Skip to content

TypeSafe AI Lib

.NET 10 client for the TypeSafe evaluation API that evaluates a state against typed questions and returns structured answers.

Stars
0
Language
C#
Published by
Community
Author
timdinh
Last verified
Oct 2026

timdinh/typesafe-ai-lib

User repository on GitHub

View on GitHub

High-performance .NET client for the TypeSafe evaluation API (POST /v1/systemone), compatible with the native API and the Vercel AI Gateway. Source-generated JSON, streaming bodies, automatic 429/529 retries

Forks
0
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

A high-performance .NET 10 client library for the TypeSafe evaluation API (POST /v1/systemone). Evaluate a state against typed questions and get back structured answers. Source-generated System.Text.Json — reflection-free serialization; AOT/trim safe, lower allocations and startup cost. Streaming bodies — request and response JSON are streamed (ResponseHeadersRead), never buffered into intermediate strings.

Quoted from the project's README. Read the full README.

Highlights

  • Targets POST /v1/systemone with Noul, Choice, and Score question and answer types.
  • Streams request and response bodies with ResponseHeadersRead instead of buffering strings.
  • Retries 429 and 529 with exponential backoff plus jitter honoring Retry-After.
  • Throws TypeSafeApiException with StatusCode and ResponseBody after retries are exhausted.

Watch out

Client library only; request shape and model behavior still follow the TypeSafe evaluation API. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

3GitHub stars
Rubric-based eval harness that judges LLM and agent outputs with Jev through the Vercel AI Gateway, answering all rubrics for a case in one round trip.
Jev Benchmarks & Evaluations#community#github
1GitHub stars
Eleven-level Jev course from hello-world to a ticket-triage capstone, pairing short lessons with runnable scripts against the live API and using LiteLLM so the writing half works with any provider.
Jev Benchmarks & Evaluations#community#github
1GitHub stars
Wire-compatible Jev re-implementation reading typed decisions from an LLM's next-token logits, plus a reproducible JevBench-based comparison of that approach against Jev on identical items.
Jev Benchmarks & Evaluations#community#github
1GitHub stars
Deliberately overengineered TypeScript package that asks Jev whether an integer is odd, with ESM and CommonJS builds, typed answers, and token and timing receipts.
Jev Benchmarks & Evaluations#community#github
Native Apple Silicon harness comparing local decision models through one decision interface, running models serially and emitting an offline dashboard with latency and accuracy.
Jev Benchmarks & Evaluations#community#github
Local demo that runs Jev and Gemini in parallel over synthetic transactions, comparing decision, latency, tokens, and audit record.
Jev Benchmarks & Evaluations#community#github
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai