Tern offers an AI‑driven platform that scans an entire code repository and returns a searchable, spreadsheet‑style inventory of files, owners, and code patterns related to a natural‑language change request. The tool helps engineers plan large migrations, generate bulk edits, and coordinate cross‑team updates through GitHub integration and credit‑based execution.
Funding
$1.6M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Engineering teams often need to perform large‑scale codebase changes—such as framework upgrades, library swaps, or deep refactors—but lack a clear view of all affected files, owners, and patterns before they start coding. This uncertainty leads to missed dependencies, broken builds, and extensive manual effort to locate relevant code.
Solution
Tern provides an AI‑driven analysis platform that ingests an entire repository and returns a structured, spreadsheet‑style inventory of files, owners, and code patterns related to a described change. Users input a natural‑language description of the intended modification, and Tern scans the codebase to surface every component that may be impacted. The results can be filtered, exported, and used to plan migrations, generate shims, or create batch edits. Tern also offers AI agents that can automate bulk edits based on the inventory, allowing developers to focus on judgment calls while the tool handles repetitive transformations. The platform integrates with GitHub via an app and supports credit‑based usage for spreadsheet fills, agentic runs, and workflow executions.
Target Audience
Primary users are software engineers and technical leads who manage large codebase migrations, as well as DevOps teams that need to coordinate cross‑team code changes and ownership tracking.
Features
- Full‑repository ingestion with AI‑powered code understanding to produce a searchable inventory of files, owners, and patterns
- Natural‑language query interface that returns results in a spreadsheet view for easy review and export
- Credit‑based execution model covering spreadsheet fills (1 credit), agentic fills (25 credits), and per‑row workflow runs (100 credits)
- GitHub app integration for seamless access to private repositories and automated pull‑request generation
- Support for a variety of migration types: framework/runtime upgrades, breaking‑change adaptations, library swaps, deep refactors, and code standardization
- Configurable AI models and prompts to tailor transformation logic to specific codebases