AI News HubLIVE
In-site rewrite4 min read

Show HN: EGC - MCP server that gives AI coding tools memory across sessions

EGC is a local runtime that provides persistent memory for AI coding tools, enabling them to retain context across sessions without manual prompting. It saves decisions, failures, preferences, and next steps, and automatically loads them at the start of new sessions. Supports multiple tools and models including Claude Code, Cursor, Gemini CLI, and more.

SourceHacker News AIAuthor: fmarzochi

Uh oh!

There was an error while loading. Please reload this page.

Notifications You must be signed in to change notification settings

Fork 16

Star 23

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

386 Commits

386 Commits

.agents

.agents

.clusterfuzzlite

.clusterfuzzlite

.codebuddy

.codebuddy

.codex-plugin

.codex-plugin

.codex

.codex

.cursor

.cursor

.gemini-plugin

.gemini-plugin

.github

.github

.kiro

.kiro

.opencode

.opencode

.trae

.trae

agents

agents

assets

assets

commands

commands

docker

docker

docs

docs

examples

examples

fuzz

fuzz

hooks

hooks

manifests

manifests

mcp-configs

mcp-configs

mcp/servers

mcp/servers

memory

memory

rules

rules

schemas

schemas

scripts

scripts

skills

skills

src/llm

src/llm

tests

tests

translations

translations

.coderabbit.yaml

.coderabbit.yaml

.env.example

.env.example

.gitignore

.gitignore

.gitlab-ci.yml

.gitlab-ci.yml

.markdownlint.json

.markdownlint.json

.mcp.json

.mcp.json

.mcp.json.example

.mcp.json.example

.npmignore

.npmignore

.prettierrc

.prettierrc

.sonarcloud.properties

.sonarcloud.properties

.tool-versions

.tool-versions

.yarnrc.yml

.yarnrc.yml

AGENTS.md

AGENTS.md

CHANGELOG.md

CHANGELOG.md

CLAUDE.md

CLAUDE.md

CODE_OF_CONDUCT.md

CODE_OF_CONDUCT.md

CONTRIBUTING.md

CONTRIBUTING.md

Dockerfile

Dockerfile

GEMINI.md

GEMINI.md

LICENSE

LICENSE

README.md

README.md

VERSION

VERSION

agent.yaml

agent.yaml

codecov.yml

codecov.yml

crowdin.yml

crowdin.yml

eslint.config.js

eslint.config.js

glama.json

glama.json

install.ps1

install.ps1

install.sh

install.sh

package-lock.json

package-lock.json

package.json

package.json

yarn.lock

yarn.lock

Repository files navigation

Language / Idioma

English | Español | Português (Brasil)

EGC - Extended Global Context

Your AI agents never start from zero again.

No commands to learn. Just work -- EGC handles the rest.

EGC is a local runtime that gives every AI coding tool you use a persistent memory. At the end of each session, your AI saves what it learned: decisions made, what failed, your preferences, what to pick up next. At the start of the next session, it loads that state back on its own -- no prompting required. Say "let's continue" or "where did we stop?" in any language and your AI already knows what to do. One install covers Claude Code, Cursor, Gemini CLI, Windsurf, and more. Works with Claude, GPT-4o, Gemini, and OpenRouter models including DeepSeek, Qwen3, and Llama 4.

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 -- on its own, without you asking. 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 EGC gives your AI

EGC ships two MCP servers that work together during every session.

Memory - 14 tools that your AI uses automatically

No commands to memorize. Your AI reads this table so you never have to. Say anything in any language -- "continue from yesterday", "remember this decision", "what broke last time?" -- and it calls the right tool. You just work. EGC handles the rest.

egc-memory

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

working_memory_set Stores transient context with a TTL

working_memory_get Reads a transient key

working_memory_list Lists all live transient entries for the current project

lesson_save Records cross-session knowledge with confidence decay

lesson_recall Retrieves active lessons above a confidence threshold

lesson_reinforce Boosts confidence on a lesson when the same pattern repeats

detect_patterns Surfaces repeated commands and recurring errors from hook events

compress_observations Compresses raw hook observations into typed summaries to reduce token usage

get_project_state Returns server health metadata and storage engine status

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

Context and safety - 5 tools for when things get heavy

egc-guardian

These tools run automatically in the background. Every shell command and every file write is checked before it executes. You never invoke them directly.

Tool What it does

validate_command Checks shell commands against project safety rules before execution

validate_write Validates file write paths to prevent unsafe writes

reduce_context Compresses file payloads to save your token budget

orchestrate_task Routes prompts with agent/skill context and returns compression metrics

auto_learn Mines session failures and writes actionable lessons to CLAUDE.md

Always in sync - across every tool you use

egc watch -- run it once and every tool you use stays in sync. Edit context in Cursor and it appears in Gemini CLI, Copilot, Windsurf, and everywhere else automatically. When your state updates, all your tool config files update with it. No manual steps, no stale state.

egc watch # watch current project egc watch /path/proj # watch a specific project egc watch --quiet # suppress output

Prompt library

479 components included as a bonus. Install to get access to 63 agents, 229 skills, and 76 commands written from real engineering sessions. Skip them entirely and EGC still gives you persistent memory.

Support EGC

EGC is built by one developer, maintained in the open, and free.

Website: full docs, feature overview, and live demo

Join the Discord: ask questions, share feedback

Sponsor on GitHub: any amount

Donate via PayPal: no GitHub account needed

Star the repository: helps other developers find it

Contribute: agents, skills, commands, bug fixes, docs

Share: if EGC changed how you work, tell someone

Sponsors

Support from the community keeps this project alive and independent.

Backers

Monthly sponsors · be the first

About

Your AI agents never start from zero again. Local-first MCP runtime with persistent memory across sessions and tools.

fmarzochi.github.io/EGCSite/

Topics

cli

open-source

hooks

typescript

skills

mcp

persistent-memory

cursor

codex

ai-agents

google-ai

gemini-cli

llm-orchestration

antigravity

mcp-server

claude-code

ai-coding-assistant

agent-runtime

claude-code-plugin

multi-harness

Resources

Readme

License

MIT license

Code of conduct

Code of conduct

Contributing

Contributing

Security policy

Security policy

Uh oh!

There was an error while loading. Please reload this page.

Activity

Stars

23 stars

Watchers

1 watching

Forks

16 forks

Report repository

Releases 13

v1.1.2

Latest

Jun 20, 2026

+ 12 releases

Sponsor this project

Uh oh!

There was an error while loading. Please reload this page.

https://www.paypal.com/donate/?business=fmarzochi%40gmail.com&currency_code=USD

Learn more about GitHub Sponsors

Packages 0

Uh oh!

There was an error while loading. Please reload this page.

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

Languages

JavaScript 83.1%

Python 9.4%

Shell 4.1%

TypeScript 3.1%

Other 0.3%