alvinunreal/oh-my-opencode-slimPublic

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

AI summary: A streamlined, fine-tuned multi-agent orchestration suite for Opencode that allows mixing various LLMs.

Stars
10.3K
+56 today
Forks
620
Watchers
35
Open issues
30
Open PRs
6
Contributors
~175
Commits
4.1K
Branches
75

TypeScriptMITCreated Jan 15, 2026Last push 3d agoLatest release v3.0.7+91 stars this week+633 this month

Quick answers

What is oh-my-opencode-slim?
A streamlined, fine-tuned multi-agent orchestration suite for Opencode that allows mixing various LLMs.
What does oh-my-opencode-slim do?
Oh-my-opencode-slim is a lean, highly optimized multi-agent suite built upon the Opencode framework. It is designed to orchestrate complex coding and development tasks by leveraging a team of specialized AI agents. The suite allows developers to mix and match different large language models seamlessly, utilizing the strengths of specific models for specific tasks. It features an auto-delegation system that intelligently breaks down complex user prompts and assigns sub-tasks to the most appropriate agent in the suite. By abstracting the orchestration layer, it enables developers to build highly capable, autonomous development pipelines with minimal overhead.
Who is oh-my-opencode-slim for?
AI engineers and developers looking to build or experiment with advanced multi-agent systems for software development. It is geared towards users who want granular control over model selection and task routing in their autonomous workflows.
How popular is oh-my-opencode-slim on GitHub?
alvinunreal/oh-my-opencode-slim has 10,275 stars and 620 forks on GitHub, and gained 91 stars in the last 7 days.
What license does oh-my-opencode-slim use?
alvinunreal/oh-my-opencode-slim is released under the MIT license.

Star history

since Jul 28, 2026
05K10KJul 2026Sep 2026Oct 2026Nov 2026
10.3K stars as of Nov 18, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

