Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

multica

multica• Pinned

multica: A source-available workspace where humans and AI coding agents work together as one team.

What problem it solves

AI coding agents often live in separate terminal sessions, lose context when those sessions end, and require repeated supervision. Teams need a shared workspace that connects assigned work, execution, decisions, and results while preserving human review before changes ship.

Key features

  • Agents as teammates — Create named AI agents with a provider and runtime, then assign them issues as teammates. Agents pick up assigned work, report progress, raise blockers, and return results for review.

    Source: README

  • Support for existing agent CLIs — Use installed and authenticated agent CLIs across different providers without changing the underlying tool. The runtime layer includes Claude Code, Codex, Cursor, Copilot, Kimi, OpenCode, and others.

    Source: README

  • Observable and controllable runs — Follow timestamped tool calls, commands, errors, and usage information for each run. Agents can be steered while they are working, and failed runs can retry automatically or stop with an explanation.

    Source: README

  • Self-hosted infrastructure and integrations — Run the complete stack with Docker Compose or Helm on infrastructure you control. Connect supported Git hosts, messaging channels, and multiple client surfaces through the same workspace.

    Source: README

  • Human review gates — Route agent output into review instead of directly into the main branch. Teams retain an explicit decision over what ships, with role and access controls defining which members can run agents.

    Source: README

Quick start

Copied verbatim from the project's README.

curl -fsSL https://raw.githubusercontent.com/multica-ai/multica/main/scripts/install.sh | bash -s -- --with-server
multica setup self-host
make dev

Who it may suit

This may suit software teams that already use multiple AI coding-agent CLIs and want to coordinate agent work through a shared, reviewable workspace.

Topics to discuss

  • Which agent-runtime and provider combinations should receive the most community attention?

  • How should review gates and issue permissions evolve as more agents join a team?

  • Which workflow should become the clearest starting point for new contributors?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/multica-ai/multica#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/multica-ai/multica

Comments

…