StarkSphere Labs
Sheet 03 · Products

We built our own infrastructure. In the open.

When a build needs memory, observability, or an agent runtime, we reach for tools we wrote and maintain, not a vendor you will still be renting in three years. These ship today, and they are the clearest proof of the engineering behind our service lines.

Collaborative docs · AI-native

Live

E.D.I.T.H

A real-time docs workspace with AI writing, inline mermaid diagrams and version history. Unlimited members, free — and every workspace serves an MCP endpoint your agent can read.

The product we write our own specs in — and the clearest proof we ship end-user software, not just infrastructure.

Agent memory · MCP-native

Live

extremis

A memory platform for AI agents with episodic, semantic, procedural, and identity layers, exposed over MCP.

This is the memory layer behind our organizational-memory builds.

LLM observability · on PyPI

Live

peekr

LLM observability and tracing. Auto-instruments OpenAI, Anthropic, and Bedrock with a couple of lines.

This is the tracing layer behind our LLM-observability and incident builds.

AI assistant · research

Research

Friday

A personal AI assistant research project: BDI reasoning and a persistent agent loop.

Where we work out the agent patterns that later harden into client builds.

Research project. No public link yet.

Want one of these built into your product? Let's scope it.