A pi coding agent extension that wraps the MiniMax mmx CLI as callable tools with self-evolving architecture
Unified LLM API with automatic model discovery and provider configuration
MiniMax MCP tools for pi - Web search and image understanding via MiniMax's Model Context Protocol
Coding agent CLI with read, bash, edit, write tools and session management
CLI for the MiniMax AI Platform
Pi extension: /usage command showing token rates, reset timers, and live provider status
pi extension for the Kiro API (AWS CodeWhisperer/Q) — 12 kiro-cli-verified models with OAuth authentication
Vercel AI Provider for running MiniMax AI models
MiniMax MCP tools for pi - Web search and image understanding via MiniMax's Model Context Protocol
Codebase CLI — a TypeScript coding agent on the pi-mono runtime. OAuth-aware, any LLM provider, single install.
MiniMax web_search and understand_image tools for pi
π.
Pi coding agent provider for MiniMax AI with M3, Anthropic-compatible streaming, and native MiniMax tools
AI-powered session naming for Pi — generate meaningful, semantic session names via LLM
AWS SDK for JavaScript Pi Client for Node.js, Browser and React Native
MCP (Model Context Protocol) adapter extension for Pi coding agent
Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.
Coding agent CLI with read, bash, edit, write tools and session management
Unified LLM API with automatic model discovery and provider configuration
2π.
The complete Alibaba provider for pi — Plan subscription + Cloud pay-per-token, International + China endpoints, Anthropic + OpenAI shapes, native thinking levels. Qwen 3.6 Max, Qwen 3.6 Plus, DeepSeek V4 Pro, Kimi K2.6, GLM-5, MiniMax M2.5.
Terminal User Interface library with differential rendering for efficient text-based applications
Square root of 2π.
Pi Coding Agent extension — routes bash/read/grep/find/ls through lean-ctx for strong token savings. The embedded MCP bridge (on by default) adds a persistent session cache so unchanged re-reads cost ~13 tokens.