Synkora

Synkora

An open source AI agent platform for role-based agents such as PM, engineer, support and marketing, with custom tools and knowledge bases. The author gave Claude Sonnet access to Jev as a tool to score five resumes against one job profile, each evaluation finishing in milliseconds at near-zero API cost.

getsynkora/synkora-ai on GitHub

Stars: 35
Forks: 6
Language: Python
License: MIT
Last push: 23 Sep 2026

Post on X

Views: 87
Likes: 0
Reposts: 0

Read from GitHub and X on 24 Sep 2026. Counts change daily.

How it uses Jev

Async HTTP client for the TypeSafe AI evaluation API.

Usage:
    client = TypeSafeClient(api_key="ts-...", base_url="https://api.typesafe.ai/v1")
    result = await client.evaluate(
        state="resume text here",
        questions={
            "meets_min": {"type": "noul",   "question": "Does this candidate meet minimum requirements?"},
            "fit":       {"type": "choice", "question": "Experience level?", "options": ["exceeds","meets","partial"]},
            "score":     {"type": "score",  "question": "Overall quality?",  "levels": ["weak","fair","strong"]},
        },
    )
"""

def __init__(self, api_key: str, base_url: str = "https://api.typesafe.ai/v1", model: str = "jev-latest"):

View in api/src/core/typesafe_client.py

Open on GitHub

View the post on X

Use casesComposite scoring

jev-trader

Makes one AI trade decision every Monad block on the Kuru MON-USDC market using Jev. The public deployment runs in dry-run mode with a mock model.

jarrodwattsOpen

2.2k starsLoop, mock model p50 100 msDecision window ~300 ms/block

ProjectConfidence-gated actions+1

Introducing System One Models and Jev (Hacker News launch thread)

The 1,978-point, 513-comment launch thread. The top comment calls the speed comparison misleading, since Jev only returns structured output, and disputes the cannot-hallucinate claim because a valid type can still hold a wrong value. Others note ordinary LLMs can already be forced into structured output.

albelfioOpen

DiscussionIntent and model routing+3

DSPy: programming, not prompting, language models

Declares typed input/output Signatures for LLM modules and optimizes the underlying prompts and weights against a metric. Its Signature abstraction is the closest widely-used open equivalent of Jev's typed-question interface. Star count is GitHub's rounded display figure.

stanfordnlp38k starsOpen

AlternativeStructured extraction+3

newsjack

Open source skills that read a morning's news feed with Jev and tell a list of brands which stories to act on. In a demo run it read 384 headlines and matched them to 15 brands in 24.9 seconds for $0.19, against 4 of 384 for $0.77 on Claude Opus 5 over the same feed.

Elvis (@elvissun)Open

851 starsCost $0.19vs Opus/headline ~390x cheaper

ProjectComposite scoring

decider: one-pass typed decisions with calibrated probabilities (Qwen3.5-2B)

Open reproduction of the System One model class, fine-tuned from Qwen3.5-2B-Base, returning a probability distribution per typed question in a single forward pass. Serves TypeSafe's POST /v1/systemone wire format so TypeSafe SDKs work unchanged by repointing TYPESAFE_BASE_URL.

Mapika348 starsOpen

AlternativeIntent and model routing+3

pg-jev

PostgreSQL extension that lets you filter, rank and classify rows with plain-language conditions, such as WHERE jev(tickets, 'the customer is angry'). Adds jev_prob, jev_choice and jev_score functions that compose with joins, GROUP BY and ORDER BY, with no index or embeddings. Published on PGXN.

realZachiOpen

329 stars2k rows, cold ~3.5s, $0.0122k rows, cached ~50ms

ProjectSupport inbox triage+1

Menu