structured-outputs 开源项目推荐（497 个）

PrefectHQ /marvin

一个环境智能库

AhmadHassan-BTed /Noria

面向消息平台的智能体式提取器。Noria 通过聊天接收消息和 URL；抓取网页数据，依据自定义评分矩阵（例如职位、奖学金）评估内容；并将带有计算出的匹配分数的结构化摘要直接发送到指定的消息接收号码。

OmniJev /awesome-jev-gallery

🔥🔥 Awesome Jev: open-source models, projects, benchmarks, and independent evaluations for Jev and System One models.

cubist38 /mlx-openai-server

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.

Heman10x-NGU /openJev-verdict-2.0

Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)

arena-ai /structured-logprobs

OpenAI's Structured Outputs with Logprobs

velocitybolt /open-extract

Structured Data Extractor for AI Agents. Search your documents or the web for specific data and get it back in JSON or Markdown in a single tool call.

Heman10x-NGU /Verdict-open-jev

基于 ModernBERT（151M）的非自回归决策引擎，具备校准不确定性（RLCD）、TypeSafe AI Jev 基准审计以及浏览器内 WebGPU 演练场

andyrewlee /awesome-system-one

A list of System One models (also called decision models): Jev, the first, plus open and hosted alternatives, agents, tools, SDKs and benchmarks.

intikhab49 /open-jev-typed-decision-engine

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

drivly /ai

Agentic Workflow Platform

TypeSafeAI /jev-harness

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

Joakimpalm-Zen /xyntetik-runner

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, byte-reproducibly. Tool calls survive the token limit; every run replays as a signed receipt. CPU/CUDA/Metal, OpenAI- and Anthropic-compatible.

amareshhebbar /TrueNorth

Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in safety, async follow-ups, and native compliance

centminmod /or-cli

通过 OpenRouter API/Cloudflare AI Gateway 或本地自托管的 Ollama 与 AI 模型交互的 Python 命令行工具。可选支持 Microsoft LLMLingua 提示词 token 压缩

nexxtmove /json-schema-kit

🧰 Some (very) simple helper functions for writing concise JSON Schema — perfect for OpenAI Structured Outputs.

r-Larch /OpenAi.JsonSchema

OpenAi.JsonSchema is a lightweight library for generating valid JSON Schema for OpenAI models' Structured Outputs feature. It supports a wide range of types, ensures compatibility with OpenAI's JSON Schema format, and leverages C# descriptions and attributes for schema generation.

trickymind1324 /personal-finance-agent

Personal finance agent that decides whether an expense is safe — pay in full, split, use installments, or wait — from a 90-day balance forecast over real transaction history, with a deterministic decision core and a narrow multimodal evidence layer for receipts and messages.

tensorlakeai /OpenIngest

Production grade Document AI workflows run on Tensorlake

cakbudak /kyn-agent-studio

Build typed agent workflows and operate every run from authoritative evidence — OpenAI Build Week 2026