Untested on omp

ClinePass provider for pi — access GLM-5.3, Kimi K3, DeepSeek V4.1 Flash and more coding models through Cline's $9.99/mo subscription

pi extension: reach every connector behind the mem0 gateway from one tool. Five operations, credentials stay server-side

Operator console for pi-dispatch, as a pi extension: a /dispatch panel over the queue, spend caps, scoped limits, run history and insights, editable cron and GitHub, GitLab, Forgejo and Azure DevOps triggers, pause windows, and human-confirmed tools your

Pi adapter for Antigravity Guard

pi arsenal of useful tools

Pi extension that reports provider usage/rate-limit budgets (Codex, Anthropic OAuth, etc.) via /usage, with a live statusline widget.

Pi extension for subagent orchestration and local session coordination

Token-optimized LLM permission reviewer — a pi-permission-system Authorizer chain link

Shared usage data core for pi extensions

Pi tool-output distillation with file-first configuration

Asynchronous agent trees for Pi, adapting Codex multi-agent v2 with plaintext tools and durable mailboxes.

Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fj

Bounded public web search and textual URL fetching for Pi

Shows prompt processing progress from llama.cpp's SSE stream

A pi extension that uses TypeSafe AI's Jev model to curate context before each LLM call, keeping only the context the next call is likely to need.

Pi extension that adds /review via an isolated review subagent.

A Pi extension that keeps long-running agentic sessions on track with background memory, contemplation, and structural review.

Microsoft Teams integration for pi coding agent — acts fully as the signed-in user across multiple accounts and tenants: chats, channels, meetings, presence, with configurable guardrails

Pi extension for Google NotebookLM — notebooks, sources, chat, research, and Studio artifacts via notebooklm-py CLI bridge.

Pi tool that delegates a self-contained sub-task to Google Antigravity's agy CLI (the CLI for Gemini). Friendly model aliases (flash/pro/gemini), configurable default model + thinking, and the AskAntigravity delegation tool.

Pi extension for explicit non-blocking background shell tasks, log tails, and completion wakeups.

Simple agent orchestration for pi coding agent (pi.dev)

Pi extension for isolated or local read-only code review.

Handoff command extension package for pi coding agent

Anthropic Claude models on Google Cloud Vertex AI for pi

Fast, lossless HTML→Markdown conversion with structured metadata, tables, and document-structure extraction.

Rewind Pi conversation context to the latest user prompt.

Pi Extension: OpenSpec workflow orchestration - coder/reviewer/planner agents, session title & progress

Per-turn model routing for Pi: a small judge picks the cheap or the strong tier for each message, with multi-model failover, task-level orchestration, and an optional decision-model judge (Jev) that answers with a calibrated probability instead of prose.

Profile-oriented wrapper for launching pi, Claude Code, and future agent CLIs with reproducible configuration.

Pi extension that uses TypeSafe Jev to route each request into bounded verification, decomposition, or normal response policy.

CLI relay that lets AI coding agents collaborate

Index, summarize, and search past pi sessions. Covers both active and archived sessions, enabling semantic search and introspection over your coding history.

pi 的 Token 用量与配额监控扩展 —— footer 实时显示 token 用量、缓存命中率、输出速率、上下文占用，以及 MiniMax/GLM/Kimi/DeepSeek/mimo 套餐配额；JSONL 记录 + /stats 日/小时/周/月/年多维查询

Quota, balance, and spend indicators for current Pi providers

Pi extension — agent skill loader (skill tool + skills bundle)

Specialist team runtime extension for Pi: independent-process teammates, agent definitions, run lifecycle, backends, steer/stop/resume and inline UI.

Minimal session-native Todo List for Pi agents.

Better compaction for pi: native /responses/compact replay for OpenAI Responses APIs, Anthropic server-side compaction, plus a configurable compaction model driving pi's native summarization everywhere else.

MAGI SYSTEM theme + extension for pi (Evangelion fan art): MAGI control screen panel, three-model /magi council, MECHA SELECT model picker, angel-attack loading, seven-seal context gauge, llama-swap and NInfer telemetry

Governed AI coding harness for pi.dev — bootstrap, plan, execute, review, and steer with deterministic policy gates

Global working memory, SQLite FTS5 recall, and complete Pi session search

Lark/Feishu CLI for the pi coding agent: bundles the official lark-cli binary for your platform plus the full set of official lark-* skills, kept in sync with upstream releases.

pi extension that compresses large tool results before they reach the model: jev picks the view (outline, relevant blocks, sections, signals, testlog), full text stays recallable

Expert Council: cost-aware multi-model expert orchestration for Pi — assemble a council of scout, oracle, implementation-worker, and reviewer experts and delegate bounded tasks

Claude-Code-style dynamic workflow orchestration for Pi.

Parse and extract code intelligence from 372 programming languages with tree-sitter — structure, imports, symbols, and syntax-aware chunking.

Pi subagents you can watch work: parallel agents in Herdr workspaces, reviewed changes, and automatic cleanup.

Multi-level subagent orchestration plugin for Pi — no built-in templates, no preset workflows, everything is yours to shape

Pi extension that routes each session between a cheap flash model and a strong pro model based on issue difficulty - Claude Code style haiku/sonnet/opus tiering, config-driven for any model family.