SIEGE (CoreWeave Hacks: Agent Loops 2026)

SIEGE — Break it. Watch it learn. A live agent security loop. — Image from github.com

vnmoorthy/siege on GitHub

Stars: 0
Forks: 0
Language: TypeScript
License: MIT
Last push: 13 Sep 2026

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

How it uses Jev

        from typesafe_sdk import Choice

        q = Choice(instructions=INSTRUCTIONS, criteria=policy["criteria"])
        resp = await self.client.system_one(state=state, questions={"action": q})
        a = resp.choices["action"]
        return {"decision": a.choice, "probabilities": {k: float(v) for k, v in a.probabilities.items()},
                "confidence": float(a.confidence), "model": resp.model}


class LLMFallbackGate:
    provider = "llm-fallback"

View in backend/app/gate.py

Open on GitHub

PrimitivesChoice

Use casesConfidence-gated actions LLM guardrails Real-time control

Jev Ultrafast (Browser Use)

Browser Use's fast browser agent where Jev picks the operation and the DOM element in a single request; a small LLM is only invoked to write text when typing is required. Demoed on a Google Flights search.

browser-useOpen

19k starsFlight search 7.1 s

ProjectTyped tool dispatch+2

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

jkudish/jev-mcp

MCP server that gives Claude Code, Codex, Amp, OpenCode and other agents ten Jev judgment tools, each returning typed probabilities they can branch on. The author calls it early software.

jkudishOpen

320 starsPer call 150-500 ms

ToolAgent routing and skill selection+2

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

Outlines: structured outputs for LLMs

Guarantees valid structured output during generation by constraining decoding to a grammar or schema. The mechanism HN commenters repeatedly cited as already covering Jev's cannot-produce-a-type-error guarantee on ordinary LLMs. Star count is GitHub's rounded display figure.

dottxt-ai16k starsOpen

AlternativeStructured extraction+2

Laya-MLX

An independent MLX port of Laya for Apple Silicon, 13.4ms median for a short English decision and 7.4ms on the multilingual checkpoint, with a Snake demo that plays at up to 75 moves per second under 1GB of memory.

mizorewwwOpen

6.1k starsShort decision 13.4 ms P50Snake demo 75.4 moves/s

ToolReal-time control

Menu