Skip to content

algovault-integrations: typesafe-jev

Example where Jev decides whether to act on an AlgoVault crypto-perp verdict now; code applies thresholds and logs act, hold or escalate.

Projectprototype

Overview

algovault-integrations holds examples for consuming the AlgoVault Verifiable-Signal v1.0 spec on downstream platforms. Most examples transform a trade signal into a platform's order format. The typesafe-jev example is a decision layer that sits between the verdict and execution instead.

Its transformer turns a composite AlgoVault verdict (direction, confidence, regime) for a crypto perpetuals market into a TypeSafe SystemOneRequest. Per the list summary, Jev answers whether to act on the verdict now and how well the regime fits a directional entry, while code computes position conflict, applies every threshold and logs act, hold or escalate. It is read-only, never places orders, and runs as a dry run without a key.

What the decision model decides

TypeQuestionAnswers
Yes / noShould we act on this verdict for this market now?yes · no
ScoreHow well does the current regime fit a directional entry?—

How it works

  1. Fetch a verdict from the AlgoVault MCP
  2. toJevRequest builds state and questions (or returns null)
  3. Jev answers via @typesafe-ai/sdk
  4. Code checks position conflict and thresholds
  5. Log act, hold or escalate; never trade

Strengths

  • Thresholds and conflicts handled in code
  • Dry run with no key
  • Pure transformer with unit tests

Caveats

  • Example only; places no orders
  • Signal quality depends on AlgoVault

Getting started

Run the examples/typesafe-jev demo; it works as a dry run without a TypeSafe key.

At a glance

Type
Project
Status
prototype
Language
TypeScript
Runtime
Node example
Has code
yes
Has tests
yes

Use cases and integrations

How curated lists describe it

  • Jev decides whether to act on a composite AlgoVault verdict (direction, confidence, regime) for a crypto perp market now, and how well the regime fits a directional entry; code computes position conflict, applies every threshold, and logs act, hold, or escalate. Read-only: it never places orders, and runs as a dry run with no key required.

    cobanov/awesome-jev

Frequently asked questions

Does it place trades?

No, it is read-only and logs act, hold or escalate.

What does Jev judge?

Whether to act on the verdict now and how well the regime suits a directional entry.

Do I need a key to try it?

No, it runs as a dry run without one.

Related projects

  • Local China A-share technical analysis workbench where Jev assesses eight indicator dimensions and returns Buy, Hold or Sell with evidence.

    ProjectbetaPython, TypeScript
  • Local stock decision service that sends market data and news to Jev or a local model and returns a policy-checked buy/sell/hold.

    ProjectbetaTypeScript
  • PyTorch factor-research stack with 213 factors and cost-aware backtests, plus a preview typed portfolio-decision adapter.

    ProjectbetaPython
  • Chinese open-source research and trading workbench whose JEV monitor watches futures contracts and judges entries and exits.

    ProjectbetaTypeScript
  • Self-hosted trading analysis platform pairing Claude briefings with Jev probabilities for signals like thesis-breaking headlines.

    Servicebeta
  • Next.js crypto dashboard where Jev judges each tick across timeframes and drives a SQLite paper-trading portfolio with automatic TP/SL.

    ServiceprototypeTypeScript