# multica-ai/multica

Make humans and AI agents work as one team — open-source and self-hostable.

Repository: https://github.com/multica-ai/multica
Canonical: https://ross.abutalabs.com/products/multica
Homepage: https://multica.ai
Language: Go
License: NOASSERTION
License Family: other
Last push: 2026-08-26T13:21:51+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 16
- inputs: {"age_days": 232, "days_push": 7, "days_rel": 7, "gap_med": 0.0, "n_releases_24m": 147}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 47845, forks 6139 (observed 2026-08-28T04:12:11.329385+00:00)

## What it is
Multica is an open-source, self-hostable workspace for managing AI coding agents as first-class teammates alongside humans. Agents get assigned issues, work autonomously on controlled runtimes, report progress, and hand results back for review, with support for 23 agent CLIs like Claude Code, Codex, and Cursor.

## Use cases
- assign coding tasks to AI agents like teammates
- orchestrate multiple AI coding agents in one workspace
- self-host an AI agent project management platform
- track agent progress and blockers on a shared board
- run scheduled autonomous agent tasks
- share reusable skills across AI agents
- coordinate humans and AI agents in one team

## When to choose
- you run several AI coding agents and lose context across terminal sessions
- you want agents to pick up issues, comment, and deliver PRs autonomously
- you need self-hosting and full control over your data and LLM providers
- you want one activity feed combining human and agent work

## When to avoid
- you only need a single agent in a terminal without team workflow
- you want a lightweight issue tracker without agent orchestration
- you cannot run agent runtimes on infrastructure you control

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, workflow-automation, scheduling, chatbot, mcp, developer-tools, self-hosted
- domain: large-language-models, developer-tools, self-hosted, cross-platform
- platform: self-hosted, cross-platform, go, cli
- tags: ai-agent-orchestration, project-management, human-agent-teams, coding-agents, issue-tracking, agent-runtimes, squads, skills, slack-integration, telegram-bot, ai-agents, automation, docker, web-server, desktop, mobile

## Member repositories
- multica-ai/multica (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:11.329385+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:20:46.431713+00:00, confidence not recorded.
  - readme: https://github.com/multica-ai/multica (fetched 2026-08-28T04:12:11.329385+00:00, sha 85b6835aced4)
  - homepage: https://multica.ai (fetched 2026-08-29T07:42:17.578962+00:00, sha ac109759f391)
  - site_page: https://multica.ai/docs (fetched 2026-08-29T07:42:17.588816+00:00, sha 2c2c4dc0a696)
  - site_page: https://multica.ai/about (fetched 2026-08-29T07:42:17.598067+00:00, sha bc639685dbf3)
  - site_page: https://multica.ai/changelog (fetched 2026-08-29T07:42:17.591252+00:00, sha 91267b1afb94)
- Data as of 2026-08-30T08:39:29.467469+00:00.