Untested on omp
-
Mobile remote control and local agent mesh for the Pi coding agent. Pair your phone via QR over a relay, watch tool calls in real time, run multi-Pi sessions over a local Unix Domain Socket broker, and let agents talk to each other through structured requ
-
Pi extension: lightweight subagent runner with streaming execution, live TUI progress card, parallel/chain execution, and zero framework lock-in.
-
OpenCode Zen session auto-refresh and free-tier model catalog synchronization for the Pi coding agent.
-
Langfuse extension for Pi coding agent
-
reddb.io dev plugin - engineering skills for code agents (autonomous /afk loop, /go dispatch, triage, tdd, diagnose, graph-aware codebase understanding, ...)
-
Host-neutral notes, history and context-window core, with plugins for Pi, Claude Code, the DeepSeek Harness and Codex.
-
Batteries-included local multilingual MoE Text-to-Speech with acoustic classifier, audible calibration testing, router-in-the-weights, and calibrated LoRA personas for Pi
-
OptChat memory for Pi: persistent profiles, zoomable history, background agents, and conversation imports.
-
Blocking + background subagents for skills that require subagents (code-review, design-it-twice, improve-codebase-architecture, research, wayfinder, grilling, no-comments), including a pstack-derived comment-audit role.
-
Role-based subagent orchestration for pi — delegates tasks to specialized pi child processes with configurable model roles
-
Pi extension providing /rewind checkpoint navigation
-
LSP and AST navigation, search, diagnostics, and refactoring
-
Structured choice and text forms for agent-user decisions
-
Give text-only pi models vision — describe images with a vision model you pick via an interactive picker, then hand off the text description to non-vision models
-
Pi-native Compound Engineering package for iterative development workflows
-
Pi-native fork of pstack skills, Poteto Mode, and bundled agents. Delegates through pi-herdr-agents instead of its own subagent tool.
-
Unified subagent execution and multi-agent workflow orchestration for Pi — spawned-process agent runtime with sync/background modes, stateful workflow management with persistence, state machine, and execution tracing.
-
A programmable tool and agent runtime for Pi
-
Adds a configurable multi-agent layer to pi, with context management, Codex quota status, a custom footer, and more.
-
Run any shell command and pi subagents under babysit, with context-safe captured output.
-
Ultra-lean supervisor. Three-layer guardrails. Semantic gate for Pi. Blocks destructive commands offline, checks tests, gates diffs through TypeSafe Jev, OpenRouter, or Cloudflare Workers AI (Clef), and reports Jev/Clef spend in /jev-eye usage.
-
Long-running agent loops for iterative development in Pi.
-
Connect independent Pi terminals with live presence, automatic message delivery and clear submission receipts.
-
A collection of pi extensions and skills for annotation UIs, context management, workflow audits, contrarian review, review-comment triage, notifications, brrr push alerts, safety guards, GitHub research, repo-local knowledge, todos, tool rendering, model
-
Save 80%+ context tokens in Pi — automatically compresses huge bash/grep logs, caches duplicate file reads, prunes unused tools, and blocks accidental .env/git deletions.
-
Pi package that polishes your daily experience
-
Default shell timeouts that prevent stalled Pi sessions
-
Subagent jobs with asynchronous main-agent messaging for Pi.
-
Define arbitrary workflows in TypeScript and run them inside the PI coding harness.
-
Pi extension for LINE:HASH-anchored file operations and structural code navigation
-
Fail-closed, model-backed approval broker for Pi: deterministically hard-denies dangerous operations, reviews dangerous boundaries with a reviewer model, and issues one-shot expiring grants that OS sandbox adapters must consume before retrying.
-
SQLite-backed project memory for Pi
-
reddb.io brain plugin - project-local RedDB knowledge repository for freeform captures and graph connections.
-
践行 Project Harness 的全流程 AI 编程工作流治理引擎
-
Pi coding-agent extension for CodeGraphContext (CGC): index lifecycle gate, freshness sync, agent routing guidance, status surfaces, and CLI-gap tools wrapping the cgc binary.
-
Pi extension — teammate agent dispatch with DAG task graphs, RPC messaging, and compact TUI
-
Herdr-backed subagents for Pi: visible, steerable, resumable child agents in Herdr panes
-
Integrated toolkit extension for pi — ask mode (read-only Q&A), session-scoped permission checks, model favorites, prompt stash, third-party code review, session autostart, and a dedicated compaction model
-
Run inspectable interactive Pi subagent batches through Herdr.
-
Todo list tool with auto-clear and subagent visibility
-
Claude Code provider and delegation bridge for Pi
-
A shared public square where agents join, catch activity, express, and step out when done.
-
Skills to maintain CLAUDE.md and AGENTS.md guidance
-
Historical Pi-session reports and shareable HTML
-
Clearer Pi replies with Jev review, optional rewrite/visuals, and on-demand bilingual settings.
-
reddb.io internal plugin - maintainer-only skills for operating the red-skills repository.
-
Pi session search, ask, handoff, messaging, auto-titling, and indexing tools
-
Pi coding-agent package for The Librarian: the 7 memory/handoff tools + primer injection, backed by a remote Librarian MCP server.
-
Voice in + voice out for Pi CLI — hold-to-talk STT for Chinese and English (Deepgram streaming or 21 offline models) plus TTS (Kitten Nano, Piper, Kokoro, or Deepgram Aura)
-
Pi provider that runs your Claude Code subscription as pi models via the Claude Agent SDK.