multica
Multica turns the pile of agent terminals most developers end up with into one workspace. Instead of running Claude Code in one tab and Codex in another, re-explaining the same context each session, you file an issue, set an agent as the assignee, and let it work on a machine you control. The agent comments as it goes, raises blockers, and moves the issue to review when it is done, so the intent, the run and the diff stay attached to one record.
It is deliberately not a model or an agent of its own. Multica drives the agent command-line tools you already have installed and signed in, and the README lists 26 of them, including Claude Code, Codex, Cursor Agent and GitHub Copilot CLI. Switching provider is a dropdown rather than a migration. Work runs through a daemon on your laptop or a cloud box, which keeps code on your own hardware, and the whole stack can be self-hosted with Docker Compose or Helm.
The oversight features are what separate it from a simple task runner: an execution log that replays every tool call and error, per-run cost analytics, review gates so work lands in review rather than main, retries and timeouts, and roles with access scopes. It suits small teams that already run several coding agents in parallel and want one place to review what they did. Note that the license is listed as source-available rather than a standard open-source license, so check it before building a business on top.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-10-19
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 30
- Latest release
- v0.6.3 (2026-10-16)
- Open issues
- 1878
- Recent issues with at least one comment
- 3/6
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #1943 [Feature]: Workflow Orchestration18 comments · 2026-04-30
- #1014 [Feature]: Add OIDC login support15 comments · 2026-04-14
- #1211 Discussion: should team knowledge compound across agent runs the way skills do?14 comments · 2026-04-16
- #3262 [Bug]: Codex app-server stays at status=running with no output; Hermes works12 comments · 2026-05-26
- #2456 Migrate workspace data from Multica Cloud to self-hosted instance11 comments · 2026-05-12
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
Who it fits
- You want to treat existing coding agents (Claude Code, Codex, Cursor) as team members, assigning issues and receiving progress updates.
- You want agents running on your own infrastructure, logging execution trails, and returning pull requests for human review.
- You only need single-developer local IDE chat and code completions without an issue ticketing workspace.
- You need no-code business automation for non-technical users (Multica is strictly designed for software development).
How it differs
vs PilotDeck★ 4.9kMultica organizes work around issue trackers and review workflows; PilotDeck provides an all-in-one agent workspace OS with memory routing.
vs Activepieces★ 25.2kMultica manages autonomous coding and pull-request creation; Activepieces handles SaaS integration and enterprise business process workflows.
Compatibility
Quick start
Use cases
Alternatives
Featured in these lists
Comments
No comments yet. Be the first!