search
Decisions API
Trends
- 1
OpenAI has introduced a new Decisions API designed to deliver fast AI-driven choices for applications and services. The tool is aimed at developers who need quick, automated decision-making built into their products. Details on pricing, availability, and technical capabilities remain limited, and reactions from the developer community are still forming as the announcement circulates.
Repos
- jaredpalmer/kev Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
- firelex/jeff Fine-tunes of Qwen3.5 and Gemma 4 for zero-shot classification
- Contrastive-LM/CLM
- ollaya-dev/ollaya Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollam
- PostHog/jeeves Jeeves – Reasoning improves Jev-like decision models
- tamaratran/fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one
- jev-chat/jev-chat-jarvis 装在手机上的对话副驾：在 QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框，发不发由你。非侵入，只读屏幕，不 hook 不改包。
- Rizzo-AI-Academy/rizzo-flow The open, local take on Jev: typed decisions from an LLM, without generating a single token
- mizorewww/laya-mlx Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or c
- githubnext/localjev
- mizorewww/laya-coreml Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reprodu