marketing-shibata50/multica
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills. https://multica.ai
1121 commits 1 branch 0 tags 31 MiB
Find a file
Jiayuan Zhang a0bb88e7b7 refactor(hub): enforce conversation-scoped device authorization
2026-02-17 09:39:25 +08:00
.github/workflows chore(ci): remove dependabot configuration (#189) 2026-02-15 02:57:31 +08:00
apps refactor(hub): enforce conversation-scoped device authorization 2026-02-17 09:39:25 +08:00
docs docs: clarify channel route key conversation binding 2026-02-17 09:39:25 +08:00
packages refactor(hub): enforce conversation-scoped device authorization 2026-02-17 09:39:25 +08:00
scripts test(e2e): add natural Notion gap-discovery benchmark case 2026-02-17 02:37:29 +08:00
skills feat(skills): add clawhub meta skill with security gate 2026-02-17 02:37:29 +08:00
.dockerignore Add Docker support for Gateway and SDK documentation 2026-01-28 17:56:22 +08:00
.env.example chore: add local dev script for Gateway + Desktop with Telegram bot 2026-02-14 00:39:43 +08:00
.gitignore chore: add __pycache__ to gitignore and remove committed cache 2026-02-15 01:32:24 +08:00
.npmrc refactor: restructure to monorepo architecture 2026-02-10 18:00:23 +08:00
AGENTS.md docs: add AGENTS.md for OpenAI Codex compatibility 2026-02-01 18:55:26 +08:00
CLAUDE.md docs: restore minimal project context in readme and claude 2026-02-17 01:18:51 +08:00
package.json feat(e2e): add clawhub skills benchmark suite 2026-02-17 02:37:29 +08:00
pnpm-lock.yaml revert(agent): remove parallel tool execution patch, keep serial 2026-02-15 20:43:37 +08:00
pnpm-workspace.yaml refactor: migrate from Hugeicons to Lucide icons 2026-02-12 10:12:56 +08:00
README.md docs: restore minimal project context in readme and claude 2026-02-17 01:18:51 +08:00
tsconfig.base.json refactor: restructure to monorepo architecture 2026-02-10 18:00:23 +08:00
tsconfig.json Implement WebSocket Gateway with NestJS and client SDK 2026-01-28 16:46:51 +08:00
turbo.json refactor: unify API URL env var to MULTICA_API_URL 2026-02-15 06:31:00 +08:00
vitest.config.ts test: add vitest setup with static mock policy checker 2026-02-13 22:03:36 +08:00
vitest.setup.ts test: add vitest setup with static mock policy checker 2026-02-13 22:03:36 +08:00

README.md

Super Multica

Super Multica is a distributed AI agent framework and product monorepo. It provides a local-first agent runtime plus CLI, gateway, web, and mobile integration surfaces.

What this project does:

  • runs AI agent sessions with tools, skills, and persistent session state
  • supports scheduled/automated execution workflows
  • supports both standalone local usage and remote-access client workflows

This repository keeps docs focused on:

  1. Development workflow
  2. Testing workflow
  3. Operational process

Architecture details are still source-of-truth in code, but docs keep minimal project context for onboarding.

Quick Start (Workflow)

pnpm install
pnpm multica credentials init
pnpm multica

Run local desktop workflow:

pnpm dev

Local Full-Stack Development (pnpm dev:local)

Use this when you need Gateway + Web + Desktop together for end-to-end dev.

Setup:

  1. Copy .env.example to .env in repo root
  2. Set TELEGRAM_BOT_TOKEN in .env (from @BotFather)
  3. Run:
pnpm dev:local

What starts:

Service Address Notes
Gateway http://localhost:4000 Telegram long-polling mode
Web http://localhost:3000 OAuth login flow
Desktop — Connects to local Gateway + Web

Data isolation:

  • runtime data: ~/.super-multica-dev
  • workspace data: ~/Documents/Multica-dev

Related:

pnpm dev:local:archive

Workflow Commands

# CLI
pnpm multica
pnpm multica run "Hello"
pnpm multica chat
pnpm multica help

# Development
pnpm dev
pnpm dev:desktop
pnpm dev:gateway
pnpm dev:web
pnpm dev:local
pnpm dev:local:archive

# Build / quality
pnpm build
pnpm typecheck
pnpm test

Testing Workflow

# Unit/integration
pnpm test
pnpm test:watch
pnpm test:coverage

# Type safety gate
pnpm typecheck

# Agent E2E
pnpm multica run --run-log "your test prompt"

E2E process docs:

  • docs/e2e-testing-guide.md
  • docs/e2e-finance-benchmark.md

Runtime Paths

By default, runtime data is stored under:

  • ~/.super-multica

You can isolate environments with:

  • SMC_DATA_DIR=~/.super-multica-dev (or other path)

Process Docs

  • CLAUDE.md
  • docs/development.md
  • docs/cli.md
  • docs/credentials.md
  • docs/skills-and-tools.md
  • docs/package-management.md
  • docs/e2e-testing-guide.md
  • docs/e2e-finance-benchmark.md