EGC

Created By

Fmarzochi6 days ago

EGC is a local runtime that gives every AI coding tool you use persistent memory. At the end of each session, the AI saves what it learned about your project: the decisions you made, what failed, your preferences, what comes next. At the start of the next session, it loads that state back. One install covers Claude Code, Cursor, Gemini CLI, Windsurf, and more. This is what EGC looks like in action:- You open Claude Code on a project you haven't touched in two weeks. Without typing anything: State loaded from egc-memory via ~/.egc/state/Projects--MyApp.md Context and preferences acknowledged (terse responses). Ready to pick up the next items: • Test full install on a clean machine • Add GEMINI.md with session memory protocol • Publish v1.0.1 fix to npm after clean install test passes • Add mcp_server_count to audit.js EGC lets you have extremely long context that is shared across sessions and tools, which is required when building production-level applications. Stop using /compact wherever your context reaches 80% and prevent the rot; adopt EGC.

# Context

# EGC

Overview Content Tools Comments

Overview

EGC - Extended Global Context

Your AI agents never start from zero again.

EGC is a local runtime that gives every AI coding tool you use a persistent memory. At the end of each session, the AI saves what it learned about your project: the decisions you made, what failed, your preferences, what comes next. At the start of the next session, it loads that state back. One install covers Claude Code, Cursor, Gemini CLI, Windsurf, and more.

This is what EGC looks like in practice

You open Claude Code on a project you haven't touched in two weeks. Without typing anything:

State loaded from egc-memory via ~/.egc/state/Projects--MyApp.md

Context and preferences acknowledged (terse responses).

Ready to pick up the next items:
• Test full install on a clean machine
• Add GEMINI.md with session memory protocol
• Publish v1.0.1 fix to npm after clean install test passes
• Add mcp_server_count to audit.js

The AI already knows what you were building, what decisions you made, what failed, and exactly where you stopped. It knows because EGC saved that state at the end of your last session and loaded it back when this one started. You didn't type anything. You just started working.

Install

npm install -g @egchq/egc && egc install

Or run without installing globally:

npx @egchq/egc install

Full installation guide

What the MCP server gives your AI

EGC ships egc-memory, an MCP server that exposes 13 tools your AI can call during a session:

Tool	What it does
`get_state`	Loads project memory at session start
`update_state`	Saves decisions, preferences, and next steps
`store_decision`	Persists a single decision to SQLite
`query_history`	Returns past decisions by timestamp
`search_history`	Full-text search with BM25 ranking
`set_working_memory`	Stores transient context with a TTL
`get_working_memory`	Reads a transient key
`delete_working_memory`	Removes a transient key
`add_lesson`	Records cross-session knowledge with confidence decay
`list_lessons`	Retrieves active lessons above a confidence threshold
`forget_lesson`	Removes a lesson permanently
`detect_patterns`	Surfaces repeated commands and recurring errors from hook events
`compress_observations`	Compresses raw hook observations into typed summaries to reduce token usage

State files live at ~/.egc/state/<project-slug>.md. One file per project, plain Markdown, human-readable.

Prompt library

479 components: optional. Install to get access to 63 agents, 229 skills, and 76 commands written from real experience. Skip them and EGC still gives you persistent memory.