GolemsGolems
Golems logo
Spawn→Work→Die→Remember

Your AI agents work alone. They don't have to.

Three open-source MCP servers that give AI agents persistent memory, voice I/O, and multi-terminal coordination. 45 tools. One ecosystem.

Voice→Claude→Memory
Claude→Orchestrate
BrainLayer
Persistent memory for AI agents

313K+ chunks indexed. 8,790 KG entities. Search quality 2.6 → 4.04/5 after v2 prompt rewrite.

Visit site →
VoiceLayer
Voice I/O for AI agents

592 tests. 11 MCP tools. Talk to your agents, hear them respond.

Visit site →
cmuxLayer
Multi-terminal orchestration

346 tests. 1,423x faster than shell. Spawn, coordinate, and monitor AI agents.

Visit site →
$ npx golems-cli install

Or install individually: pip install brainlayer · npm i voicelayer-mcp · npm i cmuxlayer

Get StartedGitHub →

What Changes

Three problems. Three open-source solutions.

×

Your agent forgets everything between sessions

✓

Persistent memory across every conversation

BrainLayer
×

You type every command by hand

✓

Talk to your agents, hear them respond

VoiceLayer
×

One terminal, one task, waiting for each to finish

✓

Spawn parallel agents across coordinated panes

cmuxLayer

Get Started

One command for everything, or install what you need. Full guide →

Full ecosystem
$ npx golems-cli install

Installs all three MCP servers, wires Claude Code config, and verifies the setup.

or install individually
BrainLayerPython
pip install brainlayer

Persistent memory — semantic search, entity graph, knowledge digest

VoiceLayerNode.js
npm i voicelayer-mcp

Voice I/O — speech-to-text, text-to-speech, 11 MCP tools

cmuxLayerNode.js
npm i cmuxlayer

Multi-terminal — spawn agents, coordinate panes, monitor output

Full Setup Guide
45MCP Tools
2,941Tests Passing
313K+Knowledge Chunks
8,790KG Entities
56Skills

Skills Library

56 reusable Claude Code skills. Install any skill with one paste.

56
Skills
golems-cli skills install
$ golems-cli skills install cmux-agents
=== INSTALLING cmux-agents ===
Downloading: github.com/EtanHey/golems/skills/golem-powers/cmux-agents/
✓ SKILL.md
✓ evals/evals.json (39 evals)
Symlinking: ~/.claude/commands/cmux-agents/ → installed
First-Time Setup:
Checking ~/.golems/config.yaml...
○ Config not found — running wizard
Detecting AI CLIs:
✓ claude /usr/local/bin/claude
✓ cursor /usr/local/bin/cursor
✓ gemini /usr/local/bin/gemini
○ codex not found
○ kiro not found
Workspace path: ~/Projects
✓ Config written to ~/.golems/config.yaml
✔ cmux-agents installed! Use /cmux-agents in any Claude session.
_
cmux-agents39 evalsPortable

Install Prompt

Paste this into any Claude Code session to install cmux-agents:

Install and configure the cmux-agents skill for managing AI agents
in terminal panes. Download from github.com/EtanHey/golems and
symlink to ~/.claude/commands/cmux-agents/. If ~/.golems/config.yaml
doesn't exist, auto-detect installed AI CLIs (claude, cursor, gemini,
codex, kiro) and ask for workspace path. Then follow the First-Time
Setup section in the SKILL.md.

First-Time Setup

  • Auto-detects installed AI CLIs (Claude, Cursor, Gemini, Codex, Kiro)
  • Asks for your workspace path
  • Writes ~/.golems/config.yaml
  • Ready — use /cmux-agents in any session
/pr-loop17 evals

Full PR lifecycle: branch → test → review → merge

/coderabbit3 evals

AI code review with multiple workflows

/cmux-agents39 evals

Spawn AI agents in terminal panes — Claude, Cursor, Gemini, Codex, Kiro

/cmux6 evals

Terminal multiplexer management

/1password3 evals

Secret management, env migration, vault ops

/golem-install11 evals

Setup golems ecosystem with guided wizard

/github-research3 evals

Explore and document unfamiliar repositories

/never-fabricate7 evals

Mandatory verification before reporting results

/large-plan7 evals

Multi-phase plan scaffolding and execution

/coach33 evals

Health, schedule, life planning with Whoop integration

/figma-loop3 evals

Iterative Figma-to-implementation workflow

Browse All Skills on GitHub →

Skills Work on Any AI

3-layer adapter architecture · one adapter file per CLI

Layer 1
SKILL.md
Universal best practices with platform-agnostic fallbacks. Any AI can follow it.
Layer 2
capabilities.yaml
Machine-readable feature matrix. Routes tasks to the right CLI automatically.
Layer 3
adapters/
Exact flags, models, and syntax per CLI. One file per AI. 40-80 lines each.

Skills with adapter support

/cmux-agents/pr-loop/coach

Built by Etan Heyman

AI engineer building open-source tools for AI agents.

Etan Heyman
Etan Heyman
AI Infrastructure & Developer Tools

Designed the architecture and built 3 MCP servers, 60 AI-agnostic skills, and an agent orchestration layer. BrainLayer indexes 313K+ chunks across 8,790 KG entities. Orchestrated parallel AI agents for implementation. Every component is open-source, tested (2,900+ tests), and documented.

PortfolioGitHubLinkedIn