pi-whisper-voice
Minimal hold-SPACE voice input for Pi using an OpenAI-compatible Whisper/STT endpoint.
6.2k listings for pi
691 results · page 11 of 15
Minimal hold-SPACE voice input for Pi using an OpenAI-compatible Whisper/STT endpoint.
A keyboard-first Pi extension for switching GPT-5.6 capability models and thinking levels within the active provider.
Pi extension that registers an inspect_image tool — analyzes local image files using a configurable vision-capable model via OpenAI-compatible API
Custom model providers for pi
Interactive TUI for discovering and managing local AI model endpoints (llama.cpp, oMLX, Ollama, vLLM, SGLang, LM Studio). Reads real server-reported model configurations — no hardcoded databases.
Codex account rotation extension for pi
Pi coding-agent extension: use frontier Anthropic, OpenAI, and Tinfoil models through nullsink — the anonymous, account-less, crypto-paid metered proxy.
Dev tool: on every provider request, dump the exact payload pi sends (final system prompt plus messages) to a file so you can see precisely what the model receives.
Google Vertex AI Claude provider for Pi coding agent
Pi package for OpenAI/Codex image generation with a local browser studio.
Fast mode toggle for OpenAI and Codex models in pi.
DeepSeek model pricing extension for pi coding agent — shows peak/off-peak pricing status in the status bar
Pi provider for vip.j3gb.com's OpenAI Chat Completions and Anthropic Messages gateway
GitHub Copilot premium request usage in the pi status bar
Pi image generation tool powered by OpenAI (GPT Image, DALL-E)
Provider-only Pi package that registers the curated ZenMux model set used by pi-excalibur.
Pi extension: llama-swap provider with dynamic model discovery
Shows Kimi usage in the pi status bar when a Kimi model is selected
xAI Grok Build provider for pi: OAuth login (borrowed Grok CLI client) plus Grok chat models over the OpenAI Responses API. OAuth only. Usable as a pi extension or as a pi-ai library provider.
Mixed-protocol relay model discovery and metadata matching for pi
Kimi K3 prefix-cache optimizer extension for pi-agent (dual-channel, zero-fork)
Pi extension that shows xAI SuperGrok subscription usage in the status line
Pi extension for monitoring API key balance and subscription quota (DeepSeek, OpenCode Go, and more)
Pi extension that shows tokens, context usage, cost spent, and model/reasoning in the footer.
Fast local workspace Finder for Pi using rg retrieval plus configurable OpenAI-compatible rerankers
Pi coding-agent extension that exposes CLIProxyAPIPlus models (Claude, Gemini, OpenAI/Codex, Copilot, Kiro, GLM, Qwen, ...) to pi's model picker, routing each family through its native streaming API (anthropic-messages, openai-completions, google-generati
Mixlayer provider extension for pi.
Plays motivational music while Chinese-origin models (DeepSeek, MiMo, Kimi, etc.) are thinking — with dynamic volume ramp and bit-crusher distortion that gets worse the longer the model thinks.
StarRouter is a focused model-routing extension for Pi. It chooses the best available model and thinking level for each prompt using a deterministic heuristic prompt profiler, Artificial Analysis benchmark data, provider-scoped model pools, strict model i
Clone Pi model providers under separate provider IDs and credential scopes
ZenMux provider extension for Pi — dynamic model discovery with caching
This extension registers a custom provider that routes LLM calls through the **Claude Agent SDK** while **pi executes tools** and renders tool results in the TUI.
LLM spend tracking, budget alerts, auto-downshift, and hard cutoff for AI coding agents — as a CLI, an MCP server, a Claude/Cursor skill, or a pi extension.
Sampling mode proxy for Qwen models served via llama.cpp — switch between thinking, coding, and instruct modes
Claude Code-style /usage panel for pi — Pi-chan navigation, seven views, 5H/weekly quota, attribution by model/skill/bundle/plugin/tool/project, Wrapped year-in-review with monthly heatmap, multi-skill + bundle tracking, live upstream quotas (ZAI, OpenAI
Tiny pi extension to toggle OpenAI GPT Fast mode.
LLM cost tracker — track spend per session, model, and project
A [pi-coding-agent](https://github.com/earendil-works/pi-coding-agent) extension that registers a **deepseek** provider via a configurable AI proxy.
ZenMux provider extension for Pi — dynamic model discovery with caching
Pi extension: gemini_proxy tool — delegate tasks to Google Gemini CLI from within pi
Dedicated Azure Foundry and AWS Bedrock provider policy for Pi
Pi extension that restores the Antigravity (Gemini 3, Claude, GPT-OSS) OAuth provider.
Pi extension wrapper for CodexBar provider state and controls
OpenAI native standalone compaction replay for Pi.
Pi extension: active-provider quota footer for OpenAI Codex and Kimi Coding.
pi extension that registers your llama.cpp server as a provider and auto-discovers every model it exposes at /v1/models — context size, vision and thinking support included
pi extension for the Kiro API (AWS CodeWhisperer/Q) — 12 kiro-cli-verified models with OAuth authentication
A Pi extension that adds [LLM Gateway](https://llmgateway.io) as a model provider, giving you access to 160+ chat models from OpenAI, Anthropic, Google, xAI, Mistral, DeepSeek, and many others through a single OpenAI-compatible API.