Article
CommunityJev Integrations & Adapters
Jev on Fly.io Sprites
Fly.io's TypeSafeAI connector gives Sprites access to Jev without the API key entering the machine: the Sprites gateway attaches the organization's encrypted key, and each Sprite sets only TYPESAFE_BASE_URL plus a placeholder key.
- Format
- Article
- Reading time
- 3 min
- Published by
- Community
- Author
- Fly.io
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Requires API key
Highlights
- Add the connector under Sprites, then Connectors; the key is checked against TypeSafe, encrypted at rest, and never shown again.
- A new connector refuses every Sprite until access is granted by name prefix, by labels, or for the whole organization.
- Set TYPESAFE_BASE_URL to the connector URL and TYPESAFE_API_KEY to any placeholder; the gateway adds the real key on the way out.
- Sprites can reach POST /v1/systemone and GET /v1/models only; every other TypeSafe path or method is rejected with a 403.
- The gateway passes 429 and 529 responses and the retry-after header back, and the TypeSafe SDKs retry on their own schedule.
Watch out
A vendor page, so the security framing is Fly.io's own: it notes Jev does not treat state text as hostile, meaning a crafted ticket can move a decision, and recommends network allowlists, checkpoints, and Firecracker microVM isolation to contain that. Pricing is not stated, and the connector needs Fly.io plus a TypeSafe key.
Questions about this entry
Short answers drawn from the linked project or page.
A Sprites connector that routes Jev calls through a Fly.io gateway: you add it once with your TypeSafe API key, grant Sprites access, and the gateway attaches the real key after checking which Sprite is calling.
Two: POST /v1/systemone for typed decisions and GET /v1/models to list the model aliases your account can use, such as jev-latest. The Fly.io gateway rejects every other TypeSafe path and method with a 403.
No. The key is stored encrypted in your Fly.io organization and attached by the gateway. Inside the Sprite, TYPESAFE_BASE_URL points at the connector and TYPESAFE_API_KEY can be any placeholder such as 'sprites'.
A new connector refuses every Sprite until you set an access policy by name prefix, by Sprite labels, or for the whole organization; the dashboard lists matching Sprites live and can fire a test request from each one.
The Fly.io gateway passes 429 and 529 responses and the retry-after header straight back to the Sprite, along with TypeSafe's rate-limit headers; the TypeSafe SDKs read them and retry on their own schedule.
Because Jev reads whatever you put in the state and does not treat it as hostile, a ticket written to push the answer toward a branch can move it, and that branch runs commands. A Sprite is a Firecracker microVM with a network allowlist and checkpoints restored after each ticket.
No. Jev answers typed questions and does not generate text or stream, so an agent still needs a language model for code and prose; a Sprite can hold an Anthropic or OpenAI connector alongside the TypeSafeAI one.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev 1.14 is now on OpenRouter
X: Jev lands on the Vercel AI Gateway
X: Jev as an LLM guardrail inside Agentgateway
YouTube: Greg Isenberg and Ryan Vogel on the businesses Jev unlocks, and a path in through the Vercel AI Gateway.
More Jev resources like this
Akka's post walks from a Jev triage example - eight questions with probabilities - to an effects API judgment call and an AI Gateway that can route to hosted Jev or a self-hosted OpenJev model.
Jev Integrations & AdaptersArticle#community#java#akka
Community
LiteLLM serves decision models on two routes that share one provider list: /v1/decisions for OpenAI-format bodies and /v1/systemone for System One bodies, with Jev available as the typesafe/jev-latest provider.
Jev Integrations & AdaptersDocs#community#litellm#gateway
Community
Concentrate's beta /v1/decisions endpoint serves TypeSafe's Jev with the same request and response shapes as TypeSafe's System One API and OpenRouter, returning calibrated probabilities for noul, choice, and score questions.
Jev Integrations & AdaptersDocs#community#gateway#api
Community
Pydantic's AI Gateway forwards Jev natively as a bring-your-own-key TypeSafe provider, so one gateway key covers spend views, limits, and input guardrails while TypeSafeModel turns each output field into a question.
Jev Integrations & AdaptersArticle#community#pydantic#gateway
Community
Autonomous agent platform with 187,504 stars for building and running agents from plain English or a visual builder. Its platform features first-class TypeSafe Jev decision blocks for typed routing, filtering, scoring and confidence-gated next-action dispatching.
Jev Integrations & Adapters#community#autonomous-agents#platform
Community
Significant-Gravitas/AutoGPTPython
Significant-Gravitas/AutoGPTPythonLiteLLM's proxy adds TypeSafe guardrail hooks and a Jev complexity classifier for policy judgments and request routing across 100+ model providers.
Jev Integrations & Adapters#community#python#gateway
Community
BerriAI/litellmPython
BerriAI/litellmPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.