Neuralwatt provider extension for pi - Access Kimi, GLM, Qwen, GPT-OSS, Devstral, and MiniMax models through the Neuralwatt API

Agent Skill and CLI for Windsurf Devstral semantic code search without an MCP server.

Agent Skill and CLI adaptation of fast-context-mcp that runs Windsurf Devstral semantic code search without an MCP server.

AI SDK V3 provider for Windsurf's Devstral code search API

Integrate Mistral AI models including Devstral, Mistral Large, and Mistral Medium into GitHub Copilot Chat

Mistral tokenizer families for tokkit.

At-will open-weights coding agent: spins up a selectable model (Qwythos default) on a cheap on-demand RunPod GPU behind a local OpenAI-compatible proxy, wires the pi.dev / Claude Code harness to it, and tears the pod down when idle.

AI-driven semantic code search via reverse-engineered Windsurf protocol (Node.js)

A universal, easy-to-use AI client with unified interface for OpenAI, Claude, Gemini, and Groq.

Universal AI model proxy — route any coding tool through OpenRouter, Ollama, LMStudio, llama.cpp, or any LLM provider

AI-driven semantic code search for the Pi coding agent — Windsurf SWE-grep protocol as a native pi package.

Locus MCP - AI-driven semantic code search client

MCP server wrapping Mistral Vibe CLI — use Mistral as a second opinion or coding agent in Claude Code, Cursor, Zed, and any MCP client

Locus MCP - AI-driven semantic code search client

AI-driven semantic code search MCP server (Node.js) — Windsurf/Devin protocol

AI-driven semantic code search MCP server (Node.js)

AetherOffice is a local-first AI software company workspace with a secure terminal setup flow.

Pi extension: all Bedrock Mantle models (GPT-5.x, Claude, DeepSeek, Qwen3, Mistral, Kimi, ...) via SigV4 — no long-term API key needed

n8n community node for Blackbox AI chat models

Chutes Models Plugin for OpenCode - Access 58+ state-of-the-art AI models through the Chutes API