Self-hostable cloud coding agent based on Pi

A starter kit for animating hand-painted cartoons with Claude: p5.js + p5.brush, the Clawd character, 31 acted emotions and a guide for the model

Google's open agentic orchestration runtime

AI can draw UI directly on the Figma canvas via JavaScript, and read existing designs back as structured data. Works with Claude Code, Cursor, VS Code, and Windsurf. No API KEY required.

Open source alternative to Semrush and Ahrefs

Zero-shot text classification over plain HTTP — no API key, no account. One Cloudflare Worker, a CLI, and an MCP server. https://classifier.dev

Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

Open-source Grok Bot alternative. Choose your own model and sandbox.

👾 Open Computer Use – Open-Source Alternative to Codex Computer Use

A beautiful screenshot + screen recording + Loom alternative - all native, self hostable and free.

Cross-platform C++20 toolkit for reading SolidWorks® files (.SLDPRT, .SLDASM, .SLDDRW) without a SolidWorks installation. Includes a zero-dependency parser library, a recursive BOM builder, and a w…

DeepSeek Harness: Everything is a Plugin.

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

Language model tokenization at GB/s

Statically verify your layout code

A programmable tool and agent runtime for Pi

Billing engine for the serverless agency — a pi extension that meters agentic dev work like cloud compute and invoices it like a timesheet.

OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation requ…

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

The fastest JavaScript BPE Tokenizer Encoder Decoder for OpenAI's GPT models (gpt-5, gpt-o*, gpt-4o, etc.). Port of OpenAI's tiktoken with additional features.

Noumena's internal version of your favorite coding tui but improved and optimized for our inference stack

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Build cross-platform modern desktop apps in Go + HTML5

Archived educational snapshot of the Repo Prompt app

Open-source Firecracker microVM sandbox platform for AI agents

Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

llama.cpp fork with additional SOTA quants and improved performance