pi-bob
Pi provider extension for IBM Bob / IBM-approved compatible model endpoints.
6.2k listings for pi
691 results · page 9 of 15
Pi provider extension for IBM Bob / IBM-approved compatible model endpoints.
Pi extension: register a self-hosted New API gateway as a custom OpenAI-compatible provider.
Auto-continue after Z.ai usage limit resets, with a live countdown and retry suppression.
A pi extension that enables OpenAI Codex Fast mode for ChatGPT-auth GPT-5.4, GPT-5.5, and GPT-5.6 Codex variants by injecting the priority service tier.
See your agent usage and cost directly in Pi — costs, languages, models, projects, and tools from session logs.
ACP bridge providing Claude Code, Codex, and Gemini CLI backends to pi-coding-agent, with the entwurf orchestration surface for cross-session delegation.
Check Codex usage limits, reset times, and reset-credit coupons from a fast, read-only terminal dashboard.
Lean Poolside AI model provider for Pi with live model discovery
Run [Berget AI](https://berget.ai) models inside [Pi](https://pi.dev).
Voice input for Pi. Multi-provider STT with Deepgram streaming, Groq Whisper, OpenAI Whisper. 56+ languages.
pi extension for the Kiro API (AWS CodeWhisperer/Q) — 12 kiro-cli-verified models with OAuth authentication
SAP AI Core (orchestration + foundation) provider for the pi coding agent
Pi extension for Codex usage visibility and fast-mode control
Opinionated multi-provider coding harness for the pi agent
Pi extension: Zero-setup multi-backend OCR — MinerU (free cloud), Ollama (local GPU, LaTeX formulas), Pix2Text (local Python). Extract text, formulas, and tables from images and PDFs. Default: zero config, works out of the box.
Pi coding agent extension for analyzing token usage and cost across session files
Native OpenRouter model sync for pi using built-in provider routing support
Lilac provider extension for pi - Access Kimi K2.6, GLM 5.1, and Gemma 4 models through Lilac's OpenAI-compatible API on idle GPUs
Standalone Pi extension for OpenAI fast mode and image generation/editing.
Pi Coding Agent extension for using Venice.ai as provider, access to ANY and ALL models under the Sun
Cursor AI editor as a native Pi stream provider — @cursor/sdk local-agent mode, API-key auth
Prompt caching for Pi's OpenCode Go provider (kimi, deepseek, mimo, qwen, minimax). Stamps prompt_cache_key, 24h retention, and cache_control breakpoints on every request — beyond what pi-ai or opencode CLI do by default.
Pi extension package that routes each turn by Low/Medium/High/Ultra capability modes.
Pi extension that shows quota usage in the footer for supported providers.
Focused Pi extension package for showing OpenAI Codex subscription usage in the status line.
OpenAI Codex usage status for the Pi footer
Pi extension that routes model groups to concrete models. Balances intelligence, cost, and availability.
OpenRouter provider with OAuth PKCE and dynamic model filtering
Model usage analytics extension for pi — track tokens & cost by model, project, and session
Use Claude Pro/Max subscription with pi — bypasses third-party app detection
Connect the Pi coding agent to local & self-hosted LLMs — Ollama, LM Studio, llama.cpp, llama-swap, vLLM, and any OpenAI-compatible server. Auto-discovery, model switching, and zero-JSON in-TUI onboarding.
Use Codex from pi-coding-agent to review code or delegate tasks.
Screenshot picker extension for pi coding agent - quickly select and attach screenshots to your prompts
Kilo Code provider extension for pi
Pi provider extension for Volcengine Ark Agent Plan (api/plan/v3).
Pi Coding Agent custom provider that routes requests through the Cursor Agent CLI — use your Cursor subscription models (Claude, GPT, Gemini, Grok…) inside Pi.
QwenCloud provider for pi — access Qwen3.8, DeepSeek V4, GLM-5.2, Wan image generation, and HappyHorse video generation through QwenCloud's OpenAI-compatible API
pi extension that auto-discovers Ollama Cloud models from ollama.com and registers them as an `ollama-cloud` provider.
OAuth login provider extension for Google Antigravity models in the Pi Coding Agent
Pi extension that adds web_search and web_fetch tools using each provider's native search backend (ZAI MCP, Anthropic, Google, OpenAI, xAI, Claude Code subscription via claude-bridge), with DuckDuckGo as a universal fallback.
Pi statusline extension — shows context usage, token speed, and provider quota in the footer.
Opper AI gateway provider and tools for the pi coding agent
Google Vertex AI provider for Pi coding agent - supports Gemini, Claude, and all MaaS models
Run Hugging Face onnx-community models locally inside pi: registers a chat provider for ONNX text-generation models and a set of tools (embeddings, classification, ASR) backed by @huggingface/transformers and onnxruntime-node.
Lightweight sub-agents for pi — spawn specialized agents with isolated sessions, tools, and models.
Fail-open fork of cc-safety-net — blocks destructive git/filesystem commands, but defaults to fail-OPEN on broken/legacy config so the shell never bricks.
Claude (Anthropic OAuth/subscription) compatibility layer for pi-coding-agent — keeps ALL extension tools usable under the Claude subscription by mapping unknown flat tool names to mcp__pi__<name> on the wire instead of dropping them, plus optional multi-
Pi extension — API key pool with session-based rotation, cooldown recovery, smart retry, and auto provider detection