Clean the context before it hits the model. AgentSkin keeps task-relevant facts and strips low-value API, JSON, and terminal noise.
{ "input": "{...}", "url": "https://api.github.com/repos/acme/demo" }
Use the compress MCP tool. In auto mode, parseable JSON is sent through the semantic pruning pipeline.
{ "input": "...terminal output...", "command": "git status" }
Supplying command selects command-aware reduction through Tokenjuice.
Other public products and experiments from Nichols AI. AgentSkin is the context layer; these are the places it lives beside.
Applied AI systems, agent infrastructure, production software, and business automation.
Turn YouTube videos, webpages, and documents into clean notes without the copy-paste mess.
A public build experiment from the Nichols AI lab, available directly on GitHub.