pi-context

Agentic Context Management for Pi

Packages

Package details

extensionskill

Install pi-context from npm and Pi will load the resources declared by the package manifest.

npm repo home report

$ pi install npm:pi-context

Package: pi-context
Version: 2.0.0
Published: Jun 17, 2026
Downloads: 1,052/mo · 207/wk
Author: ttttmr
License: MIT
Types: extension, skill
Size: 68.1 KB
Dependencies: 0 dependencies · 3 peers

Pi manifest JSON

{
  "extensions": [
    "./src/index.ts",
    "./src/context.ts"
  ],
  "skills": [
    "./skills"
  ],
  "image": "https://github.com/ttttmr/pi-context/raw/refs/heads/main/img/context.png"
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

Pi Context: Agentic Context Management for Pi

An Agentic Context Management tool that helps AI agents keep long conversations focused by maintaining a clean working set: checkpoint useful anchors, inspect the active history structure, and compact noisy completed paths into state summaries.

Inspired by kimi-cli d-mail, it brings lossless time travel to Pi's session tree.

For more on the design philosophy, see the blog post (中文版本).

Naming migration note

Earlier versions used more Git-like names such as context_tag, context_log, and context_checkout.

Current versions intentionally use conversation-native names instead:

context_checkpoint
context_timeline
context_compact

These tools manage conversation history, not repository state. They should not be treated as Git commands or as replacements for real git tag, git log, or git checkout. Context navigation does not modify or roll back files, running processes, browser state, tickets, databases, or remote services.

Installation

pi install npm:pi-context

Usage

For Humans

Run the following command to enable ACM (Agentic Context Management) for the current session.

/acm

Open a visual dashboard to inspect context-window usage and token distribution (similar to claude code /context).

/context

For Agents

This extension adds the context-management skill, which guides agents to keep the active conversation as the smallest sufficient working set for the next step. It includes three core tools:

🔖 Anchor (context_checkpoint) Label a meaningful conversation node with a unique semantic checkpoint name, such as parser-fix-start or timeout-investigation-search.
📊 Inspect (context_timeline) View the active path as a structural map of checkpoints, summaries/compactions, branch points, user turns, and current position. Use it when orientation or compact target selection depends on history shape.
⏪ Compact (context_compact) Create a summarized continuation branch from an earlier checkpoint, history node, or root. The summary should restore the useful state after the target: current task, decisions, external side effects such as changed files or remote updates, validation state, source anchors, and the explicit next step.