DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to keep one project context across coding agents with Acryl

Move between Claude Code, Codex, and Gemini CLI on the same project without re-setting context.

  • Top pick
  • Software and DevOps
  • Intermediate
  • 30 minutes
  • From the README
  • Claude Code
  • Codex
  • Gemini CLI

Who it is forA developer who uses several coding agents for different tasks and loses the thread of the work every time they switch agents.

The problemEach agent keeps its own chat, so switching agents means rebuilding setup, context, and task history from scratch.

The outcomeOne ACRYL workspace holds the project, its tasks, and its handoffs, and each agent enters and leaves that same workspace.

What you need first

  • macOS, Windows, or Linux machine
  • Installed coding agent such as Claude Code, Codex, or Gemini CLI, if you want to launch it from ACRYL
  • Node.js ^22.19.0 or >=24.0.0 and Corepack, only for running from source

Steps

  1. Run curl -fsSL https://acryl.dev/install | bash to install the CLI and add acryl to your PATH.
  2. Run acryl to open the terminal surface.
  3. Add your project as a project in the left panel, then open a git worktree for the task if needed.
  4. Launch an agent such as Claude Code, Codex, or Gemini CLI from the built-in catalog into that project.
  5. When you want a different agent, launch another one from the same roster in the same project and keep working in the same canvas.

Prompt for your agent

Using the acryl repo at github.com/acryldev/acryl, set up ACRYL on this machine and open the project at <project-path> as a project. Report the project name shown in ACRYL and list which agents from the roster are available; verify the project appears in the left panel before you finish.

Caveat. The README says ACRYL is in active early development and interfaces may change, so check the current release before relying on a workflow.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page