CommunityJev Integrations & Adapters
Classifier.dev
A zero-shot text classification service over plain HTTP: send text and a list of labels, get the best-fitting label and a calibrated probability per label, with Jev as the default and fast tier.
- Published by
- Community
- Last verified
- Oct 2026
Works forJev for Classification
Used inJev for Software & DevTools
Highlights
- You post text and labels; it returns the fitting label plus a probability per label.
- Jev is the default model and the fast tier; the smart tier re-asks only answers below 0.7 confidence.
- Can be pointed at Laya instead by sending model: laya in the request.
Watch out
A third-party hosted service: text leaves your environment, and it presents Jev as a classifier rather than exposing the full decision API or your own question design.
Questions about this entry
Short answers drawn from the linked project or page.
Over plain HTTP: you send the text and a list of labels in a POST, and it returns the label that fits plus a calibrated probability for each label. No SDK or account is described.
Jev, TypeSafe's decision model, is the default classifier. You can also send model: laya to run the same classification against the open Laya model instead.
The fast tier is Jev. The smart tier is Jev plus a reasoning model that re-asks only the answers Jev scored below 0.7 confidence, so the extra cost is spent on the uncertain cases.
Any zero-shot labelling task where you supply the candidate labels: topic tagging, intent, moderation categories, and similar text classification, returned with per-label confidence.
It is a hosted third-party service at classifier.dev, not a library. That means your text is sent to their endpoint and then to the model provider, so review the privacy terms before sending sensitive content.
It removes the prompt and response plumbing for the common case of labelling text with a fixed set of labels, and adds a confidence-routing tier, at the cost of an extra hop and dependency.
The service prices per request rather than per output token, consistent with Jev's free output tokens, but check the current page because third-party pricing can change without notice.
Related terms
Glossary definitions related to this entry.
More Jev resources like this
60.9kGitHub stars
LiteLLM'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/litellmPython46.7kGitHub stars
Privacy-first, self-hosted personal knowledge management system with block-level references and a local-first Markdown editor; the project integrates Jev's decision model for high-speed document classification, flashcard intent categorization and automated tag routing.
Jev Integrations & Adapters#community#note-taking#knowledge-base
Community
siyuan-note/siyuanTypeScript
siyuan-note/siyuanTypeScript33kGitHub stars
Alibaba's multi-agent platform, which implements native TypeSafe Jev classification through JevClassifierModel for binary, choice and score routing across agent pipelines. Python 3.11+, Apache-2.0, with a FastAPI agent service and web UI.
Jev Integrations & Adapters#community#multi-agent#framework
Community
agentscope-ai/agentscopePython
agentscope-ai/agentscopePython20.5kGitHub stars
Python agent framework whose TypeSafeModel class runs Jev as a decision model inside Pydantic AI agents: Pydantic output-type fields become typed Jev questions answered together in one request, each answer carrying its own confidence, and tools can be offered as Choice options.
Jev Integrations & Adapters#community#agents#framework
Community
pydantic/pydantic-aiPython
pydantic/pydantic-aiPython19.6kGitHub stars
Open-source TypeScript agentic operating system: a core runtime, app for web and mobile, CLI, cloud services and first-party plugins. The directory's curated summary reports it integrates TypeSafe System One decision services for sub-100ms intent classification, action dispatching and confidence-gated tool execution.
Jev Integrations & Adapters#community#agents#framework
Community
elizaOS/elizaTypeScript
elizaOS/elizaTypeScript12.4kGitHub stars
Open-source AI email assistant (Next.js, Postgres, 12k+ stars) with a decision-model layer that can run on openrouter:typesafe/jev-1.13: Jev-backed questions cover rule selection, cold-email detection, thread status, recurring patterns, unsubscribe pages, and sender categorization, each with evals.
Jev Integrations & Adapters#community#email#gmail
Community
elie222/inbox-zeroTypeScript
elie222/inbox-zeroTypeScriptFrom the Jev community
Posts from builders shipping with Jev right now.