AI Tools & Services

Tokenomy forecasts token count, dollars, latency & energy before an API call, so your team ships without surprise bills.

Free AI routing with smart 3-tier fallback. Maximize subscriptions, auto-switch to cheap/free models. Never stop coding with Claude Code, Codex, Gemini CLI.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

SwarmUI - A Modular AI Image Generation Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility. Supports AI image models (Stable Diffusion, Z-Image, Flux, Qwen Image, etc.), and AI video models (Wan, Hunyuan Video, etc.), with plans to support eg audio and more in the future.

[CVPR 2025] Official implementation for "Empowering LLMs to Understand and Generate Complex Vector Graphics" https://arxiv.org/abs/2412.11102 - ximinng/LLM4SVG

Transform your creative vision into scalable workflows with Figma Weave. Integrate AI models and editing tools in one seamless, node-based platform.

FLORA is the AI-powered canvas for designers, brand teams, and agencies. Generate, edit, and produce visuals across 50+ models in one workspace.

VMs starting at $1.20/day. USDC (x402) or card. SSH in under 60 seconds.

AirLLM 70B inference with single 4GB GPU

Agent = Model + Harness. Flue is the TypeScript framework for building modern agents — programmable, deployable anywhere, from chatbots to coding platforms.

UI Demo of the TensorStack SDK. Contribute to saddam213/AmuseAI development by creating an account on GitHub.

AI-powered screen memory — captures, analyzes, and lets you search/chat your screen history. Powered by Gemma 4 . 100% local, 100% private. - ayushh0110/ScreenMind

Build enterprise agentic AI with benchmark-leading open reasoning and multimodal models.

A self-learning AI companion that lives on your Mac. She remembers you, listens, learns who you are. No cloud, no subscription. $25 once, 7 days free.

Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly. - Andyyyy64/whichllm

The first AI consumer layer - build, share, and own AI Agents.

Ideogram 4: Open image model at the forefront of design - ideogram-oss/ideogram4

Run Llama, Gemma, Qwen, DeepSeek, and more on your iPhone, iPad, and Mac. Optimized for Apple Silicon. Offline. Private.

PicoClaw that works with Oracle AI Database

Automated content moderation solutions with human-level accuracy