4 recorded
  • Nov 7, 2026New release v3.0.7 (previously v3.0.6).
  • Oct 27, 2026New release v3.0.6 (previously v3.0.5).
  • Oct 19, 2026New release v3.0.5 (previously v3.0.4).
  • Oct 10, 2026New release v3.0.4 (previously v3.0.0).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-16: 0 commits2025-11-17: 0 commits2025-11-18: 0 commits2025-11-19: 0 commits2025-11-20: 0 commits2025-11-21: 0 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 12 commits2026-01-16: 8 commits2026-01-17: 9 commits2026-01-18: 10 commits2026-01-19: 4 commits2026-01-20: 18 commits2026-01-21: 11 commits2026-01-22: 10 commits2026-01-23: 1 commit2026-01-24: 16 commits2026-01-25: 8 commits2026-01-26: 5 commits2026-01-27: 0 commits2026-01-28: 5 commits2026-01-29: 0 commits2026-01-30: 3 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 1 commit2026-02-04: 0 commits2026-02-05: 1 commit2026-02-06: 0 commits2026-02-07: 3 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 1 commit2026-02-11: 2 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 2 commits2026-02-15: 1 commit2026-02-16: 1 commit2026-02-17: 1 commit2026-02-18: 1 commit2026-02-19: 0 commits2026-02-20: 1 commit2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 1 commit2026-02-24: 0 commits2026-02-25: 1 commit2026-02-26: 2 commits2026-02-27: 1 commit2026-02-28: 1 commit2026-03-01: 1 commit2026-03-02: 1 commit2026-03-03: 0 commits2026-03-04: 1 commit2026-03-05: 1 commit2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 1 commit2026-03-12: 1 commit2026-03-13: 0 commits2026-03-14: 5 commits2026-03-15: 3 commits2026-03-16: 1 commit2026-03-17: 0 commits2026-03-18: 1 commit2026-03-19: 1 commit2026-03-20: 1 commit2026-03-21: 1 commit2026-03-22: 1 commit2026-03-23: 2 commits2026-03-24: 4 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 12 commits2026-03-30: 4 commits2026-03-31: 2 commits2026-04-01: 11 commits2026-04-02: 3 commits2026-04-03: 0 commits2026-04-04: 1 commit2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 0 commits2026-04-08: 12 commits2026-04-09: 1 commit2026-04-10: 3 commits2026-04-11: 11 commits2026-04-12: 8 commits2026-04-13: 9 commits2026-04-14: 6 commits2026-04-15: 0 commits2026-04-16: 11 commits2026-04-17: 12 commits2026-04-18: 12 commits2026-04-19: 8 commits2026-04-20: 10 commits2026-04-21: 18 commits2026-04-22: 12 commits2026-04-23: 21 commits2026-04-24: 10 commits2026-04-25: 3 commits2026-04-26: 0 commits2026-04-27: 14 commits2026-04-28: 6 commits2026-04-29: 8 commits2026-04-30: 4 commits2026-05-01: 0 commits2026-05-02: 3 commits2026-05-03: 16 commits2026-05-04: 9 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 6 commits2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 2 commits2026-05-12: 15 commits2026-05-13: 0 commits2026-05-14: 9 commits2026-05-15: 14 commits2026-05-16: 22 commits2026-05-17: 8 commits2026-05-18: 0 commits2026-05-19: 3 commits2026-05-20: 2 commits2026-05-21: 1 commit2026-05-22: 3 commits2026-05-23: 24 commits2026-05-24: 4 commits2026-05-25: 3 commits2026-05-26: 2 commits2026-05-27: 0 commits2026-05-28: 1 commit2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 5 commits2026-06-05: 5 commits2026-06-06: 4 commits2026-06-07: 0 commits2026-06-08: 13 commits2026-06-09: 2 commits2026-06-10: 0 commits2026-06-11: 3 commits2026-06-12: 15 commits2026-06-13: 12 commits2026-06-14: 13 commits2026-06-15: 27 commits2026-06-16: 11 commits2026-06-17: 6 commits2026-06-18: 8 commits2026-06-19: 4 commits2026-06-20: 8 commits2026-06-21: 16 commits2026-06-22: 6 commits2026-06-23: 1 commit2026-06-24: 8 commits2026-06-25: 5 commits2026-06-26: 1 commit2026-06-27: 15 commits2026-06-28: 14 commits2026-06-29: 8 commits2026-06-30: 2 commits2026-07-01: 4 commits2026-07-02: 18 commits2026-07-03: 31 commits2026-07-04: 16 commits2026-07-05: 12 commits2026-07-06: 33 commits2026-07-07: 16 commits2026-07-08: 27 commits2026-07-09: 13 commits2026-07-10: 34 commits2026-07-11: 24 commits2026-07-12: 20 commits2026-07-13: 6 commits2026-07-14: 8 commits2026-07-15: 12 commits2026-07-16: 33 commits2026-07-17: 16 commits2026-07-18: 39 commits2026-07-19: 17 commits2026-07-20: 9 commits2026-07-21: 22 commits2026-07-22: 35 commits2026-07-23: 12 commits2026-07-24: 7 commits2026-07-25: 0 commits2026-07-26: 0 commits2026-07-27: 0 commits2026-07-28: 3 commits2026-07-29: 0 commits2026-07-30: 8 commits2026-07-31: 1 commit2026-08-01: 7 commits2026-08-02: 2 commits2026-08-03: 19 commits2026-08-04: 6 commits2026-08-05: 4 commits2026-08-06: 16 commits2026-08-07: 4 commits2026-08-08: 34 commits2026-08-09: 6 commits2026-08-10: 23 commits2026-08-11: 11 commits2026-08-12: 1 commit2026-08-13: 11 commits2026-08-14: 2 commits2026-08-15: 2 commits2026-08-16: 12 commits2026-08-17: 7 commits2026-08-18: 4 commits2026-08-19: 2 commits2026-08-20: 3 commits2026-08-21: 5 commits2026-08-22: 6 commits2026-08-23: 18 commits2026-08-24: 5 commits2026-08-25: 6 commits2026-08-26: 17 commits2026-08-27: 0 commits2026-08-28: 21 commits2026-08-29: 14 commits2026-08-30: 4 commits2026-08-31: 4 commits2026-09-01: 7 commits2026-09-02: 7 commits2026-09-03: 1 commit2026-09-04: 3 commits2026-09-05: 0 commits2026-09-06: 3 commits2026-09-07: 3 commits2026-09-08: 0 commits2026-09-09: 8 commits2026-09-10: 6 commits2026-09-11: 2 commits2026-09-12: 25 commits2026-09-13: 13 commits2026-09-14: 25 commits2026-09-15: 16 commits2026-09-16: 12 commits2026-09-17: 21 commits2026-09-18: 29 commits2026-09-19: 39 commits2026-09-20: 18 commits2026-09-21: 29 commits2026-09-22: 13 commits2026-09-23: 14 commits2026-09-24: 45 commits2026-09-25: 40 commits2026-09-26: 59 commits2026-09-27: 29 commits2026-09-28: 4 commits2026-09-29: 34 commits2026-09-30: 28 commits2026-10-01: 31 commits2026-10-02: 16 commits2026-10-03: 24 commits2026-10-04: 103 commits2026-10-05: 16 commits2026-10-06: 9 commits2026-10-07: 9 commits2026-10-08: 32 commits2026-10-09: 6 commits2026-10-10: 6 commits2026-10-11: 28 commits2026-10-12: 89 commits2026-10-13: 64 commits2026-10-14: 13 commits2026-10-15: 25 commits2026-10-16: 11 commits2026-10-17: 14 commits2026-10-18: 5 commits2026-10-19: 12 commits2026-10-20: 13 commits2026-10-21: 38 commits2026-10-22: 44 commits2026-10-23: 16 commits2026-10-24: 24 commits2026-10-25: 33 commits2026-10-26: 25 commits2026-10-27: 8 commits2026-10-28: 26 commits2026-10-29: 22 commits2026-10-30: 46 commits2026-10-31: 89 commits2026-11-01: 52 commits2026-11-02: 23 commits2026-11-03: 25 commits2026-11-04: 26 commits2026-11-05: 8 commits2026-11-06: 2 commits2026-11-07: 19 commits2026-11-08: 9 commits2026-11-09: 25 commits2026-11-10: 26 commits2026-11-11: 3 commits2026-11-12: 7 commits2026-11-13: 2 commits2026-11-14: 15 commits
3,182 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    10,275 stars

