Awesome TypeSafe

A curated list of official resources and community projects for TypeSafe, System One models, and Jev.

TypeSafe’s Jev returns typed, probabilistic decisions instead of generated text. This list focuses on the things you can use to understand that model shape, build with it, test its limits, and reproduce community experiments.

Independent community project. This repository is not affiliated with or endorsed by TypeSafe AI. Community entries are labeled by section; inclusion is not a claim that TypeSafe has reviewed or approved them.

Last reviewed: 2026-09-17. Jev and its ecosystem are moving quickly; please open a pull request when something changes.

Contents

• Start here
• Official resources
  • Product and documentation
  • SDKs and developer tools
  • Concepts, patterns, and cookbooks
  • Research and writing
  • Community and updates
• Community projects
  • Client libraries and integrations
  • Agent and developer tooling
  • Browser agents
  • Games, robotics, and interactive demos
  • Evaluations and independent research
  • Showcases and field notes
• Contributing

Start here

• Introduction — What Jev is, how System One models differ from text-generation models, and the Choice, Score, and Noul primitives.
• Quick start — The shortest path from an API key to a typed decision in Python or JavaScript.
• How to build with TypeSafe — Design guidance for decomposing a workflow into narrow judgments while keeping policy and side effects in code.
• TypeSafe Console — Create keys and inspect live Jev requests.

Official resources

Product and documentation

• TypeSafe AI — Official product site for System One models and Jev.
• Documentation — Guides, SDK references, patterns, cookbooks, and the HTTP API.
• HTTP API reference — Request and response contract for direct API integrations.
• Interactive demos — Official hands-on examples, including the smart-home assistant.
• Workflow evals — TypeSafe’s published workflows, model comparisons, methodology, and example queries.

SDKs and developer tools

• JavaScript SDK — Official JavaScript and TypeScript client with inferred answer types.
• Python SDK — Official synchronous and asynchronous Python client.
• System One Adapter — Drop-in Python adapter for running the same typed interface over OpenAI, Anthropic, and OpenAI-compatible LLM APIs.
• TypeSafe Agent Skills — Official agent skill for designing TypeSafe workflows from Claude Code, Codex, and other skill-compatible agents.
• TypeSafe GitHub organization — Source repositories maintained by TypeSafe.

Concepts, patterns, and cookbooks

• Primitives — Choice, Score, and Noul, including their result shapes and when to use each one.
• Confidence — How confidence differs from answer probability and how to use it as an architectural control.
• Patterns — Confidence-gated routing, composite scoring, speculative fan-out, and intent routing.
• Example use cases — A map from real-world workflows to typed judgments.
• Cookbooks — Reproducible implementations for parallel questions, reranking, semantic search, guardrails, extraction, classification, and more.
• Agent skill guide — Installation and usage instructions for the official TypeSafe skill.

Research and writing

• Introducing System One Models & Jev — Launch post, product thesis, published results, and explicit limitations.
• Manifesto — TypeSafe’s case for machine-native intelligence built for software rather than conversation.
• The Bitterest Lesson — Why optimizing the wrong task can dominate gains from scale.
• AI: too good to be true, too bad to be useful — The argument for moving beyond preference-optimized chat models in automation.

Community and updates

• Discord — Official community server for builders, support, and discussion.
• Show and Tell — Builder demos and work in progress; joining the Discord server is required.
• X — Product and research updates.
• LinkedIn — Company announcements and hiring updates.

Community projects

Community projects are independent unless their repository says otherwise. Read the code, licenses, data-handling notes, and evaluation caveats before using them in a consequential system.

