alvinunreal/oh-my-opencode-slim

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

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 29 minutes ago
Added to GitGenius on September 1st, 2026
Created on January 15th, 2026
Open Issues & Pull Requests: 54 (+0)
GitHub issues: Enabled
Number of forks: 514
Total Stargazers: 8,687 (+0)
Total Subscribers: 33 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 15.8 hours
Mean response time: 9.6 days
90th percentile: 23.4 days
Tracked items: 466

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 88% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "bug" is answered fastest, typically in about 14 hours, while "good-to-code" waits about 3 days. Almost all tracked open issues have seen activity in the last three months. Only 12% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 40
New in 7 days: 11
Closed in 7 days: 3
Avg open age: 19 days
Stale 30+ days: 2
Stale 90+ days: 0

Recent activity

Opened in 7 days: 9
Closed in 7 days: 2
Comments in 7 days: 2
Events in 7 days: 7

Top labels

  • bug (121)
  • enhancement (89)
  • good-to-code (53)
  • wontfix (31)
  • needs-info (27)
  • status:in-review (8)
  • Share Your Thoughts (5)
  • status:approved (4)

Detailed Description

oh-my-opencode-slim is an agent orchestration plugin for OpenCode that routes coding tasks to specialized agents based on their strengths.

The tool addresses the inefficiency of forcing a single model to handle all aspects of a coding project. Instead, it distributes work across seven specialized agents: an Orchestrator that plans the work graph, an Explorer that scouts codebases, an Oracle that looks up documentation, a Council that synthesizes multiple model perspectives, a Librarian that manages information, a Designer that handles UI work, and a Fixer that executes implementation tasks. The Orchestrator dispatches these specialists as background tasks running in parallel, then reconciles their results before proceeding. This approach allows developers to mix any models across any providers and balance quality, speed, and cost by matching each subtask to the agent best equipped for it.

Adoption makes sense for teams working on substantial codebases where different phases of development benefit from different capabilities. The tool suits projects where parallel agent work can accelerate progress and where cost optimization matters. The plugin includes bundled skills like deepwork, codemap, verification-planning, and reflect that are assigned per agent. It offers a Council mode to run multiple models in parallel on the same question and synthesize results, a Companion window showing active agents, and integration with terminal multiplexers like Tmux, Zellij, and Herdr. Preset switching allows swapping the entire team's models at runtime, and code intelligence tools include LSP support, AST-aware search across 25 languages, and built-in MCPs for documentation and GitHub code search. The system is fully customizable through custom agents, prompt overrides, per-agent skill and MCP permissions, and project-local configuration.

The project maintains active development with regular updates to its documentation and feature set. The team provides multiple language translations of the README and maintains communication channels including a website, social media presence, and community Telegram channel. The codebase is written in TypeScript and includes comprehensive documentation covering background orchestration, Council functionality, multiplexer integration, preset switching, tools, and configuration options.