omp packages
-
A context-compression plugin — small context windows (a 100K context is enough), 5x fewer tokens, month-long single sessions (billions of tokens), and compression quality — for all agents: pi, OpenCode, Codex, Claude Code, and more. billion-context is all
-
MCP (Model Context Protocol) adapter extension for Pi coding agent
-
Web search, URL fetching, GitHub repo cloning, PDF extraction, YouTube video understanding, and local video analysis for Pi coding agent. Supports OpenAI, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Crawl4AI, Jina, SE
-
Pi extension for single-agent delegation and scripted multi-agent workflows
-
MCP (Model Context Protocol) client extension for the Pi coding agent — connect Pi to any MCP server
-
Langfuse observability extension for the pi coding agent — traces prompts, agent turns, model generations, and tool calls to Langfuse.
-
Pi extension. A structured questionnaire the model can put to you when it would otherwise guess, with typed options instead of free-form replies.
-
Pi extension. A todo list for the model, rendered as a live overlay that survives /reload and conversation compaction.
-
A CLI that uses a DeepAgents documentation agent to generate and maintain an OpenWiki for a codebase.
-
Adds /goal to pi: conversational goal planning, flexible or ordered goals, persistent progress, and an independent completion auditor.
-
Plannotator Pi extension - interactive plan review with annotations, annotate agent messages, and review code/PRs
-
Postman's API engineering skills for coding agents: a Pi package, and an npx installer that sets up Claude Code, Codex, Cursor, Kimi Code, Factory Droid, OpenCode and Pi.
-
73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers
-
Powerline-style status bar extension for pi coding agent
-
The open source AI research agent.
-
MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.
-
Lazy senior dev mode for AI agents. The best code is the code you never wrote.
-
Pi extension for durable background shell tasks, read-only delegated agents, local attested Pi runs, and fixed-purpose Fusion workflows through child Pi processes.
-
LangSmith extension for Pi Coding Agent
-
Real-time code feedback for pi — LSP, linters, formatters, type-checking, structural analysis & booboo
-
Pi extension for provider usage, limits, reset times, API balances, and Codex Fast mode.
-
Pi extension that uses Claude Code (via Agent SDK) as a model provider and adds an AskClaude tool.
-
Claude Code-style TUI output with some personal touches and handy utilities.
-
Advanced Executor/Advisor flow for Pi, fully configurable and extendable.
-
Permission enforcement extension for the Pi coding agent.
-
A coding agent CLI hook - block destructive commands and secret file access
-
Pi extension for autonomous single-objective /goal completion.
-
Log sink MCP server with HTTP ingestion and AI analysis
-
A command-line interface for Atlassian Confluence with page creation and editing capabilities
-
[BETA] Codex-style /usage status + autonomous coding harness for pi. Not production ready — expect breaking changes.
-
One billion, not one million. Model-driven context management for the Pi coding agent.
-
Provider-native web search for pi: Gemini + URL Context, xAI Grok, OpenAI Responses (Azure/Codex/Copilot), Anthropic, DeepSeek, and OpenCode Zen/Go
-
Pi coding agent extension for memory with qmd-powered semantic search across daily logs, long-term memory, and scratchpad
-
A Pi extension that reviews recently changed code for clarity, consistency, and maintainability.
-
A pi extension for parallel side conversations with /btw
-
pi extension: FFF-powered fuzzy file and content search
-
Turn Pi into el Gentleman: an ODD development harness with focused subagents, configured TDD evidence, native review, and skill discovery.
-
A programmable tool and agent runtime for Pi
-
A pi extension that brings Claude Code-like sub-agents and workflow orchestration to pi — parallel execution, live widget, fleet view, custom agent types, mid-run steering, dynamic workflows, Claude Code compatibility, look and feel.
-
Improve Pi prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.
-
Pi extension. The localization foundation for rpiv-* skills: locale detection, the /languages command, the --locale flag, and a cross-package locale registry.
-
Soul-bound workflow roles for Pi
-
Braintrust extension for pi. Includes automatic tracing for pi sessions, turns, LLM calls, and tool executions to Braintrust.
-
🐿️ A Pi extension that archives sessions into local content-addressed storage.
-
MMI workflow skills and org gates delivery.
-
Browser tools for your agent: framework-neutral tool catalog, per-model compilation, Kernel-browser execution, and a pi binding + extension
-
Persistent memory for Pi agents — one local-or-cloud brain shared across sessions, compactions, and MCP agents
-
Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and real-time push delivery over TCP
-
KXM local-first multi-agent orchestration and operator dashboard
-
<p> <img src="banner.png" alt="pi-intercom" width="1100"> </p>