@ariesfish/pi-goal
Autonomous experiment loop for pi — run, measure, keep or discard. Inspired by karpathy/autoresearch.
6.2k listings for pi
397 results · page 2 of 9
Autonomous experiment loop for pi — run, measure, keep or discard. Inspired by karpathy/autoresearch.
Pi extension that auto-sends a 'continue' message whenever the agent stops, so local agents can run autonomous overnight research loops (autoresearch-style) without babysitting.
A pi extension extension that brings smart Claude Code-style autonomous sub-agents to pi.
Simple scheduled loop/reminder extension for pi
Turn skill-constrained workflows into monitored loop graphs — typed stages, mechanism constraints, full replay. Comprehensive AI-friendly docs
Interactive + headless subagent framework for pi and Claude Code, with mux-pane support, sync/async orchestration, and a multi-CLI design.
⚔️ Run the same task across multiple models in parallel and compare answers side by side — with an optional referee judge. Works with every model pi knows, including future ones.
Multi-agent collaboration extension for pi — enables multiple pi instances to communicate and collaborate on shared tasks
Effect-based temporal loops for Pi
Enforces sequential subagent execution — prevents concurrent subagent spawns that cause model swapping overhead on single-GPU setups.
Human-in-the-loop document inquiry and feedback for Pi.
A lightweight subagent spawning and managing system for pi.
Dependency-aware todo orchestration for pi
Minimal Pi subagent extension with explorer and general roles.
A Pi package extension that provides sub-agent functionality.
Generic Symphony autonomous issue orchestration extension for pi.
Execute tasks from task files/PRD's using DAG-based dependency resolution with persistent progress tracking
Native c2c for Pi — anywhere-to-anywhere messaging between AI coding agents. Adds c2c send/list/rooms tools, slash commands, and background auto-delivery of inbound messages straight into pi's transcript.
A conversation-only brainstorm mode extension for pi, with dynamic tool detection (grep, ask_user_question, subagent)
Claude Code-inspired addons for Pi.
Task graph manager for Pi — DAG-based plans with sub-tasks and parallel groups
Recursive decompose-solve-critique-iterate-synthesize loop for Pi — the loop engineering pattern as an extension.
Subagent delegation extension for the pi coding agent — discover, list, and delegate tasks to specialized sub-agents.
Ambient multi-agent observability for Pi — a terminal habitat for coding agents.
A reusable Pi extension that adds a supervised loop harness around the normal Pi coding agent. Supports bounded LLM nodes, deterministic gates, steering, evidence collection, and composable workflow definitions.
Pi sub-agent extension with isolated child sessions, fork-current context, interactive agent chats, bundled agents, and structured result merging.
Opinionated pi extension — lightweight in-process subagent system
Cairn's authoring-and-orchestration loop for the Pi coding agent: /skill:spec, /skill:program, /skill:round-review, /skill:fast-execute, /skill:peer-review, /skill:note. Markdown skills only — no runtime code.
Codex-like /goal command for pi — autonomous goal tracking with continuation loops
Dynamic multi-agent workflow orchestration for the pi agent harness — a faithful clone of Claude Code's workflow primitives (agent/parallel/pipeline/phase/log/budget) with structured output, adversarial verification, resumable journaling, and a live progr
GitHub research subagent for pi: deep-dive specific repos, discover across the ecosystem
A pi extension that brings smart Claude Code-style autonomous sub-agents to pi, with npm:pi-subagents-style JSON agent overrides.
Pi extension for Herdr-visible subagent herds - local-first preference, single-stream local seat, and difficulty-based model routing.
Pi extension for fan-out code review: N parallel reviewer subagents + a cheap-model gate
Pi extension for autonomous software engineering — structured discovery, ADR-driven design, and multi-agent implementation from idea to PR.
A pi extension extension that brings smart Claude Code-style autonomous sub-agents to pi.
Lightweight subagent orchestration for pi.
A pi extension that brings Claude Code-style autonomous sub-agents to pi. Fork of @tintinweb/pi-subagents.
Persistent shared task lists for Pi agents and MCP clients.
A Pi extension that lets local Pi agents join rooms, see each other, and send tasks/messages.
Claude Code-style, controllable Pi subagents with a live TUI dock, foreground switching, persistence, and steering.
A pi extension extension that brings smart Claude Code-style autonomous sub-agents to pi.
Pi extension for delegating tasks to subagents with chains, parallel execution, and TUI clarification
Multi-model collaborative coding & review for pi — Architect → Executor → Codex → Challenger
Pi extension for goal-directed autonomous work loops
Detect when problem-solving degrades into unproductive loops, over-reflection, or runaway self-criticism, then stop and escalate to the user for help.
Autonomous Self-Extending Universal Agent for Pi - ANY task across coding, infrastructure, cybersecurity, cloud, API integration, browser automation, enterprise apps, and more
Autonomous development loop engine for pi — verify-driven iteration with subagent isolation and error tracking