  • Very active

    3,182 commits in 52 weeks

  • Community-driven

    ~175 contributors

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

What oh-my-opencode-slim does

Oh-my-opencode-slim is a lean, highly optimized multi-agent suite built upon the Opencode framework. It is designed to orchestrate complex coding and development tasks by leveraging a team of specialized AI agents. The suite allows developers to mix and match different large language models seamlessly, utilizing the strengths of specific models for specific tasks. It features an auto-delegation system that intelligently breaks down complex user prompts and assigns sub-tasks to the most appropriate agent in the suite. By abstracting the orchestration layer, it enables developers to build highly capable, autonomous development pipelines with minimal overhead.

AI engineers and developers looking to build or experiment with advanced multi-agent systems for software development. It is geared towards users who want granular control over model selection and task routing in their autonomous workflows.

  • Multi-Model Orchestration: seamlessly combine different LLMs within the same agentic workflow.
  • Auto-Task Delegation: Automatically parses complex goals and delegates discrete sub-tasks to specialized agent roles.
  • Lean Architecture: A slimmed-down, fine-tuned version of Opencode that reduces boilerplate and improves execution speed.
  • Specialized Agent Personas: Pre-configured with distinct agent identities optimized for specific development tasks like debugging, architecture, or writing tests.
  • Extensible Framework: Easily add new tools, models, or custom agent personas to the existing orchestration engine.

Where teams use it

Autonomous Feature Development

Provide a high-level feature request and let the suite delegate architecture, implementation, and testing to different AI agents.

Cost-Optimized Orchestration

Route simple syntax tasks to cheaper, smaller models while reserving expensive models like GPT-4 for complex architectural decisions.

Automated Code Review

Deploy a specialized critic agent to review code generated by other agents, ensuring high quality and adherence to best practices before finalizing.

Polyglot Code Migration

Use multiple specialized agents to translate a legacy codebase into a modern framework, handling frontend and backend simultaneously.

README

master branch
oh-my-opencode-slim V3 Marketplace

✨ oh-my-opencode-slim ✨

Six divine beings emerged from the dawn of code, each an immortal master of their craft,
awaiting your command to forge order from chaos and build what was once thought impossible.

