@kky42/pi-subagents
Claude Code-style subagents for pi.
6.2k listings for pi · 0 reviewed by us
364 results · page 1 of 8
Claude Code-style subagents for pi.
Multi-agent team orchestration for pi — leader-coordinator pattern with researcher, planner, and implementer teammates in tmux panes
Claude Code-style /loop command for pi-coding-agent.
A pi extension for parallel side conversations with /btw
A focused, in-process sub-agent core for pi — autonomous agents plus a typed API and lifecycle events other extensions build on. Friendly fork of @tintinweb/pi-subagents.
reddb.io dev plugin - engineering skills for code agents (autonomous /afk loop, /go dispatch, triage, tdd, diagnose, graph-aware codebase understanding, ...)
Parallel AI code review for GitHub pull requests in the Pi coding agent, with model-agnostic tiered subagents, structured findings, optional verification, and safe COMMENT-only publishing.
Orchestration spine for long-running pi development
Self-hosted, agent-agnostic secure communication network for Claude, Codex, Pi, Antigravity, and A2A agents
NERVous System — durable multi-agent orchestration, coding-agent coordination, and workflow recovery for pi.
Workflow + project management for pi-coding-agent. Plans, state, MANDATORY rules, self-review, multi-question picker. One npm install, zero config. LLM drives the workflow inline via the soly_workflow tool — no external subagent plugin.
Autonomous experiment loop for pi — run, measure, keep or discard. Inspired by karpathy/autoresearch.
Multi-agent collaboration extension for pi — task decomposition, dependency management, parallel execution, TUI panel
Deterministic multi-agent workflow orchestration for Pi
Asynchronous, resumable, and recursive subagent conversations for Pi with exact-run retrieval and live progress.
A declarative, verifiable graph of task nodes for the Pi coding agent — statically verified before it runs, with dynamic fan-out, gates, isolated subagent context, resumable runs, and saveable commands.
Fire-and-forget goal mode for Pi with visual planning, autonomous recovery, evidence, and independent completion audit.
Unified pi extension. Autonomous engineering skill framework (public skills plus maintainer opt-ins) plus the `delegate` role primitive (explore, session-miner) in one npm package. Successor to the separately-shipped pi-dev (skills) and pi-role (delegate)
Pi tool — planner-driven sub-agents: spawn, fetch, steer scoped child agents
A pi extension for cron/event-based agent re-wake loops and background process monitoring.
Run AI coding agents in pi TUI overlays with interactive, hands-free, and dispatch supervision
In-process subagents for Pi with isolated SDK sessions, parallel and chained delegation, and inspectable threads.
Opinionated, gated workflow skills, subagent personas, and runtime extensions for the pi coding agent.
A pi extension that delegates tasks to a specialized subagent in an isolated pi process.
The armory suite's subagent orchestrator for the pi coding agent — a cross-harness, superpowers-native fleet where every agent is armory-native from birth.
dteam - model-tier routing execution layer and evidence-driven main-agent protocol for Pi; fresh T1/T2/T3 workers, structured verification, and bounded fan-out
TLH extension for single and parallel subagent delegation
Delegating task/subagent extension for Pi: foreground/background subagents, widgets, tmux observability, SDK fallback.
Asynchronous subagent delegation for pi with run, batch, chain, and continuation workflows.
Cynos — an autonomous AI engineering runtime with evidence-based completion verification.
Multi-role LLM orchestration via a guarded, observable handoff state machine — installs as a pi extension exposing `/conduct`.
Pi extension that registers avenor agent runs as tools in your Pi session. When you need a sub-agent to handle a well-defined task — write code, run tests, search a codebase — avenor operates in the background while you keep your session focused.
Effect-based temporal loops for Pi
Subagent dispatch with live TUI streaming and cost tracking
Pi extension that adds /review via an isolated review subagent.
Reusable agent workflows and observable, attachable sub-agents for the Pi coding agent
Extensión de Pi para tareas /loop iterativas con cadencia dinámica o fija y compuertas de seguridad.
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.
Pi extension that runs a strict, multi-agent fairness review of a benchmark task's agent_prompt.md, test.patch, and solution.patch, plus behavioral test-gap analysis, via /checks.
Todo list tool with auto-clear and subagent visibility
Multi-backend subagents and dynamic workflow orchestration for pi.
Agent-harness-agnostic dev-loop infrastructure (Pi and Claude Code) for reusable local and remote development loops
A pi coding-agent extension that runs a prompt repeatedly on a timer, pi event, or self-paced (Claude Code-style /loop)
Stronger answers for hard Pi questions via a parallel model panel + judge, built on pi-subagents
Semantic loop-engineering for agent-owned, visible, interruptible continuation in Pi.
GitHub research subagent for pi: deep-dive specific repos, discover across the ecosystem
Pi extension that derives a goal from the conversation and keeps the agent working until the condition is met
Subagent extension for Pi coding agent. Delegate tasks to specialized agents.