agent-of-empires and claude-forge
These are complements—agent-of-empires provides the terminal session orchestration infrastructure (tmux/git worktrees) while claude-forge layers AI agent coordination and command frameworks on top of Claude Code, allowing them to work together for enhanced code generation workflows.
About agent-of-empires
njbrake/agent-of-empires
Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI Coding Agent Terminal Session manager via tmux and git Worktrees
Wraps tmux to isolate each AI agent in its own persistent session, enabling parallel execution across git worktrees with optional Docker sandboxing. Provides a Rust-built TUI dashboard for session management alongside git diff viewing and per-repo configuration hooks, while maintaining background sessions that survive client disconnection.
About claude-forge
sangrokjung/claude-forge
Supercharge Claude Code with 11 AI agents, 36 commands & 15 skills — the claude-code plugin framework inspired by oh-my-zsh. 6-layer security hooks included. 5-min install.
Organizes Claude Code through a modular plugin architecture with 11 specialized agents (planner, architect, code-reviewer, security-reviewer, etc.) that operate across 40 slash commands and 15 skill workflows, plus 9 rule files defining development principles like "surgical changes" and evidence-based verification. Implements persistent agent memory (`~/.claude/agent-memory/`) to capture learnings between sessions, and provides chained workflow templates (plan → TDD → code-review → handoff-verify → PR) that enforce quality gates rather than linear CLI usage. Installs via symlinks to `~/.claude/` for seamless updates and integrates directly with Claude Code's native plugin marketplace.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work