Open-source repos built for typed decisions like Jev
After tracing a support run where 37 of 44 model calls only picked the next branch, the author lists repos like Jev, laya and jev-mcp built for typed choices.
THEY RAISED $40M FOR AN AI THAT CAN’T WRITE, CAN’T CODE AND CAN’T EXPLAIN ITSELF in one traced support run, 37 of 44 model calls only picked the next branch, and these repos are built for that part 01 langextract (37.3k ⭐) structured information pulled out of text, with source grounding ▸ https://github.com/google/langextract 02 dspy (36.7k ⭐) programming language models instead of prompting them ▸ https://github.com/stanfordnlp/dspy 03 laya (30.3k ⭐) an open decision engine with typed choice, score and yes/no answers ▸ https://github.com/NandhaKishorM/laya 04 guidance (21.8k ⭐) a language for controlling large language models ▸ https://github.com/guidance-ai/guidance 05 jev-ultrafast (20.9k ⭐) a web agent where jev picks every browser action ▸ https://github.com/browser-use/jev-ultrafast 06 pydantic-ai (19.6k ⭐) agents that are typed end to end ▸ https://github.com/pydantic/pydantic-ai 07 outlines (15.9k ⭐) structured outputs from any model ▸ https://github.com/dottxt-ai/outlines 08 fast-jev-compaction (7.2k ⭐) a claude code plugin that scores every tool call with jev before compaction ▸ https://github.com/tamaratran/fast-jev-compaction 09 jev-review (650 ⭐) a staged code review workflow built with jev ▸ https://github.com/devagrawal09/jev-review 10 jev-mcp (507 ⭐) typed judgments from jev as mcp tools ▸ https://github.com/jkudish/jev-mcp a model that only returns typed answers can be wrong, but it can’t be malformed
This post quotes another post: x.com/thegreatest_sv/status/2102802378378621355