structured-output repositories
Trending repositories tagged structured-output, ranked by trending score. Updated daily.
-
1
AbdelStark/awesome-typesafe-jev
Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.
GitHub · HTML · 620 stars · 162 forks · +22 stars in 24 hours · Trending score 2.31
-
2
shcherbak-ai/contextgem
Extract structured data and insights from documents using LLMs and decision models
GitHub · Python · 2,095 stars · 189 forks · +15 stars in 24 hours · Trending score 1.90
-
3
cobanov/awesome-jev
A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.
GitHub · 600 stars · 138 forks · +12 stars in 24 hours · Trending score 1.87
-
4
aaddrick/building-with-typesafe-jev
Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
GitHub · Python · 158 stars · 12 forks · +10 stars in 24 hours · Trending score 1.66
-
5
Buffalo2024/Rulora
Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.
GitHub · JavaScript · 135 stars · 7 forks · 0 stars in 24 hours · Trending score 1.03
-
6
feigo313/dsh-structured
Persona mode + structured output for DSH: identity header, three cards and signature rendered by the plugin while the model only submits a persona JSON envelope.
GitHub · JavaScript · 11 stars · 0 forks · +3 stars in 24 hours · Trending score 1.01
-
7
aigengame/godot-agent
Godot automation for AI agents to build and verify projects through a CLI, Agent Skill, or MCP server, with structured results, headless operations, and live runtime control.
GitHub · Python · 58 stars · 10 forks · +3 stars in 24 hours · Trending score 1.00
-
8
MaximeRivest/functai
Typed functions whose body a language model writes: run them on tables, measure how often they're right, make them better. Python, TypeScript, R and Julia.
GitHub · Python · 91 stars · 5 forks · +3 stars in 24 hours · Trending score 0.94
-
9
nola-lang/nola
Nola - an AI-notation TypeScript superset (.tsi): infer functions and typed ask extractors, lowered to plain TS
GitHub · TypeScript · 9 stars · 0 forks · +3 stars in 24 hours · Trending score 0.93
-
10
Valen-Team/Valen
Open multimodal decision models, 0.8B to 27B, for text, images and video. Decide with probabilities over your own candidates and locate with bounding boxes, in place of generated text. Free API, ONNX, GGUF, vLLM and SGLang; fine-tuning code included.
GitHub · Python · 933 stars · 88 forks · 0 stars in 24 hours · Trending score 0.87
-
11
Zipstack/unstract
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
GitHub · Python · 7,460 stars · 760 forks · 0 stars in 24 hours · Trending score 0.85
-
12
crmne/ruby_llm
The Ruby AI framework.
GitHub · Ruby · 4,520 stars · 539 forks · 0 stars in 24 hours · Trending score 0.82
-
13
yzfly/awesome-jev-zh
Jev / TypeSafe System One 中文精选列表:官方资料、SDK、爆款应用、Agent 工具、开源复现与独立评测,附中文上手指南,每日自动收录 GitHub 热门项目。
GitHub · HTML · 97 stars · 24 forks · +1 stars in 24 hours · Trending score 0.73
-
14
zhulinchng/jevper
Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients
GitHub · Python · 21 stars · 5 forks · +2 stars in 24 hours · Trending score 0.72
-
15
GAIK-project/gaik-toolkit
Generative AI knowledge management toolkit: strategy, guidance, evaluation and reusable Python components.
GitHub · Python · 110 stars · 23 forks · 0 stars in 24 hours · Trending score 0.57
-
16
tamnd/kime
Typed decisions over text in milliseconds. A Rust inference engine and server that answers choice, score and yes or no questions with calibrated probabilities, compatible with Jev and Laya. The bar is 10x faster on every benchmark at equal or better accuracy.
GitHub · Rust · 8 stars · 0 forks · +1 stars in 24 hours · Trending score 0.52
-
17
rupeshpoojary9/poorjev
Open-source, local Jev alternative: a System One decision layer with provably calibrated confidence (ECE 0.170→0.071). Typed decisions, runs offline, no API key, no waitlist.
GitHub · Python · 11 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46
-
18
aliaihub/awesome-jev-usecases
Evidence-backed use cases, patterns, and guidance for building with Jev, TypeSafe AI's System One model. Every claim is labeled and sourced.
GitHub · 25 stars · 7 forks · +1 stars in 24 hours · Trending score 0.45
-
19
call518/LogSentinelAI
LLM-powered security log analyzer: detect threats & anomalies with zero regex — just declare a Pydantic schema. Real-time Telegram alerts, SIEM-ready with Elasticsearch/Kibana. Supports OpenAI, Ollama, vLLM.
GitHub · Python · 68 stars · 13 forks · +1 stars in 24 hours · Trending score 0.45
-
20
Dave-London/Pare
Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.
GitHub · TypeScript · 141 stars · 15 forks · 0 stars in 24 hours · Trending score 0.29
-
21
EnragedAntelope/EA_LMStudio
ComfyUI node for local LLMs and vision models via LM Studio: prompt enhancing, image captioning, reasoning extraction, structured JSON output and VRAM management.
GitHub · Python · 26 stars · 9 forks · 0 stars in 24 hours · Trending score 0.28
-
22
clifton/rstructor
Pydantic + Instructor for Rust: extract structured, validated data from LLMs (OpenAI GPT, Anthropic Claude, Gemini, Grok/xAI) into native Rust structs & enums. Derive macros auto-generate JSON Schema, parse responses, and retry on validation errors. Type-safe structured outputs & function calling.
GitHub · Rust · 34 stars · 4 forks · 0 stars in 24 hours · Trending score 0.28
-
23
JoakimCarlsson/ai
A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.
GitHub · Go · 50 stars · 10 forks · 0 stars in 24 hours · Trending score 0.27
-
24
elflodge/elflodge
Hundreds of agents working unattended. One job API. Run sandboxed agents in parallel on your own machine, without a costly fleet of hosted sandboxes. Send a task or a whole batch; get structured results your code can use.
GitHub · TypeScript · 8 stars · 2 forks · 0 stars in 24 hours · Trending score 0.24