hardness1020hardness1020/learn-agent-architectureLearn Agent Architecture
Explains how modern AI agents are built, covering loops, tools, memory, and more. Section 22 integrates TypeSafe Jev as a typed decision edge in graph engineering.
972945MIT
Jev Exam Question Categorisation
An integration using TypeSafe Jev/System One to classify and group Polish exam questions, used in production at matura.lol.
该仓库在 README 中详细说明如何调用 TypeSafe Jev / System One API（api.typesafe.ai），包含可运行示例、生产管道及与 matura.lol 的集成，属于真实使用。
· 0 starsOpen on GitHub
More like this
hardness1020hardness1020/learn-agent-architecture
kylemclarenkylemclaren/jevqljevQL: Semantic SQL for Postgres
jevql is a CLI/SDK that adds Jev semantic predicates, choices, and scores to ordinary Postgres SQL. It calls TypeSafe AI's System One model via the Jev API and supports Go, TypeScript, Python, MCP, and HTTP.
1202MIT
frostneyfrostney/clean-code-reviewClean Code Review
Uses TypeSafe's Jev evaluation model through eve and the AI Gateway to judge every file in a pull request against Clean Code, then Luna writes the review. Includes a live Next.js web app, CLI scripts, and an MCP server.
1011MIT