First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

Native macOS App Store Connect tool with MCP. Submit iOS apps to App Store with AI agents

Local knowledge graph for Claude Code. Builds a persistent map of your codebase so Claude reads only what matters — 6.8× fewer tokens on reviews and up to 49× on daily coding tasks.

Use TradeRepublic in terminal and mass download all documents

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

GEO-first SEO skill for Claude Code. Comprehensive AI search optimization for any website — citability scoring, AI crawler analysis, brand authority, schema markup, platform-specific optimization, …

Open-source orchestration for zero-human companies

Hindsight: Agent Memory That Learns

π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.

Open-source Agent Operating System

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

Free and open node based generative workflows.

AI generated RPG with LiveKit and Inworld TTS 1.5 Max

A lightweight, Vercel AI SDK based coding agent library.

A collection of sample apps and recipes built with the TinyFish web agent. Open-source examples for you to learn & build!

🌋LavaSR: Fast Speech restoration and enhancement

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

PersonaPlex code.

Trade autonomously on Polymarket using AI Agents

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

[ICLR 2026] pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

bloom - evaluate any behavior immediately  🌸🌱

🕸️ Web apps in pure Python 🐍

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.