Skillget

cryochamber

agent
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 11 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose

This agent acts as a persistent scheduling daemon for AI coding tools (like Claude Code or OpenCode). It wakes hibernating AI agents at optimal times to execute long-running, irregular tasks, allowing them to manage projects spanning days or weeks without manual supervision.

Security Assessment

Overall Risk: Medium. The tool is explicitly designed to execute shell commands by waking up AI agents and instructing them to complete tasks. Because it manages these automated sessions via a background daemon, any instructions fed into the system will be executed by the connected AI. The light code scan found no dangerous patterns, malware, or hardcoded secrets in the core repository. However, giving an automated daemon permission to routinely trigger an AI agent to act on your behalf inherently requires high trust in the plans and scripts being fed to it.

Quality Assessment

The project is actively maintained, with its most recent push occurring today. It has garnered 11 GitHub stars, indicating early but growing community interest. The automated rule scan flagged a warning for missing license file, which restricts formal permissions for use, modification, and distribution. Interestingly, the README directly contradicts this by featuring an MIT license badge, suggesting the license file might have been accidentally excluded or misconfigured in the repository. Documentation appears highly professional, featuring a detailed book, CI workflows, and clear onboarding instructions.

Verdict

Use with caution: the clean codebase and active maintenance are positive signs, but developers should verify the actual licensing status and fully understand the security implications of running an automated agent scheduler.
SUMMARY

Cryochamber for your AI agents, for scheduling long running tasks

README.md

Crates.io
CI
Docs
License: MIT

cryochamber logo

Cryochamber is a hibernation chamber for AI agents (Claude, OpenCode, Codex). It hibernates an AI agent between sessions and wakes it at the right time — not on a fixed schedule. The agent checks the plan and log, completes a task, and decides when to wake next. Cryochamber empowers AI agents to run tasks that span days, weeks, or even years, like interstellar travelers in stasis.

Our goal is to automate long-running activities that are too irregular for cron. A conference deadline slips because submissions are low. A space probe's next burn window depends on orbital mechanics. A code review depends on when the author pushes fixes. Cryochamber lets an AI agent reason about when to wake and what to do next, with a persistent daemon that manages the lifecycle.

Quick Start

Prerequisites: Rust toolchain (rustup.rs), an AI coding agent (OpenCode, Claude Code, or Codex), macOS or Linux.

1. Install cryochamber

cargo install cryochamber

This installs cryo, cryo-agent, cryo-gh, and cryo-zulip binaries.

Copy-Paste Onboarding Prompt

If you want your coding agent to set up a new Cryochamber project for you, paste this:

Set up a new Cryochamber project for me in this directory.

1. If `cryo` is not installed, install it with `cargo install cryochamber`.
2. If the `make-plan` skill is not installed and your coding agent supports custom skills, install it from the Cryochamber repo: clone https://github.com/GiggleLiu/cryochamber somewhere local, then use your agent's skill installation mechanism to install `/path/to/cryochamber/skills/make-plan`.
3. Invoke the `make-plan` skill to create the Cryochamber project and generate the initial plan/config files.
4. Start the daemon with `cryo start`.
5. Tell me which files were created or updated, and whether the service started successfully.

2. Write your plan and configure

Edit plan.md with your task — describe the goal, step-by-step tasks, and notes about persistent state. Edit cryo.toml to configure the agent command, retry policy, and inbox settings. See examples/ for reference (chess-by-mail, mr-lazy).

Recommended: If your AI coding agent supports custom skills, install make-plan from the Cryochamber repo:

Add the make-plan skill from https://github.com/GiggleLiu/cryochamber

Then invoke the make-plan skill to create a new project interactively via guided Q&A.

3. Start the service

cryo start                                                    # start the daemon

Depending on the way you interact with your agent, start the corresponding service wtih:

cryo-zulip init --config ./zuliprc --stream "my-stream"       # if using Zulip
cryo-zulip sync
cryo-gh init --repo owner/repo                                # if using GitHub Discussions
cryo-gh sync
cryo web                                                      # if using the web UI

4. Manage the running service

Go to the project folder and type:

cryo status          # check if the daemon is running
cryo watch           # follow the live log
cryo send "message"  # send a message to the agent
cryo cancel          # stop the daemon

Messaging Channels

Cryochamber supports external messaging channels that sync between a remote service and the local inbox/outbox directories. The cryo daemon and agent remain unaware of the channel — all sync is handled by a dedicated binary. These are configured automatically when using /make-plan.

Channel Binary Backend Docs
Web UI cryo web Built-in HTTP server Web UI
GitHub Discussions cryo-gh GitHub GraphQL API GitHub Sync
Zulip cryo-zulip Zulip REST API Zulip Sync

License

MIT

Reviews (0)

No results found