Opencode Multi Agent Suite · Mix any models · Auto delegate tasks

by Boring Dystopia Development

boringdystopia.ai  X @alvinunreal  Telegram Join channel 

svgdiagram.ai  svgdiagram.ai · Turn your notes into clean, editable SVG diagrams

English | 简体中文 | 繁體中文 | 日本語 | 한국어 | فارسی

✦ ✦ ✦

What's This Plugin

oh-my-opencode-slim is an agent orchestration plugin for OpenCode. It includes a built-in team of specialized agents that can scout a codebase, look up fresh documentation, review architecture, handle UI work, and execute well-scoped implementation tasks under one orchestrator.

The main idea is simple: instead of forcing one model to do everything, the plugin routes each part of the job to the agent best suited for it, balancing quality, speed and cost. The Orchestrator plans the work graph, dispatches specialists as background tasks, and reconciles their results before continuing.

✨ Highlights

  • Deepwork for heavy programming sessions. Big projects get built in phases, with an Oracle review between each one.
  • Agent Marketplace is live, and it grows with the community. Suggest an agent or open a PR on oh-my-opencode-marketplace to help build it.
  • OmniRoute is your friend. One free gateway to hundreds of providers and models, with automatic fallback when a quota runs out. Mix models across the team without the account juggling.
  • Want to use Claude? Check out ACP support: bring Claude Code in as a subagent the Orchestrator can delegate to.
  • Make it yours. oh-my-opencode-slim is built to be customized, globally or per project: add new agents, override prompts, and rewrite the delegation rules so the Orchestrator routes work your way.
  • Own your presets. Model lineups change fast, so the example presets go stale quickly. Use them for ideas, then build your own around the models you actually have.

What Users Say

“Task management went from 5/10 to 8-9/10 easily. The Orchestrator sends Fixers and Explorers, and I can still talk and plan with the Orchestrator in the same session. The experience feels way smoother now.”

- vipor_idk

“I ditched all my harnesses for this beta version of omo-slim and don't look back or miss anything. Great work and IMHO all in the right direction.”

- stephanschielke

“I love omo-slim, and can't imagine running opencode without it. I love that I can create a Frankenstein of models... Makes the setup such a beast.”

- Capital-One3039

“It has significantly improved my workflow... Now, it is working very smoothly, and I love it.”

- xenstar1

Merch · The Pantheon in gold

The six agents as gold tarot artwork, on clothing, desk gear and prints.

The Orchestrator in gold on a black tee
Tee
The Oracle tarot card on the back of a black hoodie
Hoodie
All six agent tarot cards in a black frame
Framed poster
All six agents in gold on a black mouse pad
Mouse pad

Explore the collection →

Quick Start

Copy and paste this prompt to your LLM agent (Claude Code, AmpCode, Cursor, etc.):

Install and configure oh-my-opencode-slim: https://raw.githubusercontent.com/alvinunreal/oh-my-opencode-slim/refs/heads/master/README.md

Manual Installation

bunx oh-my-opencode-slim@latest install

The published CLI is a Node-compatible bundle, so npx works too if you don't have Bun installed:

npx oh-my-opencode-slim@latest install

Run from Master

Use this if you want the latest code, easier bug fixes, or a local setup for development and contributions:

git clone https://github.com/alvinunreal/oh-my-opencode-slim.git ~/repos/oh-my-opencode-slim
cd ~/repos/oh-my-opencode-slim
bun install
bun run build
bun dist/cli/index.js install

The installer adds the local repo path to the plugin array in ~/.config/opencode/opencode.json, so OpenCode loads the plugin from that folder. To update later:

cd ~/repos/oh-my-opencode-slim
git pull
bun install
bun run build

Upgrading from separate Librarian/Explorer agents? See the configuration update guide for restored MCP defaults and custom model/skill precedence.

Getting Started

Slim requires OpenCode 2.3.0 or newer. OpenCode delivers subagent completions to the parent. Slim removed its five-minute idle TODO reminder. See the upgrade guide for the host update and configuration changes.

The installer generates both OpenAI and OpenCode Go presets, with OpenAI active by default.

