How We Got LLMs to Recommend Our Open Source Library — Christopher Burns, Inth
Christopher Burns from Inth describes how his open source library c15t (a consent banner) began being recommended by AI agents — from April 13th, this became the largest source of new users.
To make his project AI-friendly, he built a documentation pipeline that generates files specifically for agents. His main insights: write llms.txt by hand instead of generating it, serve markdown instead of HTML, and bundle documentation directly in the package because agents typically read source code and node_modules rather than visiting websites. He saved nearly half the tokens agents need by sending bundled markdown inside the package.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago