structured-outputs repositories

Trending repositories tagged structured-outputs, ranked by trending score. Updated daily.

  1. 1
    OmniJev/awesome-jev-gallery

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

    GitHub · Python · 494 stars · 43 forks · +5 stars in 24 hours · Trending score 1.36

  2. 2
    PrefectHQ/marvin

    an ambient intelligence library

    GitHub · Python · 6,204 stars · 420 forks · −2 stars in 24 hours · Trending score 0.41

  3. 3
    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.

    GitHub · C · 29 stars · 3 forks · 0 stars in 24 hours · Trending score 0.10

  4. 4
    ihubanov/hunch

    Calibrated yes/no, pick-one and scale judgments from your own LLMs, on text and images, read straight off the logprobs. Runs on vLLM.

    GitHub · Python · 6 stars · 2 forks · 0 stars in 24 hours · Trending score 0.05

  5. 5
    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.

    GitHub · 65 stars · 15 forks · 0 stars in 24 hours · Trending score 0.02

  6. 6
    AhmadHassan-BTed/Noria

    An agentic extractor for messaging platforms. Noria receives messages & URLs via chat; scrapes web data to evaluate the content against custom scoring matrices (e.g., jobs, scholarships); and sends a structured summary with a calculated match score directly to the assigned messenger number.

    GitHub · JavaScript · 4,635 stars · 3 forks · 0 stars in 24 hours · Trending score 0.01

  7. 7
    Heman10x-NGU/Verdict-open-jev

    Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground

    GitHub · Python · 119 stars · 15 forks · 0 stars in 24 hours · Trending score 0.00

  8. 8
    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.

    GitHub · Python · 15 stars · 5 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    nshkrdotcom/typesafe_sdk

    An idiomatic, type-safe Elixir port of the official TypeScript AI SDK (ai / ai-sdk) providing unified LLM integrations, streaming text and structured outputs, tool calling, and agentic workflows. Jev is their current flagship model and is the first System One model.

    GitHub · Elixir · 5 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    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)

    GitHub · Python · 305 stars · 49 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    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.

    GitHub · Python · 50 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00

  12. 12
    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.

    GitHub · TypeScript · 38 stars · 12 forks · 0 stars in 24 hours · Trending score 0.00

  13. 13
    emnlmn/snap

    Typed decisions from unstructured state: one forward pass, zero generated text. Local, deterministic, Jev-compatible. Not affiliated with typesafe.ai.

    GitHub · Rust · 10 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  14. 14
    alphaparkinc/genpark-agent-output-schema-enforcer-guardrail-skill

    Strict JSON schema validator with streaming partial JSON repair, missing field filling, and sanitization

    GitHub · Python · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  15. 15
    alphaparkinc/genpark-json-schema-contract-validator-skill

    Zero-dependency JSON schema subset validator ensuring LLM structured outputs strictly conform to tool contracts

    GitHub · Python · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  16. 16
    alphaparkinc/genpark-structured-output-json-schema-guard-and-repairer-skill

    Enforces strict JSON schema validation on model outputs and autonomously repairs malformed JSON syntax, trailing commas, and unclosed quotes | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550

    GitHub · Python · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00