Skip to main content
What it contains
Self-hostable workspace where many coding-agent CLIs act as teammates: issues, squads, runtimes, skills, autopilots, logs, costs, and review gates.
Typical uses
Coordinate Claude Code, Codex, Cursor, Copilot and other agents with humans through an issue board and controlled execution runtimes.
Why people choose it
Inference: solves multi-agent/team coordination rather than one agent's prompting.
LicenseCustom Apache-2.0-derived license with additional conditions
Last meaningful updateUnknown
Production readinessproduction
Classification
Subject domains
coding agentsteam collaborationorchestration
Task categories
coding agentsteam collaborationorchestration
Project phases
planningimplementationtestingreview
Secondary types
monorepoagent orchestration platform
Select when
- Need a shared work board for many coding agents/humans
Do not select when
- Only one lightweight local agent
- Do not want server/database/daemon stack
Implementation complexityhigh
Routing heuristic 84.0%
Security boundary clarity
5/5 First-party routing documentation
5/5 Strengths
None documented.
Poor-fit scenarios
- Only one lightweight local agent
- Do not want server/database/daemon stack
Limitations
None documented.
README.md
Issues/agents/projects/review/audit UI.
work board
README.md
API/task orchestration/persistence.
backend
README.md
Spawn supported agent CLIs on controlled machines.
runtimes
README.md
Reusable solved-problem playbooks.
knowledge
README.md
Scheduled standups/audits/reports.
automation
README.md
Organize people/agents with routing leader.
team routing
FrameworksNext.js 16, Electron, Expo, PostgreSQL 17/pgvector
RuntimesNode.js 20+, Go 1.26+, Docker
Operating systemsNone documented
Installation methodsNone documented
Interfacesweb, desktop, mobile, CLI, API
Required credentialsNone documented
External servicesNone documented
Major dependenciesNone documented
Compatibility notes
None documented.
One-sentence semantic summary
Self-hostable workspace where many coding-agent CLIs act as teammates: issues, squads, runtimes, skills, autopilots, logs, costs, and review gates.
Capability keywords
issue assignment20 agent CLIsruntimessquadsskillsautopilotsreview gatesaudit logs
User intent phrases
- Need a shared work board for many coding agents/humans
Negative match phrases
- Only one lightweight local agent
- Do not want server/database/daemon stack
Differentiators
None documented.
Security considerations
- Review license/security model and daemon credentials.
Privacy considerations
None documented.
Uncertainty
Unresolved items
None documented.
Inference notes
None documented.
Repository usage guidance
installation summaryUnknown
basic usage summaryCoordinate Claude Code, Codex, Cursor, Copilot and other agents with humans through an issue board and controlled execution runtimes.
documented entry pointsNone documented
key configuration filesNone documented
important directoriesNone documented
documentation pathsREADME.md
example pathsNone documented
Relationships
alternative
high
SWE-AF is autonomous engineering factory; Multica is human+agent workboard/orchestration.
Recommended combinations
Agent-team orchestration high
Each repository covers a distinct layer; avoid combining tools that duplicate lifecycle ownership.
Order of operations
- Connect least-privilege agent runtimes
- Add RTK on runtime machines
- Install only role-relevant engineering skills
- Keep human review gates
Routing rules
rule_043: Need a shared work board for many coding agents/humans P957
Rationale
Self-hostable workspace where many coding-agent CLIs act as teammates: issues, squads, runtimes, skills, autopilots, logs, costs, and review gates.
Required conditions
None documented.
Preferred
multica-ai/multica
Fallback
None