Find the original file, then read the claim in context. This library keeps official documentation, independent analysis, research papers, and working notes clearly labeled.
The 12-page Jev engineering note has circulated as a founder release, but its cover says it was independently compiled and is not endorsed by TypeSafe. Our Jev Engineering for Coding Agents PDF guide includes the download, ten harness ideas, a practical walkthrough, and a check of the claims most often repeated with it.
Resources are grouped by format. Labels describe provenance, not an endorsement or quality score.
The 12-page working note on context selection, routing costs, tools, and permission gates in a proposed Jev harness.
Source note: Based on design notes attributed to Diogo Almeida; the PDF says it is not affiliated with or endorsed by TypeSafe.
TypeSafe's explanation of state, typed questions, probabilities, and where Jev fits in a software workflow.
The original launch article from TypeSafe founder Diogo Almeida. Product and performance claims are publisher claims.
The research paper behind the widely shared 56.2% tool-turn and 46.5% token figures. This is not a Jev evaluation.
A community roundup linking 20 repositories, including coding-agent routers, review tools, context pruning, browser agents, and other Jev experiments.
Source note: This is a secondary project list. Each linked repository and its Jev integration needs its own source check; the post is not evidence that all 20 builds work as described.
Rahul's long-form X article sketches a coding loop where Jev routes task difficulty and retry decisions, Luna writes code, and tests verify results before escalation to Sol.
Source note: The article offers a configuration proposal, not a public working Jev-to-Codex integration or an independently measured savings result. Its $20 figure is the ChatGPT Plus base subscription, with Jev API usage separate.