Discover products

Play text-based RPGs and create your own games effortlessly.

Buy OpenAI API keys at 90% off, Claude at 85% off. Compare ChatGPT API key prices across fingerprint-verified.

Create AI photos with GPT Image technology. OpenAI image generator transforms text prompts into stunning visuals.

Distributed LLM inference. Chat for free, powered by GPUs worldwide. No signup. Open source.

One API key for every model: hosted providers, your own keys, your own GPUs. Routing, access control, and attribution for everything your agents call.

openheim is an open-source Rust LLM agent. Interactive TUI, ACP stdio agent for Zed and JetBrains, MCP server integration, and self-hosted WebSocket server. Supports OpenAI, Anthropic, Gemini, Ollama, and any OpenAI-compatible endpoint.

Deploy AI agents via Telegram with ease.

Video.js v10 is a ground-up rewrite combining four open source players into one modern framework — 88% smaller default.

Claw Code is an open-source AI coding agent framework — a clean-room Python and Rust rewrite of the Claude Code.

Railo is the fixed point in your GitHub workflow: scan PR diffs, apply rule-based patches, open merge-ready fix PRs. No LLM guesswork. Public beta.

Corsair helps AI products add secure, multi-tenant integrations with OAuth, permissions, MCP, webhooks, and hosted or self-hosted execution.

Lastly the openai model gpt-5.4 gained in popularity within the OpenClaw community (maybe this is the reason).

An open-source AI pipeline that transforms public domain literature into stylistically consistent graphic novels.

Kiso is a publishing engine that turns Open Knowledge Format (OKF) bundles into static websites for humans and AI.

A community of builders sharing GPUs to run open models at a flat rate. OpenAI-compatible API, zero logs, spots limited by compute.

TRACE is an open specification for hardware-attested AI agent governance records. A Trust Record states what ran, where, under which policy, touching which data, calling which tools, in a form any third party can verify without trusting the operator.

Wan 3.0 is Alibaba's upcoming open-source video model — 60B parameters, native 4K output, up to 30-second.

Point a projector and a webcam at a wall, draw with a laser pointer, and the projector paints your strokes. Open source, runs in the browser.

DataZen is a free open-source desktop database workspace: natural-language SQL, one-click error diagnosis, EXPLAIN analysis, charts, cross-database workflows, and a built-in MCP server for AI agents. Local-first, under 15 MB.

An open source password vault for Windows. Import passwords, 2FA codes, and recovery details. Sesame never receives your vault. Free download.

Share your local AI agents with your team. Claude Code, Codex, Cursor, OpenCode, and Pi get persistent identities and memory — while running on your machine. Open source.

TokenGO self-operated inference API for open-weight LLMs and video models. OpenAI-compatible. Cheaper than OpenRouter per model. US-governed.

FlexAI runs managed inference on 20+ open models and agent workloads through one OpenAI-compatible key, from serverless to dedicated endpoints and private cloud.

Sim is the open-source AI workspace where teams build, deploy, and manage AI agents across 1,000+ integrations and every major LLM, visually or with code.

Create an API cost estimate for OpenAI, Claude, Gemini, and other models from input tokens, output tokens, requests, active users, and current prices.

Discover the most useful community plugins for Claude Code and OpenAI Codex. Curated, ranked by what people.

Democratic California Attorney General Rob Bonta subpoenaed OpenAI on Wednesday as the state investigates cybersecurity incidents involving the AI company and its models. The investigative subpoena comes as part of the California Department of Justice’s inquiry into a July incident involving OpenAI and AI development platform Hugging Face. OpenAI models broke out of testing environments, […]

an async Rust LLM gateway routing to 330+ models — OpenAI, Anthropic, Google, Meta, Mistral, and every model on.

Join the Notifier Dev - Early Adopter group for release alerts when The Notifier API and developer sandbox open – a privacy-first way to send user-controlled alerts without phone numbers or email addresses.

Pick a Mac mini, Mac Studio, DGX Spark or Strix Halo box, see which open models fit and how fast they run, and how much usage it takes to break even against paying an API. It is willing to say: it doesn't.