@santiago-r/pi-ml-intern
ML Intern extension for Pi — autonomous ML research & implementation with literature-backed recipes. Inspired by Hugging Face's ml-intern.
6.2k listings for pi · 0 reviewed by us
397 results · page 7 of 9
ML Intern extension for Pi — autonomous ML research & implementation with literature-backed recipes. Inspired by Hugging Face's ml-intern.
Autonomous phase execution for pi — executor → ast-grep audit → LLM audit → remediation loop
dkod extension for Pi — parallel agent execution with AST-level semantic merging
Stateful PUA runtime extension for pi — lifecycle hooks, pressure escalation, capability-aware enhancement, and subagent inheritance
Mixture of Agents for Pi. Registers a virtual `moa` provider (presets selectable in /model) and a `/moa` command that runs one-shot passes plus a drill-down preset menu. Each preset fans out N reference models in parallel over a trimmed transcript, an agg
Persistent, branch-scoped autonomous goals for the Pi coding agent
Pi extension for goal-directed autonomous work loops
Pi extension package for voice-loop operation with provider-backed speech in Pi.
Inject reflection reminders into long-running pi agent loops
Autonomous project director for pi. Recommends actions (NEXT.md), clarifies intent (CHOICES.md), and executes TDD development (PLAN.md) through specialized subagents.
Personal AI Infrastructure extension for Pi — full v4.0.3 sync: ISC splitting test, count gates, anti-criteria, capability tracking, time budgets, enhanced observability, agent personas, sentiment tracking, self-evolution, Ralph iteration, damage control
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Goal-driven autonomous continuation for Pi coding agent - set a goal and let the agent work until done, with LLM-based judge evaluation
Manual janitor for ~/.pi cruft: DS_Store, dead stats-pid, empty session dirs, idle sessions, stale subagent runs.
PI extension that runs a verifier subagent to observe and correct builder sessions
Pi extension that adds the /ralph command — a Ralph Wiggum loop that runs a prompt file over multiple fresh sessions
Enforces sequential subagent execution — prevents concurrent subagent spawns that cause model swapping overhead on single-GPU setups.
Simple scheduled loop/reminder extension for pi
PI-native constrained subagent orchestration library
Pi-to-Pi local bidirectional communication: run peer Pi agents that can message each other on the same machine.
Persistent subagent tools and UI for Pi.
Companion extension for pi-subagents: caps a spawned sub-agent's tool calls (soft nudge + hard stop) so runaway agents finalize instead of overflowing context. No-op outside sub-agents.
Graphite/PR-stack orchestration for pi: a main agent that splits work into PRs, dispatches a dedicated worktree subagent per PR, and lays them out as labelled tmux panes.
Predefined, reusable agent loops for Pi: declarative YAML pipelines with review gates, scoring, and goal-loop convergence. Built on pi-subagents.
Warns the pi orchestrator to delegate after 3 turns — prevents getting stuck in endless work loops
Minimal pi extension: delegate, review, and explore via isolated subagent processes
YARI (Yet Another Repetition Intervention). Interrupts agent tool loops and runaway/stuck thinking.
Universal agent loop with rate-limit detection and auto-recovery for pi coding agent
Dynamic parallel agent execution for pi - run multiple agents with different models without pre-defining configurations
Agent-to-agent message bus for pi — decentralized LAN P2P, agents discover each other via mDNS and talk point-to-point, no server required
A no-nonsense Pi extension for focused foreground child-session delegation.
Enterprise-grade A2A (Agent2Agent) protocol implementation for pi coding agent - enables multi-node, multi-agent collaboration across enterprise environments
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.
Pi extension that gives non-vision models the ability to analyze images via a vision-capable subagent
Workflow orchestration extension for pi-coding-agent — subagent spawning, research workflow, output capture
A Pi extension that indexes your local TypeScript/TSX codebase into Chroma Cloud, enabling semantic and symbol-based code retrieval directly within Pi's agent loop.
Standalone side chat for Pi CLI — parallel AI agent with read-only tools
Detect when problem-solving degrades into unproductive loops, over-reflection, or runaway self-criticism, then stop and escalate to the user for help.
Dual Active eXtension — a symbiont for the Pi coding agent that provides peer code review and loop prevention
Pi extension that runs a prompt or slash command on a recurring interval
Minimal Pi subagent extension with explorer and general roles.
Pi extension: small configuration helper for @gotgenes/pi-subagents agent model and thinking frontmatter.
Minimal pi extension that delegates tasks to isolated subagent processes with optional skill loading
Detect and alert on agentic reasoning loops and tool call repetition in pi-coding-agent
Minimal Pi extension: one subagent tool that spawns role-shaped child pi processes. Roles defined as markdown in ~/.pi/agent/agents/.
Repeat-send a prompt to the pi agent on a fixed interval. Each repeat arrives as a user message with a Loop header (created time / repeat count / user task). Adds /loop commands and a loop tool.
Multi-agent coordination for Pi - presence, messaging, file reservations
Run isolated Pi subagents from Pi via the AskPi tool