
Sage AI
Sage AI is a YC Winter 2023 (W23) company. Based in San Francisco, CA, USA; Remote. Team of 2.
About Sage AI
Summary
Sage AI builds a self-generating, self-maintaining knowledge base for software codebases, aimed at engineering teams working with large or complex code. It parses source code into a symbol-level graph of functions, classes, types, and interfaces, then uses LLMs to write and continuously update documentation for each symbol. The product replaces manual documentation work and the slow, fragile process of onboarding engineers by keeping code knowledge current and queryable through a built-in chat interface.
Business model
SaaS subscription.
Go-to-market
Engineering teams and individual developers at B2B software companies are the buyers, reached through integration with existing source control workflows.
From the Y Combinator listing
Your self-generating, self-maintaining code knowledge base.
Sage is a self-generating, self-maintaining knowledge base for your code with in-built chat, accelerating expertise, and comprehension of any codebase. Documentation is perpetually stale, codebases become increasingly old, large, and complex, and knowledge remains siloed within individuals and teams. As a result, engineers take 8-12 months to become fully operational, enterprise code becomes slow and unmaintainable, and core knowledge is continually lost upon engineer turnover. Sage is changing this reality. We take your code and automatically generate a symbol-level knowledge base that self-updates to remain forever fresh. We integrate with source control to pull your code and generate a symbolic graph representation of functions, classes, interfaces, types, etc., automatically determining the relevant context for each symbol, and using LLMs to annotate and propagate documentation via traversals of the symbol graph. Sage revolutionizes the way teams and individuals interact with and understand their code, ensuring that knowledge is always accessible, up-to-date, and interactive.
Facts
- B2B / B2B -> Engineering, Product and Design
- San Francisco, CA, USA; Remote
- 2
- Active
- Early
Founders (1)
- Joshua Ying
Score every batch against your own thesis
GPAgent's sourcing agent reads every company in a batch, scores each one against your fund's thesis in a private workspace, and lines up the founders worth meeting before Demo Day. You decide who to contact. Your scores, notes, and pipeline never appear on these pages.
How Accelerator intelligence works