Tip

Tune the models and agents for your own workflow. The defaults are only a starting point; the plugin is designed for deep flexibility and customization.

To make OpenCode Go active during install, run bunx oh-my-opencode-slim@latest install --preset=opencode-go or change the default preset name in ~/.config/opencode/oh-my-opencode-slim.json after installation.

Then:

  1. Log in to the providers you want to use if you haven't already:

    opencode auth login
  2. Refresh and list the models OpenCode can see:

    opencode models --refresh

    On OpenCode v2, use opencode models instead.

  3. Open your plugin config at ~/.config/opencode/oh-my-opencode-slim.json

  4. Update the models you want for each agent

Tip

It's recommended to understand how background orchestration works. The Orchestrator prompt contains the scheduler rules, specialist routing logic, and thresholds for when work should be assigned to background agents. You can always delegate manually by calling a subagent via: @agentName <task>

Tip

Because background agents are now the default workflow, it is highly recommended to enable and configure Multiplexer Integration. It automatically opens each agent in a dedicated Tmux, Zellij, Herdr, cmux, kitty, WezTerm, or Orca pane, so you can watch specialists work live while the Orchestrator continues coordinating the session. On OpenCode v2 hosts, panes work with the shared background service or an explicit --server; --standalone hosts cannot host panes (one diagnostic per process; use v2's native subagent surfaces instead).

The default generated configuration includes both openai and opencode-go presets.

{
  "$schema": "https://unpkg.com/oh-my-opencode-slim@latest/oh-my-opencode-slim.schema.json",
  "preset": "openai",
  "presets": {
    "openai": {
      "orchestrator": { "model": "openai/gpt-6.1-sol", "variant": "medium", "skills": ["*"] },
      "oracle": { "model": "openai/gpt-6.1-sol", "variant": "high", "skills": ["simplify"] },
      "explorer": { "model": "openai/gpt-6-luna", "variant": "low", "skills": [] },
      "designer": { "model": "openai/gpt-6-luna", "variant": "medium", "skills": [] },
      "fixer": { "model": "openai/gpt-6.1-sol", "variant": "low", "skills": [] }
    }
  }
}

Presets can inherit from one base preset with extends: a design preset can extend base and override only its designer model. On v2, /preset lets you apply subagent inference settings to Current session or change the Global default. /preset <name> applies the preset to the session you are in — no restart — while manual configuration edits change the default for future sessions and refresh default-bound roots on their next admission. Explicitly applied sessions keep their saved configuration until you reapply the preset to that session. After reapplying, explicitly continuing a bound child with the same agent adopts the parent's updated inference settings while retaining its ID and history. This is best-effort: a failed continuation can leave the native model changed without saving the new team snapshot. Main-session models, prompts, tools, skills and MCPs are not switched by the session action. The sidebar shows the current session's saved team models and variants; /preset marks its bound preset separately from the global default. V2 defaults to backgroundJobs.mode: "native": OpenCode owns the child Job lifecycle, and Slim keeps exact-ID status, cancellation, permission reply, and queue-only progress reporting. V2 rejects the V1-only "managed" mode. With backgroundJobs.mode: "off", V2 delegation stays fully native: session bindings and all OMOS task tools are disabled, while the configured global preset still selects the agent settings registered at startup. See Preset Switching for scope and timing, and Configuration for the inheritance example and precedence rules.

Preset Docs

Project settings in .opencode/oh-my-opencode-slim.json[c] are inherited from ancestor directories up to the filesystem root. OPENCODE_DISABLE_PROJECT_CONFIG disables the project walk. Closer settings override matching fields. Prompt files and the optional skills_include_local grants also search ancestor .opencode directories, following OpenCode's directory discovery. See Configuration for precedence and trust boundaries.

Tip

Treat these presets as starting points, not recipes. Models change fast and presets go stale quickly. Build your own from the models you actually have access to rather than copy-pasting one blindly. The bundled oh-my-opencode-slim skill can help: ask the Orchestrator to tune your setup.

