Additive request-field registry for the official DeepSeek LLM API adapter

Display language model outputs in your React project.

Export an eval session's artifacts — screenshots and/or text outputs — to bryel for judging. Framework-agnostic, zero dependencies.

First-message LLM provider plugin for DeepSeek Harness session titles

LLM-judge service for the @unotest ecosystem: judges free-form text (chat replies, generated content) against a natural-language rubric and returns a structured pass/fail verdict with reasoning. Runs as a small HTTP service (`npx @unotest/judge`) or in-pr

Multi-LLM MCP server: confer / debate / coordinate / audit / orchestrate across Anthropic + OpenAI + xAI + Gemini + Mistral + Groq + DeepSeek + Kimi + Qwen, with scoreboard-driven router, canary-leak detection, sandboxed shell verifiers, and a tier-aware

micromark extension to support math (`$C_L$`, `\(C_L\)`)

[llm-ui](https://llm-ui.com) markdown block.

Durable storage for post-hoc evaluations (LLM-judge scores, human annotations, rule-based verdicts) keyed on the @llm-ports/observability-contract EvaluationRef shape. Ships an in-memory store (default) and an opt-in SQLite writer (peer-dep on better-sqli

Shared LLM generation policy for DeepSeek Harness session-title providers

[llm-ui](https://llm-ui.com) JSON blocks for building custom components.

Detox driver for Wix Pilot usage

Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c

[llm-ui](https://llm-ui.com) code block.

Screen the wallets that pay your x402 endpoints against OFAC. Free, local, sub-millisecond. Optionally anchor each screening as permanent evidence.

Rubric-scored feedback on any conversation transcript. Bring your own LLM client, bring your own rubric.

A library for working with LLMs in Grafana plugins

External eval harness that proves your product does what it claims — deterministic L0 checks + LLM-judged L2 rubric scoring

Promptster AI-fluency rubric — the public data artifact (4 process dimensions + sub-facets & behavioral anchors, 5 tiers, methodology sources). Anchors and citations only; criteria and scoring weights are not part of this package.

Opik TypeScript and JavaScript SDK