context · local-ai

Open model download

Kimi K2.6 weights (Hugging Face) →

The actual Kimi K2.6 model weights, published under a modified-MIT license for anyone to download, run, and build on; large enough that full-strength use needs a multi-GPU node.

open-weight-models · self-hosting · moe · coding

Open-weight model

MiniMax-M3 →

A natively multimodal open model trained on text, image, and video from the first step, with a million-token context and a sparse-attention design built for speed; downloadable for self-hosting and also offered through MiniMax's own API and agent platform.

open-weight-models · multimodal · long-context · ai-agents

Open-weight model (agent world model)

Qwen-AgentWorld →

Alibaba's open language world model that simulates agent environments -- browser, terminal, phone, coding workspace and more -- so other agents can be trained inside the simulation. Released with open weights and code in two sizes.

open-weight-models · ai-agents · world-models · reinforcement-learning

Open-weight model (self-host)

DiffusionGemma →

Google's open-weight text-diffusion model that generates text in parallel blocks instead of one token at a time; Apache-2.0, runnable locally, with community tooling already shipping.

open-weight · diffusion · text-generation · self-host

Run AI models efficiently

SGLang v0.5.13 →

A high-performance open serving engine for language models. The new version turns on faster 'guess-ahead' decoding by default and trims scheduling overhead for quicker responses.

inference · serving · open-source · infrastructure

vLLM v0.23.0 →

The widely-used open engine for serving language models fast and cheaply. The latest release adds smarter memory handling for long conversations and faster GPU execution.

inference · serving · open-source · infrastructure

Run models on your computer

LM Studio →

A friendly desktop app to find, download, and chat with open models on your own machine — no command line needed.

local · desktop-app · models · free

Ollama →

Download and run open AI models locally with a single command. The easiest on-ramp to running your own model.

local · models · cli · free

Open WebUI →

A polished, ChatGPT-style web interface for the open models you run yourself.

local · chat-ui · open-source

llama.cpp →

The lean, fast engine that makes big models run on ordinary laptops; powers much of the local-AI ecosystem.

local · inference · open-source

Security coding assistant

OpenAI Codex Security (Daybreak) →

An in-IDE plugin from OpenAI's Daybreak initiative that finds, validates, and fixes software vulnerabilities, plus an open-source remediation program run with Trail of Bits and HackerOne.

security · coding-agent · ide · vulnerabilities

Serve at scale

vLLM →

The popular open engine for serving AI models fast and efficiently when you need to handle real traffic.

serving · infrastructure · open-source

Train & fine-tune AI models

veRL →

The open RL post-training framework used by most research labs training reasoning models today. Run GRPO, PPO, and related reward-training methods on your own models.

rl-training · fine-tuning · open-source · reasoning