  • OpenAI Preset — the default generated preset; runs all agents on OpenAI models.
  • OpenCode Go Preset — runs the agents on OpenCode Go models; enables the Observer agent for visual analysis since its orchestrator model isn't multimodal.
  • Author's Preset — the exact config the author runs day to day, with third-party skills.
  • $30 Preset — a mixed-provider setup built around Codex Plus and GitHub Copilot Pro for about $30/month.
  • $40 Preset — a dual-subscription setup pairing Claude Pro and ChatGPT Plus for about $40/month.

For Alternative Providers

To use custom providers or a mixed-provider setup, use Configuration for the full reference.

✅ Verify Your Setup

After installation and authentication, verify all agents are configured and responding:

opencode

Then run:

ping all agents
Ping all agents

Confirmation that all configured agents are online and ready.

If any agent fails to respond, check your provider authentication and config file.


🏛️ Meet the Pantheon

Tip

The Pantheon has a saga. The Chronicle of the Pantheon tells where these agents came from, starting in the emptiness before the world. Read it at ohmyopencodeslim.com/lore.

01. Orchestrator: The Embodiment Of Order


Forged in the void of complexity.
The Orchestrator was born when the first codebase collapsed under its own complexity. Neither god nor mortal would claim responsibility - so The Orchestrator emerged from the void, forging order from chaos. It determines the optimal path to any goal, balancing speed, quality, and cost. It guides the team, summoning the right specialist for each task and delegating to achieve the best possible outcome.
Role: Master delegator and strategic coordinator
Prompt: orchestrator.ts
Default Model: openai/gpt-6.1-sol (medium)
Recommended Models: claude-opus-5-5 gemini-4-argon claude-fable-5.1 glm-5.3 mimo-v2.6 minimax-m3.1 qwen3.8-plus
Model Guidance: Choose your strongest planning and judgment model. Orchestrator is the workflow manager: it plans, schedules background specialists, reconciles results, and verifies outcomes, so it needs reliable instruction-following and high-level technical judgment more than raw worker throughput.

02. Explorer: The Eternal Wanderer


The wind that carries knowledge.
The Explorer is an immortal wanderer who has traversed the corridors of a million codebases since the dawn of programming. Cursed with the gift of eternal curiosity, they cannot rest until every file is known, every pattern understood, every secret revealed. Legends say they once searched the entire internet in a single heartbeat. They are the wind that carries knowledge, the eyes that see all, the spirit that never sleeps.
Role: Codebase reconnaissance and external research
Prompt: explorer.ts
Default Model: openai/gpt-6-luna
Recommended Models: gpt-6-luna deepseek-flash
Model Guidance: Choose a fast, low-cost model. Explorer handles broad scouting work, so speed and efficiency usually matter more than using your strongest reasoning model.

03. Oracle: The Guardian of Paths


The voice at the crossroads.
The Oracle stands at the crossroads of every architectural decision. They have walked every road, seen every destination, know every trap that lies ahead. When you stand at the precipice of a major refactor, they are the voice that whispers which way leads to ruin and which way leads to glory. They don't choose for you - they illuminate the path so you can choose wisely.
Role: Strategic advisor and debugger of last resort
Prompt: oracle.ts
Default Model: openai/gpt-6.1-sol (high)
Recommended Models: gpt-6-astra claude-opus-5-5 claude-fable-5.1 kimi-k3.1 deepseek-flash glm-5.3 qwen3.8-max
Model Guidance: Choose your strongest high-reasoning model for architecture, hard debugging, trade-offs, and code review.

04. Council: The Chorus of Minds

Note

Why doesn't Orchestrator auto-call Council more often? This is intentional. Council runs multiple models at once, so automatic delegation is kept strict because it is usually the highest-cost path in the system. In practice, ask for it in your message — mentioning council, @council, consensus, 共识, or another trigger word injects the Council Mode procedure once per session (at the first trigger; later triggers don't re-inject it) and the orchestrator dispatches every councillor seat in parallel, for example: run a council on these two architectures. The full procedure is never carried statically: sessions that never ask for a council pay zero tokens for it, and the injection can be turned off entirely with disabled_hooks: ["council-inject"].


