mattneel/typesafe (Elixir)
Idiomatic Elixir client for the TypeSafe AI API with configuration-driven auth, retries, telemetry and test support. Returns judgments as data structures the caller thresholds itself.
Entries 97 to 132 of 132, in the hub's default order. The introduction is on page 1.
Showing 97 to 132 of 132
Idiomatic Elixir client for the TypeSafe AI API with configuration-driven auth, retries, telemetry and test support. Returns judgments as data structures the caller thresholds itself.
PostgreSQL extension that runs Laya decision-model inference natively inside the database, using Rust and Candle.
Runs Laya's English typed-decision checkpoint on a Windows machine with an AMD Radeon RX 6900 XT (gfx1030) GPU through a pinned PyTorch ROCm build, with an optional Jev-compatible HTTP loopback service.
A community Unity package, installable via the Package Manager git URL, giving a backend-independent C# client for typed Choice/Score/Noul decisions against local Laya servers or TypeSafe-compatible endpoints.

Laya's English checkpoint quantized to 8-bit and run entirely client-side via onnxruntime-web WebAssembly, with an editable JSON playground, three question types, calibrated confidence and weights cached in the browser.

A deterministic decision runtime for Jev with zero-token caching and a certainty calibrator for gating actions on confidence.
A documentation hub explaining how to wire Jev into Nous Research's Hermes Agent framework, with a latency and cost comparison against frontier LLMs.
TypeScript library for typed decisions across Jev, Cloudflare AI Gateway and Laya, with both Promise-based and Effect-native clients.
A local MCP gateway that uses Jev for tool discovery across connected MCP servers, with credential storage, a CLI and a dashboard.
A Go client library for the TypeSafe API, wrapping Jev's endpoints for Go projects.
n8n community node for the System One API exposing typed yes/no, choice and score questions with calibrated probabilities a workflow can branch on. Self-hosted n8n only until n8n verifies the package.
MoonBit client for the Jev API plus a Jev-vs-Jev gomoku match with per-move timing logs. Write-up at zenn.dev/mizchi/articles/jev-plays-gomoku.
Go 1.27 client with generic typed questions (jev.Noul, jev.Choice, jev.Score, plus jev.Raw). Supports batching, retries, and Vercel AI Gateway as an alternative backend.
A native Swift library that runs Laya inside a macOS app on Apple MLX, with no Python, ONNX or helper process, answering typed choice, boolean and score questions at 27.1ms p50 on an M3 Max.
An MCP server and HTTP sidecar around Laya that fixes its silent failure modes: a token-budget preflight before truncation happens, structured errors naming the bad question, and confidence labelled for what it actually measures.
A stateless CLI for typed judgments with Jev, turning a state plus typed questions into JSON on stdout and exit codes a shell script can branch on.
An MCP server that lets Claude hand a whole browser task to Jev, which makes each click, type or select decision in about 100ms while Claude keeps planning the task and verifying the result.
Unofficial typed Elixir client for TypeSafe AI and Jev with offline test stubs, concurrent fan-out and atom-keyed answers.

A video demo of jev(), a PostgreSQL extension that filters rows with a natural-language condition inside a WHERE clause with no index or embeddings. It judged 129 rows in about 1 second for $0.0009, and 6 milliseconds on a cached rerun.
478k viewsFirst run 129 rows/~1sCost $0.0009

A DuckDB extension that runs Jev classification on rows of any CSV, Parquet file or DuckDB table, taking about 10 seconds for 1,000 rows.
181k viewsPer 1k rows ~10s

Announces ai-cli, an npm package installed with npm install -g ai-cli, that lets any agent harness ask yes/no questions, choose between options, or score against criteria using Jev.

Google's LiteRT conversion of Laya's multilingual checkpoint for on-device Android GPU inference, matching the official CPU implementation on 201 validation rows with a Kotlin sample app answering typed choice, score and noul questions.

A ready-to-run deployment package for all three Laya checkpoints (English, multilingual, typed-decisions) on Axera AX650/AX8850 edge NPUs, with sample requests, outputs and a demo app via the axllm runtime.
Laya's English checkpoint compiled to GGUF with ggmlc, scoring choice, score and noul questions in one encoder pass with a CLI that ships an injection-guard preset and a local serve/daemon mode.

An ONNX export of Convai's Laya decision model, with int8 and fp16 variants and a Python quickstart that builds the marker-token sequence and runs one inference in about 15ms on CPU.
Elixir Forum thread (8 replies, 281 views) announcing an Elixir SDK for Jev with strict noul/choice/score constructors and evaluate/evaluate_many/streaming. Notes five independent Elixir Jev clients appeared in the same launch week.
Async Python client for Jev, version 1.1.0, requiring Python 3.12+ and aiohttp. Supports Noul, Choice and Score and encourages batching multiple questions into one call.

Vercel changelog announcing Jev on AI Gateway under model ID typesafe-ai/jev. Evaluation calls appear in Gateway logs, count toward budgets and accept Gateway provider options.
PyPI listing for the official Python SDK, version 0.6.0, MIT licensed. Requires Python 3.10+.

Official AI SDK provider exposing Jev through the experimental evaluate API in AI SDK 7. Supports Choice (1-255 options), Score (2-10 ordered levels) and Boolean/Noul, batching all questions in one request against the same state.

Cloudflare Workers AI model catalog page for TypeSafe Jev, documenting the state plus questions request shape and the Noul, Choice and Score answer types. Examples cover ticket routing, refund review and risk assessment.

OpenRouter lists two TypeSafe models, typesafe/jev-latest and typesafe/jev-1.13, both with a 32K context window, at $0.042/M input and $0/M output.
LangChain integration package (0.0.1a2 pre-release, MIT) providing TypeSafeClassifier as a Runnable plus experimental agent middleware: ModelRouterMiddleware, SkillsMiddleware and AutoModeMiddleware for tool-risk gating.
Reference for POST https://api.typesafe.ai/v1/systemone, covering the state/model/questions request body, the answer shapes, and error codes 401, 422, 429 and 529.
Official documentation for the @typesafe-ai/sdk npm package, covering installation (Node 20+), client setup and the question DSL.
Hex package listing for the Elixir SDK, version 0.4.0, MIT licensed, last updated 2026-09-18.
Nothing matches those filters
Clear a filter to widen the search, or send us the thing you were looking for.