# alvinunreal/oh-my-opencode-slim

Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks

Repository: https://github.com/alvinunreal/oh-my-opencode-slim
Canonical: https://ross.abutalabs.com/products/oh-my-opencode-slim
Homepage: https://ohmyopencodeslim.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: agentic-ai, antigravity, cerebras, oh-my-opencode, opencode, orchestration, herdr-plugin
Last push: 2026-08-26T14:39:37+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": 230, "days_push": 7, "days_rel": 8, "gap_med": 1, "n_releases_24m": 62}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8437, forks 503 (observed 2026-08-28T04:10:21.162550+00:00)

## What it is
A lightweight agent orchestration plugin for OpenCode that delegates tasks to a team of seven specialized sub-agents (Orchestrator, Explorer, Oracle, Council, Librarian, Designer, Fixer), mixing any models across providers. It supports background task dispatch, bundled prompt-based skills, multi-model synthesis via Council, and live monitoring through Tmux/Zellij/Herdr panes or a desktop companion window.

## Use cases
- orchestrate multiple AI agents to work on my codebase
- delegate coding tasks to specialized sub-agents automatically
- mix different LLM models for different agent roles
- run multiple models in parallel and synthesize their answers
- watch AI agents work live in tmux panes
- auto-generate codebase maps and documentation with AI agents
- balance cost, speed, and quality across AI coding agents

## When to choose
- you use OpenCode and want multi-agent orchestration with model mixing
- you want an orchestrator that dispatches specialist agents as parallel background tasks
- you need multi-model consensus (Council) on hard questions
- you want live visibility into agent activity via terminal multiplexers

## When to avoid
- you don't use OpenCode as your AI coding assistant
- you want a single-model, single-agent coding assistant without orchestration overhead
- you need a standalone agent framework independent of OpenCode

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, llm-inference, developer-tools, workflow-automation, mcp
- domain: large-language-models, developer-tools
- platform: cli, cross-platform
- tags: opencode, agent-orchestration, multi-agent, model-mixing, background-tasks, tmux-integration, sub-agents, ai-agents, automation, nodejs

## Member repositories
- alvinunreal/oh-my-opencode-slim (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:21.162550+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 2026-08-29T17:27:14.783349+00:00, confidence not recorded.
  - readme: https://github.com/alvinunreal/oh-my-opencode-slim (fetched 2026-08-28T04:10:21.162550+00:00, sha 1982797280a4)
  - homepage: https://ohmyopencodeslim.com (fetched 2026-08-29T08:27:22.438676+00:00, sha 44c500288d82)
  - registry_npm: https://registry.npmjs.org/oh-my-opencode-slim (fetched 2026-08-29T08:27:22.448165+00:00, sha 838658d57f1a)
- Data as of 2026-08-30T08:39:29.467469+00:00.