Many minds, one verdict.
The Council is not a lone being but a chamber of minds summoned when one answer is not enough. It sends your question to multiple models in parallel, gathers their competing judgments, and then the Council agent itself distills the strongest ideas into a single verdict. Where a solitary agent may miss a path, the Council cross-examines possibility itself.
Role: Multi-LLM consensus and synthesis
Prompt: council.ts
Guide: docs/council.md
Default Setup: Config-driven - councillors come from council.presets and the Council agent model comes from your normal council agent config
Recommended Setup: Strong Council model + diverse councillors across providers
Model Guidance: Use a strong synthesis model for the Council agent and diverse models as councillors. The value of Council comes from comparing different model perspectives, not just picking the single strongest model everywhere.

05. Designer: The Guardian of Aesthetics


Beauty is essential.
The Designer is an immortal guardian of beauty in a world that often forgets it matters. They have seen a million interfaces rise and fall, and they remember which ones were remembered and which were forgotten. They carry the sacred duty to ensure that every pixel serves a purpose, every animation tells a story, every interaction delights. Beauty is not optional - it's essential.
Role: UI/UX implementation and visual excellence
Prompt: designer.ts
Default Model: openai/gpt-6-luna
Recommended Models: claude-opus-5-5 gemini-4-argon gemini-3.8-flash kimi-k2.7-code minimax-m3.1
Model Guidance: Choose a model that is strong at UI/UX judgment, frontend implementation, and visual polish.

06. Fixer: The Last Builder


The final step between vision and reality.
The Fixer is the last of a lineage of builders who once constructed the foundations of the digital world. When the age of planning and debating began, they remained - the ones who actually build. They carry the ancient knowledge of how to turn thought into thing, how to transform specification into implementation. They are the final step between vision and reality.
Role: Fast implementation specialist
Prompt: fixer.ts
Default Model: openai/gpt-6.1-sol (low)
Recommended Models: gpt-6.1-sol claude-opus-5-5 deepseek-flash
Model Guidance: Choose a reliable coding model for scoped implementation work. Fixer receives a concrete plan or bounded instructions from Orchestrator, making it a good place for efficient execution tasks and straightforward code changes.

🛒 Marketplace

The Pantheon is open to newcomers. The Agent Marketplace is live: community-built specialist agents you can install with one command and add to your team.

Browse the Marketplace →  ·  Submit your agent →

Paladin
Paladin by stevio2d
Read-only security review for changes that cross a trust boundary.
alvin/paladin
Arbiter
Arbiter by capyBearista
Evidence-backed merge-readiness review after real implementation work.
capybearista/arbiter
Hunter
Hunter by capyBearista
Hunts swallowed errors, misleading fallbacks, and hidden retry exhaustion.
capybearista/hunter
Proctor
Proctor by capyBearista
Checks whether a change has enough behavioral tests and ranks the gaps.
capybearista/proctor
Janitor
Janitor by hbollon
Read-only maintainability audit for when the repo is getting harder to change.
alvin/janitor
Documenter
Documenter by Alvin
Documentation architect for coherent, source-grounded docs.
alvin/documenter
Chronicler
Chronicler by capyBearista
Durable docs, changelogs, architecture notes, and migration guides.
capybearista/chronicler
➕ Your agent here

Built a specialist that earns its place? Publish it to the marketplace and let every oh-my-opencode-slim user add it to their team.

See all agents →

Add one to your team. Ask the Orchestrator ("install the Paladin agent from the marketplace"), or use the CLI from your project directory:

bunx oh-my-opencode-slim@latest marketplace install alvin/paladin
bunx oh-my-opencode-slim@latest marketplace enable alvin/paladin

Restart OpenCode afterwards; new agents join the registry on the next plugin load. Installed agents use your session model by default, and the Orchestrator routes work to them the same way it routes to the built-in specialists. See Marketplace packages for the full CLI, preset activation, and update flow.


Optional Agents

Observer: The Silent Witness

Note

Why a separate agent? If your Orchestrator model is not multimodal, enable Observer to handle images, screenshots, and other visual files. Observer is disabled by default and gives the Orchestrator a dedicated multimodal reader without forcing you to change your main reasoning model. Set disabled_agents: [] and an observer model in your configuration. The bundled opencode-go install preset does this automatically because its GLM Orchestrator is not multimodal. Omitting image_routing preserves existing conditional Observer behavior. "auto" is capability-aware: models that accept image input keep attachments inline for native vision; non-vision chains get attachments saved under .opencode/images/<session>/ with a delegation nudge by path. "direct" always keeps image parts inline. Saved workspace images are not automatically deleted. Remove the whole .opencode/images/ directory or a single session subdirectory manually when no longer needed (references in old conversations then stop resolving); images from session-less messages are saved at the top level.

