Skip to content
JevDirectory.org
CommunityTools & Integrations2 starsVerified 2026-09-22

pi-typesafe-jev

A pi extension that exposes TypeSafe Jev judgments as five tools, calling POST /v1/systemone directly with native fetch so your code and users keep control of thresholds, weights, and actions.

Open github.comlegacybridge-tech/pi-typesafe-jev
Category
Tools & Integrations
Published by
Community
Author
legacybridge-tech
Added
2026-09-22
Tagscommunitytypescriptagentstool-calling

Highlights

  • Five tools: typesafe_noul, typesafe_choice, typesafe_score, typesafe_evaluate, and typesafe_ask for questions pinned in a local YAML or JSON file.
  • Calls https://api.typesafe.ai/v1/systemone with native fetch; there is no SDK runtime dependency.
  • The API key is stored by /typesafe setup under the pi agent directory and needs no environment variable.
  • Credential hygiene: directory mode 0700, file mode 0600, atomic rename writes, and refusal to follow symlinks.
  • typesafe_evaluate answers several independent questions over one state in a single request; state and questions share a roughly 32k-token request budget.

Quickstart

bash
pi install npm:pi-typesafe-jev

Watch out

MIT-licensed. Requires pi and node >= 22.19; the credential file is plaintext JSON with no OS keychain protection, and /typesafe setup input is not masked on screen. An independent integration, not affiliated with TypeSafe AI.

More like this

Reticle
815GitHub stars
An MCP server and agent skill that verifies coding-agent work by driving the real running app and returning pass, fail, or couldn't-tell verdicts with the file:line to fix; its listing frames the approach as Jev-style machine-native runtime perception.
Tools & Integrations#community#typescript#mcp
Communityreticle
Hippo
753GitHub stars
A local SQLite memory layer for CLI agents with an opt-in Jev reranker that batches Noul judgments over the top 40 recalled memories and falls back to a local cross-encoder on errors.
Tools & Integrations#community#typescript#agents
Communityhippo-memory
Skillbox
226GitHub stars
A self-hosted, versioned skills library for AI agents with HTTP MCP, scoped client keys, and opt-in Jev recommendations that rank skills for a task using your own OpenRouter, TypeSafe, or Vercel key.
Tools & Integrations#community#typescript#mcp
Communityskillbox
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A really smart switch statement

Nathan Flurry 🔩
Nathan Flurry 🔩
Rivet
@NathanFlurry
·

hype-free explanation of jev: jev does not replace gpt / claude jev is just a *really* smart switch statement like if 2016 ml classifiers got 2026 levels of intelligence it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate * = and by Show more

Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 230 replies

When a designer gets Jev

Full Jev video tutorial

The case against Jev-scored compaction

Theo - t3.gg
Theo - t3.gg
@theo
·

This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the Show more

tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Watch on X
Reply
Read 182 replies

Classifying rows in DuckDB

A playable 16-judgment demo