@lincoln504/pi-research
A set of web research tools (search, scrape, and others) and research agent system that uses them safely and efficiently.
6.2k listings for pi
662 results · page 4 of 14
A set of web research tools (search, scrape, and others) and research agent system that uses them safely and efficiently.
OpenCode plugin — define custom AI agent roles via YAML with per-role prompts, models, skills, and permissions
Pi extension. Shell-style $1 / $ARGUMENTS placeholders and !`cmd` / ```! shell substitution, expanded into your Pi skills at invocation.
A skill-based development workflow for Pi Agent. 27 contract-carrying skills (discover → research → design → plan → implement → validate → code-review → commit, and more), the 15 named subagents they dispatch, and five built-in /wf workflows that chain th
Pi extension. Chain skills into typed multi-stage workflows with audited JSONL state, predicate routing, and per-stage output validation. Skill-agnostic — bring your own skills.
Pi package that adds document_parse, document_search, document_screenshot, and a companion skill for local document understanding with LiteParse v2.
Multi-agent fleet orchestration for coding agents. Pi as the primary runtime, Herdr as the workspace control plane, coms as the peer data plane, and Hermes for remote control — plus skills, personas, harnesses, and a guided setup CLI.
Pi extension for Maestro knowledge and workflow orchestration with teammate dispatch
all Howaboua Pi extensions and skills
Pi adapter for dotdotgod: project-initializer skill, shared docs scaffold, plan/archive workflow, and project loading extensions.
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.
Passive Obsidian vault extension — watches @agent markers, dispatches forked subagents, and stores knowledge in LanceDB with vector, full-text and graph search.
Agentic Context Management for Pi
Reusable Pi agent platform, project adapters, MCP/tool policy, and coding workflow harness.
Fixed two-line status footer for pi with model, thinking, context, git, token, worktree, and skill indicators
Armin's pi coding agent commands, skills, extensions, and themes
SuPi claude-md skills — CLAUDE.md/AGENTS.md maintenance workflows for pi
Operator console (a pi extension) + skill for pi-dispatch: run the pi coding agent as a self-hosted service. A /dispatch TUI for the queue, spend caps, run history, editable GitHub and GitLab triggers (cron/label/comment/PR/MR), and scheduled pause window
Read, edit, redline, and comment on Microsoft Word .docx files from the command line — built for AI agents.
Pi extension — agent skill loader (skill tool + skills bundle)
Add external directories to your pi session — loads their AGENTS.md, CLAUDE.md, and skills into context.
JHP's Pi extension suite for team coding workflows
Human-reviewed habits for Pi coding agents—a local-first behavioral learning layer alongside skills and memory.
A discoverable /exec command and exec-plan skill for reliable, resumable ralphex-style plan execution in Pi
Semantic loop-engineering for agent-owned, visible, interruptible continuation in Pi.
SuPi extras — command aliases, skill shorthand, tab spinner, /supi-stash prompt stash with TUI overlay, and other small utilities
Personal agent skills collection for pi, Claude Code, Codex, Cursor, etc.
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
Toggle skill visibility in pi's system prompt — flip disable-model-invocation on skills via an interactive TUI
Deep research skill for pi — structured search, reflection, and analysis.
Ory plugin for Pi (the minimal coding agent): scaffolding skills, a local Ory instance, and authentication, authorization, and audit for every tool call
Xquik TypeScript SDK & agent Skills for X/Twitter data, automation, MCP & webhooks. Not affiliated with X Corp.
Agent skill that generates beautiful HTML pages for diagrams, diff reviews, plan reviews, slide decks, and data tables
Interactive Pi command to enable or disable local skills from a multi-selection list.
Pocket-driven development skills: structured subagent delegation, bug hunting, iterative planning, and code review workflows for Pi.
Pi extension for managing skill/package catalogs.
Namespace tools and skills in pi — group tools by extension with configurable prefix rewriting
Amber Protocol: repository-local governance kit for coding agents — install, audit, validate, and hand off agent-facing project state.
Declarative, user-definable permission modes for the pi coding agent: OS-level sandboxing (bubblewrap / sandbox-exec), an allow/ask/deny policy engine, real bash AST gating (tree-sitter), tool hiding, and skill/custom-tool gating.
Feedback-based control system for coding agents.
Detailed guidance for creating Agent Skills (Pi-compatible Agent Skills format).
Governed AI coding harness for pi.dev — bootstrap, plan, execute, review, and steer with deterministic policy gates
Pi package that moves skill discovery from slash commands to $ mentions.
Footer widget with costs, cache, turns, ctx window tracking etc. Detailed usage reports, Isolated SSH, Self learning & injecting issues & solutions, various skills, 3 themes, prompt repeater, shortcuts and more.
Evidence-driven engineering review, validation, remediation planning, and quality governance for real codebases.
The simple way to obtain the best code. Portable rules, skills, and slash commands for AI agents with lowest tokens usage.
ADLC integration for the pi terminal coding agent: in-session rail/scope/suppression enforcement, native adlc_prosecute/adlc_gate tools, lifecycle skills.
Pi-ponytail — lazy senior dev mode for your Pi agent. Forked from DietrichGebert/ponytail.