Open‑Source Multica Lets You Self‑Deploy Claude‑Style Agent Teams Ahead of Anthropic’s Official Release
Multica, an open‑source clone of Anthropic’s Claude Managed Agents, offers a self‑hosted agent lifecycle platform with task boards, reusable skills, unified runtime management, and multi‑workspace isolation, contrasting the official hosted service’s pricing and data‑control model, and is suited for teams needing vendor‑neutral, on‑premise agent orchestration.
Timeline and Positioning
Multica’s GitHub repository was created on 2026‑01‑13, roughly three months before Anthropic announced Claude Managed Agents. The project was later described on Twitter as “the open‑source version of Claude Managed Agents,” aligning its branding with the announcement.
Core Functionality
Task board : Issues can be assigned to agents; agents claim, execute, and update progress in real time, similar to a Jira‑style board.
Reusable Skills : After an agent resolves a problem, the solution is distilled into a skill that any agent can invoke, covering tasks such as deployment workflows, database migrations, and code reviews.
Unified Runtime Management : Both local and cloud machines can be registered; Multica automatically detects available Agent CLIs and schedules them.
Multi‑workspace isolation : Separate workspaces keep agents, issues, and configurations independent across teams.
Multica supports two agent runtimes—Claude Code and Codex—making it a vendor‑neutral orchestration layer.
Architecture
Frontend (Next.js 16) → Backend (Go + WebSocket) → Database (PostgreSQL 17 + pgvector)
↓
Agent Daemon (local)
Executes Claude Code / CodexThe backend is written in Go for performance; WebSocket streams real‑time agent progress; pgvector suggests vector‑based skill retrieval and matching.
Deployment
Local deployment is containerized. Running docker compose up -d and setting a few environment variables starts the system.
Comparison with Anthropic’s Managed Service
Anthropic’s service is fully hosted, stores data on Anthropic’s servers, and charges based on usage.
Multica stores all data on the user’s own machines; costs are limited to the underlying model API calls.
This distinction matters for teams with data‑compliance requirements or those needing full control over agent infrastructure.
Use Cases and Limitations
Suitable for teams already using Claude Code (or Codex) that want a unified, self‑hosted management interface without exposing data to third‑party servers.
Less suitable for teams unwilling or unable to maintain additional infrastructure; the official cloud‑hosted version may be more convenient.
Repository: github.com/multica-ai/multica
Signed-in readers can open the original source through BestHub's protected redirect.
This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactand we will review it promptly.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.