AI Agent Skills built for Founders who hate Marketing

Janus is a API router for AI models written in Go and has a Vulkan Model runner

Open source inference engine for agents that optimizes itself for your exact hardware. Compiles and tunes its kernels on your device, so open models run up to 2x faster than llama.cpp. Works on App…

Benchmark for tracking model capability after release.

Jeeves – Reasoning improves Jev-like decision models

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

The Agentrun Workflow DSL

A Programming Paradigm for Spatiotemporal Composability

Linux sandboxing that doesn't get in your way

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

ZK proofs over verifiable data for multi-dimensional governance power, incentives distribution, chat gating, and more.

A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

A clustered, Valkey-compatible database backed by object storage

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

Fast, accurate & comprehensive text measurement & layout

PKZip for LLMs

Embedded single-file knowledge graph database with vector search and full-text search for AI/RAG apps

The smallest possible complete Windows application

Nix-powered agentic reverse engineering environment

A featherweight framework for building your own LLM benchmarks

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

A tool for collaboratively refining your understanding in order to improve a situation.

A seed agent: the smallest starting point from which an agent can grow

Agent traces you can run, not just read.

LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and m…

Baochip 1x Silicon