An uncensored, local-first CLI coding agent — streams live reasoning, edits files, runs commands. Provider-agnostic, runs on any OpenAI-compatible uncensored LLM.

Venice AI provider for the Vercel AI SDK

Manipulate any language model from the command line.

DeepSeek chat-completions adapter for the DeepSeek Harness LLM seam

Provider-neutral LLM service interface for the DeepSeek Harness

First-message LLM provider plugin for DeepSeek Harness session titles

Provider-routed LLM request retry policy for the DeepSeek Harness

pi-ai-backed DeepSeek adapter for the DeepSeek Harness LLM seam (design-verification twin of dsh-llm-deepseek)

LLM eval & testing toolkit

Typescript bindings for langchain

Hardware accelerated language model chats on browsers

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

Display language model outputs in your React project.

Native CLI worker for Compute Network (compute.tech), the distributed inference network. Runs LLM inference via ollama and connects to the orchestrator via Socket.io.

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

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

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