cliclaw

cliclaw is an open-source CLI agent harness and orchestrator developed by Younggi Choi. Built with TypeScript and targeted at runtimes like Bun and Node.js, the system coordinates multiple AI agents and background task execution while bridging local terminal operations with remote messaging interfaces like Telegram. In daily use, cliclaw acts as a background runner and dispatcher through its internal JobRegistry. Users can manage, trigger, and inspect agent tasks either through local CLI commands or remotely via Telegram chat endpoints. The harness tracks active sessions, monitors process health (memory RSS, heap allocation, in-flight jobs), and manages conversational state persistence. What distinguishes cliclaw from standard single-agent CLIs is its multi-agent orchestration architecture coupled with remote operational control. It incorporates safety confirmation gates to review actions before execution, instance locking to prevent duplicate processes, graceful agent failovers, and structured logging via audit.jsonl and bot.log files. cliclaw is open-source software distributed on GitHub and distributed as an npm package (@younggichoi/cliclaw) ready for deployment via Bun or Node.

Tags: agent harness, cli, coding agent, developer tools, OpenSource

Visit cliclaw

Key features

  • Multi-Agent Orchestration — Coordinates multiple underlying agent runners through a centralized JobRegistry. - Remote Telegram Interface — Inspect status, check system health, and issue commands remotely using Telegram endpoints like /health and /status. - Safety Confirmation Gates — Intercepts sensitive actions with an interactive approval gate before tasks execute. - Runtime Health & Resource Telemetry — Reports process uptime, memory consumption (RSS/heap), active chat counts, and in-flight jobs. - Structured Audit Logging — Writes execution events and errors to structured logs (audit.jsonl, bot.log, bot.err) for traceability. - Instance Locking — Employs process locking mechanisms to prevent concurrent runner conflicts on the host.

Use cases

Use Case: Remote Task Execution and Monitoring A developer running long automated coding or diagnostic agent tasks can monitor progress and issue management commands remotely via Telegram without maintaining an open SSH session.

Use Case: Gated Multi-Agent Operations A team orchestrating multi-step codebase updates can route actions through cliclaw's confirmation gates, ensuring that agent-proposed code modifications or destructive shell commands require explicit manual approval.

Use Case: Headless Agent Fleet Diagnostics A developer managing background AI workers can run /health to quickly identify memory bloat, active versus total agent availability, and job queue status across the daemon.

Who it is for

cliclaw is designed for developers, systems engineers, and DevOps practitioners who want to orchestrate, monitor, and gate multi-agent AI workflows remotely across servers. It is not suitable for users seeking a simple in-editor inline code autocompletion extension.

Install guide

Installation Install cliclaw globally using Bun or npm: bash bun add -g @younggichoi/cliclaw # or npm install -g @younggichoi/cliclaw

First Run Set up your required environment variables (e.g., Telegram bot tokens or API credentials) in your environment or local .env configuration file: bash export TELEGRAM_BOT_TOKEN="your-telegram-bot-token" export TELEGRAM_ALLOWED_USERS="your_user_id" Initialize and start the cliclaw daemon: bash cliclaw start

Example Session Check the status and health of running agents via CLI or Telegram chat: bash # Verify version cliclaw --version # In Telegram chat with the bot: /status /health

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

  • SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
  • Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
  • Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
  • Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
  • Vibe Kanban — Vibe Kanban, originally developed by Bloop AI, is an open-source orchestration harness and visual task board designed to manage and…
  • Parallel Harness Pets — Parallel Harness Pets (parallel-harness-pets) is an open-source companion tool and harness plugin created by TevvvB. It is designed for developers…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories