Pi Messenger connects Pi coding agent sessions working in separate terminals on the same project. It's for developers who want agents to share progress and divide work without editing over one another. Coordination runs through local files, with no separate server or background service.
Agents can send direct messages or broadcasts that prompt recipients to respond. File reservations block other agents from writing to claimed files or directories and clear when the owner leaves or exits. A terminal overlay lets you join the conversation and see each agent's model, Git branch, and current activity. The shared feed records edits, commits, test runs, and task events; stuck detection alerts peers when an agent stays idle with unfinished work.
Crew handles larger assignments. It reads a product requirements document or a plain-language request, examines the codebase, and splits work into tasks with dependencies. Workers tackle independent tasks in parallel, and reviewers check completed work. Autonomous execution continues until tasks finish or hit a blocker. Workers can draw on project-specific skills for domain knowledge.
The optional Team layer adds roles, reusable profiles, persistent project memory, and approval gates for risky tasks. Crew logs and activity records stay in the project folder, while shared messaging state lives locally. Model execution is separate: agents inherit the Pi session's model or use role-specific choices, including Anthropic Claude models through cloud providers.
Claim this page and we'll verify you by hand. Pi Messenger gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Pi Messenger?Promote it
Something wrong or outdated on this page?
403Updated 11 hours agoApache-2.0
macOS · Windows · Linux#Agent Skills#Code execution#Git integration
Liza coordinates coding agents through a software delivery workflow with separate authors and reviewers. It's for developers who want to delegate work from specifications through tested, documented code while retaining control over product decisions. Its Go supervisor enforces role boundaries, validation gates and merge authority in code, rather than relying entirely on agents to follow prompts.
106Updated 2 weeks ago
macOS · Windows · Linux · Web#Agent Skills#Code execution#Git integration
Albert coordinates Claude Code agents for developers who want to hand off a coding goal across several tasks. Its harness and dashboard run locally on Windows, macOS or Linux, and it requires an installed, signed-in Claude Code account. It assigns work to Haiku, Sonnet or Opus according to the task and continues until the goal is complete or it reaches a requested review checkpoint.
29Updated 5 months ago
#Git integration#Human approval#Multi-agent workflows
Claudio runs on your machine and coordinates multiple Claude Code sessions working on the same repository. It's for developers who want to split coding work across parallel agents while keeping each agent's edits on a separate branch. It requires an authenticated Claude Code CLI, Git and tmux.
587Updated 21 hours agoMIT
Web · VS Code · JetBrains#Agent Client Protocol#Code execution#Git integration
127.4KUpdated 16 hours agoApache-2.0
macOS · Windows · Linux#Code execution#Git integration#Human approval
371Updated 5 months ago
Docker#Agent Skills#Code execution#Git integration
cook coordinates Claude Code, Codex, and OpenCode so developers can give coding tasks repeated reviews or compare competing implementations. It runs as a CLI in a local terminal or CI environment, with a Claude Code skill also available. It requires Node.js and one of the supported coding agents.
Claw Orchestrator is a self-hosted runtime for developers who want to coordinate coding agents on their own machine or server. It brings Claude Code, Codex, Antigravity, Grok Build and OpenCode into one interface, with support for custom coding CLIs. The runtime and browser dashboard run locally.
Codex CLI is an open source coding assistant that runs on your computer and works with local repositories. It's for developers who want to explore code, make changes, and use their existing development tools from the terminal. It runs on macOS, Windows, and Linux under the Apache 2.0 license.