Typed public Model & Reasoning contracts and runtime validation for ProFlow inference.

External DeepSeek Harness web client plugin: a Settings page to configure per-model reasoning efforts (thinking levels) for third-party (pi-ai) providers, written into llm-pi-ai.providers.*.models[].reasoningEfforts.

This is an addon demo that can **perform whisper model reasoning in `node` and `electron` environments**, based on [cmake-js](https://github.com/cmake-js/cmake-js). It can be used as a reference for using the whisper.cpp project in other node projects.

Eval harness for non-deterministic (LLM) code — subjects, variants (provider × model × reasoning), weighted-assertion scoring, trial cache, SQLite runs, CLI + TUI.

Pi extension that shows tokens, context usage, cost spent, and model/reasoning in the footer.

Persist model & reasoning settings per session, workspace, or globally

Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wi

Internal component of Sutra SDK — applications should install sutra-sdk. The cognitive core. Domain-agnostic composition of the cognitive primitives (memory, model, reasoning, speech, vision, tools, planning, knowledge) into one perceive-recall-reason-act

Pi tool that delegates a self-contained sub-task to OpenAI's Codex CLI via `codex exec --json`. Streams structured events as partial output, returns the final agent message. Configurable default model + reasoning effort, with multi-turn session continuity

Internal component of Sutra SDK — applications should install sutra-sdk. Pure cognitive contracts: memory, model, reasoning, planning, knowledge, tool, vision, speech, runtime, budget, and degradation interfaces. Zero dependencies, zero implementations.

The **[Alibaba provider](https://ai-sdk.dev/providers/ai-sdk-providers/alibaba)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model, embedding model, and video model support for [Alibaba Cloud Model Studio](https://modelstudio.console.alib

Playwright Tools for MCP

SOTA NPM module for agentic processes using local or cloud LLMs.

Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence

[](https://www.npmjs.com/package/@agentclientprotocol/codex-acp)

`orlithra-code` is a local autonomous coding agent. It talks to the authenticated `/coding` backend for model reasoning, then executes deterministic tools on your current workspace: indexing, file edits, patches, safe commands, verification, checkpoints,

Token-meter-driven compaction policy and LLM summarization backend for the DeepSeek Harness

Model selection: the /model popupSelect over session.models / session.selectModel

Replay-aware token measurement service (ctx.tokenMeter) for the DeepSeek Harness

Playwright CLI