Client libraries and integrations

• Advocaat — Small TypeScript client with ergonomic tagged helpers for typed chances, choices, and scores.
• pi-typesafe — Pi extension and library that gives the agent and other extensions one consented, key-managed TypeSafe client with a batched typesafe_evaluate tool and offline-testable transport; requests are billable and opt-in per user.
• RubyLLM TypeSafe — TypeSafe provider for RubyLLM 2 with offline model metadata and typed responses.
• s1-rs — Rust derive layer for Choice, Score, Noul, typed question sets, confidence gates, and network-free testing.
• TypeSafe AI for Rust — Rust client with asynchronous and blocking transports, typed responses, observable retries, and inspectable errors.
• typesafe-ai-rails — Community Rails integration for TypeSafe’s System One API, built on typesafe-sdk, with Rails configuration, persisted usage and cost telemetry, and opt-in confidence policies for Choice and Score answers.
• Rust typesafe-rs — Latency-focused Rust transport SDK designed around behavioral parity with the official clients.
• Elixir typesafe_sdk — Elixir SDK for TypeSafe AI and Jev with typed Choice, Score, and Noul structs, configurable retries, and upstream API parity.
• Ruby typesafe-sdk — Community Ruby client for TypeSafe’s System One API with typed Noul, Choice, and Score questions, retries, model listing, and thread-safe pooled HTTP connections; requires Ruby 3.1 or newer and has no async client.
• Vercel AI Gateway — Third-party hosted gateway entry for calling Jev through Vercel’s AI SDK and gateway.

Agent and developer tooling

• Bicameral — Pi coding harness where an LLM writes while Jev supplies typed reflexes for policy, loop detection, and review; explicitly not a sandbox.
• Every — Semantic code search CLI that asks a yes/no question of every function and ranks the resulting probabilities.
• Jev MCP — Python MCP server exposing classify, score, check, match, and screen tools to MCP-compatible agents.
• Jev Review — Staged code-review workflow and local dashboard that follows structured signals through focused Jev calls.
• pi-jev — Pi extension with a shadow-mode tool-call gate, output judge, and a general typed jev_ask tool.
• pi-warden — Pi guardrails built on pi-typesafe that return Jev’s verdict to the agent as a held tool result or a short steer instead of a dialog, check writes against a project rules file, and grade their own holds against the user’s next message on recorded sessions; the action guard is calibrated on one user’s 17k calls, the other guards on synthetic cases only.
• TypeSafe MCP — Go CLI and single-binary MCP server with setup for Claude Desktop, Claude Code, and Codex.

Browser agents

• Jev Browser — Agent skill and runtime that lets Jev select browser actions inside a continuous observation-action-verification loop.
• Jev Ultrafast — Browser Use agent with a dynamic indexed action space, batched operation and target decisions, traces, and a measured Google Flights demo.

Games, robotics, and interactive demos

• Jev Drone — MuJoCo quadrotor stack that keeps control and safety in code while using Jev for slower tactical judgments.
• Jev Plays StarCraft — Structured-state harness, verified run, probability trace, and evidence bundle for the original StarCraft shareware campaign.
• TypeSafe Mario — NES controller experiment that turns emulator telemetry into structured state and has Jev choose legal actions.
• TypeSafe Typewriter — Live Val Town demo that updates 16 typed judgments as text changes.

Evaluations and independent research

• Jev Rerank Bench — Reranking comparison with raw provider responses, scoring code, dataset-level results, uncertainty intervals, and documented limitations.
• Jev Spam Eval — Exploratory zero-shot spam study against trained TF-IDF baselines, including results and explicit post-hoc-tuning caveats.
• OpenJev — Independent open-model research baseline for direct typed option scoring; it reproduces the interface pattern, not Jev’s undisclosed model or training.
• TypeSafe AI Benchmark — Side-by-side Jev and Qwen-on-Cerebras comparison with raw exports, cost accounting, methodology, and task-specific limitations.

Showcases and field notes

• Browser Use + Jev — Gregor Zunic’s real-time flight-search demo and short description of the dynamic DOM action space.
• Internal classifier field note — A builder’s early matched-precision comparison against a private fine-tuned Qwen classifier; useful anecdotal evidence, not a reproducible benchmark.
• Jev Typewriter launch post — Steve Krouse’s playable 16-judgment demo and video.
• Qwen on Cerebras comparison — Shannon’s video and source-backed comparison of a structured-output LLM baseline with Jev.
• Typed Decisions, Not Chat — Independent technical walkthrough that distinguishes TypeSafe’s published claims from what the public evidence establishes.

Contributing

Contributions are welcome. Please read the contribution guide before opening a pull request.

The short version: submit a public, directly useful resource; describe what it actually does; put it in one category; and include limitations when a result depends on a private dataset, a single run, or an unverified claim.

License

MIT. Individual projects and linked content retain their own licenses and terms.