tmux-agentsManage background coding agents in tmux sessions. Spawn Claude Code or other agents, check progress, get results.
Install via ClawdBot CLI:
clawdbot install cuba6112/tmux-agentsRun coding agents in persistent tmux sessions. They work in the background while you do other things.
| Agent | Command | Best For |
|-------|---------|----------|
| claude | Claude Code | Complex coding, refactoring, full projects |
| codex | OpenAI Codex | Quick edits, auto-approve mode |
| gemini | Google Gemini | Research, analysis, documentation |
| Agent | Command | Best For |
|-------|---------|----------|
| ollama-claude | Claude Code + Ollama | Long experiments, heavy refactoring |
| ollama-codex | Codex + Ollama | Extended coding sessions |
Local agents use your Mac's GPU — no API costs, great for experimentation!
./skills/tmux-agents/scripts/spawn.sh <name> <task> [agent]
# Cloud (uses API credits)
./skills/tmux-agents/scripts/spawn.sh fix-bug "Fix login validation" claude
./skills/tmux-agents/scripts/spawn.sh refactor "Refactor the auth module" codex
./skills/tmux-agents/scripts/spawn.sh research "Research caching strategies" gemini
# Local (FREE - uses Ollama)
./skills/tmux-agents/scripts/spawn.sh experiment "Rewrite entire test suite" ollama-claude
./skills/tmux-agents/scripts/spawn.sh big-refactor "Refactor all services" ollama-codextmux list-sessions
# or
./skills/tmux-agents/scripts/status.sh./skills/tmux-agents/scripts/check.sh session-nametmux attach -t session-name
# Detach with: Ctrl+B, then Dtmux send-keys -t session-name "additional instruction here" Entertmux kill-session -t session-name| Scenario | Recommendation |
|----------|----------------|
| Quick fix, time-sensitive | ☁️ Cloud (faster) |
| Expensive task, budget matters | 🦙 Local |
| Long experiment, might fail | 🦙 Local |
| Production code review | ☁️ Cloud (smarter) |
| Learning/exploring | 🦙 Local |
| Heavy refactoring | 🦙 Local |
Run multiple agents simultaneously:
# Mix and match cloud + local
./scripts/spawn.sh backend "Implement user API" claude # Cloud
./scripts/spawn.sh frontend "Build login form" ollama-codex # Local
./scripts/spawn.sh docs "Write API documentation" gemini # Cloud
./scripts/spawn.sh tests "Write all unit tests" ollama-claude # LocalCheck all at once:
./skills/tmux-agents/scripts/status.shLocal agents require Ollama with a coding model:
# Pull recommended model
ollama pull glm-4.7-flash
# Configure tools (one-time)
ollama launch claude --model glm-4.7-flash --config
ollama launch codex --model glm-4.7-flash --configtmux ls to see all active workGenerated Mar 1, 2026
Agencies can run multiple agents in parallel to handle different client projects simultaneously, such as backend development with a cloud agent and frontend work with a local agent. This maximizes productivity by allowing developers to oversee progress while agents handle coding tasks in the background, reducing manual effort and speeding up delivery.
Researchers can use local agents via Ollama for free to experiment with code for data analysis, simulations, or algorithm development without incurring API costs. This is ideal for long-running experiments where failures are acceptable, enabling iterative testing and refinement of research code in persistent tmux sessions.
Startups can leverage cloud agents for time-sensitive tasks like bug fixes or production code reviews, while using local agents for cost-effective refactoring and feature experimentation. This hybrid approach balances speed and budget, allowing small teams to scale development efforts without extensive hiring.
Freelancers can manage multiple client projects by spawning agents for tasks like documentation with Gemini or coding with Claude, checking progress via status scripts. This enables handling parallel workloads efficiently, with sessions persisting even during breaks, ensuring continuous progress on deliverables.
Offer basic local agent functionality for free via Ollama, with premium tiers for cloud agents that use API credits for faster, smarter tasks. Revenue comes from subscription fees for access to advanced agents, priority support, and higher usage limits, targeting cost-conscious developers and teams.
Sell licenses to large organizations for integrating tmux agents into their development workflows, with features like custom agent configurations, security compliance, and dedicated support. Revenue is generated through annual contracts based on the number of users or sessions, focusing on scalability and reliability.
Operate a platform where users purchase API credits to use cloud agents like Claude or Codex, with a markup on top of provider costs. Additional revenue streams include commissions from Ollama model downloads or partnerships with AI service providers, appealing to developers seeking flexible payment options.
💬 Integration Tip
Ensure tmux is installed and Ollama is set up for local agents; start by testing with simple tasks to familiarize with session management commands like spawn.sh and status.sh.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.