Tip

Subagents reading images. Advisory subagents (explorer, oracle, designer, councillors) can dispatch @observer themselves for image files on disk. On OpenCode v2 hosts this needs one extra hop of nesting, which the host denies by default — set "experimental": { "subagent_depth": 2 } in your opencode config to enable it. Fixer, observer itself, and the council synthesizer stay non-spawning by design.


The eye that reads what others cannot.

Read-only visual analysis - interprets images, screenshots, PDFs, and diagrams. Returns structured observations to the orchestrator without loading raw file bytes into the main context window.

  • Images, screenshots, diagrams → read tool (native image support)

  • PDFs → read tool (passed to the model as PDF media, not text-extracted)

  • Disabled by default - enable with "disabled_agents": [] and configure a vision-capable model; installing with --preset=opencode-go enables it with opencode-go/mimo-v2.5. In "auto", attachments ride the turn model's capabilities: vision-capable models read them inline, non-vision chains get attachments saved as workspace assets and routed to Observer by path; set "image_routing": "direct" to always keep them inline. The automatic save-and-route covers pasted images only (PNG/JPEG/GIF/WebP); PDFs and images produced by tools stay inline, so delegate those by path yourself.

Prompt: observer.ts
Default Model: openai/gpt-6-luna - configure a vision-capable model to enable
Recommended Models: mimo-v2.5 qwen3.5-plus
Model Guidance: Choose a vision-capable model if you want the agent to read screenshots, images, PDFs, and other visual files.

🧩 Skills

Skills are prompt-based instructions injected into an agent's system prompt to guide decisions, workflows, and tool use. Unlike MCPs (which are running servers), a skill runs no process — it is a focused playbook an agent activates when the task calls for it. The plugin registers its eight bundled skills in-process at load — updates apply on restart, nothing is copied to disk. A same-named skill directory under ~/.config/opencode/skills/ overrides the bundled version.

Skill Purpose Default agent How to invoke
Codemap artifact
codemap
Hierarchical repository maps so agents understand codebases without re-reading everything orchestrator run codemap
Deepwork artifact
deepwork
Autonomous pass-by-pass workflow (sketch → structure → detail) for large, risky coding sessions, one review gate per pass orchestrator /deepwork <task>
Verification Planning artifact
verification-planning
Plans a project-specific evidence path before non-trivial changes orchestrator automatic before non-trivial work
Simplify artifact
simplify
Behavior-preserving simplification for readability and maintainability oracle ask for simplification or during review
Worktrees artifact
worktrees
Git worktrees as safe, isolated coding lanes for risky or parallel work orchestrator work in a worktree
Clonedeps artifact
clonedeps
Clones dependency source locally so agents can inspect library internals orchestrator clone dependencies
Step Back artifact
step-back
Pauses snowballing patches to reassess direction and propose a cleaner path orchestrator automatic when fixes start stacking
Deanchor artifact
deanchor
Generalizes from examples instead of copying them with light edits orchestrator automatic when a request includes examples
AI Estimates artifact
ai-estimates
Estimates task duration for a human working with AI, not alone orchestrator ask how long something will take
Reflect artifact
reflect
Turns repeated workflow friction into reusable skills, agents, or config orchestrator /reflect
oh-my-opencode-slim artifact
oh-my-opencode-slim
Configures and safely improves the plugin setup itself orchestrator ask to tune your setup

Skill assignments are permission grants — an agent can only activate skills it has been given. Configure them per agent with the skills array in ~/.config/opencode/oh-my-opencode-slim.json: an explicit list, "*" for everything, or "!skill-name" to deny one.

See Skills for full documentation, or browse the illustrated overview at ohmyopencodeslim.com/skills.


🖥️ Companion

Native source and releases: oh-my-opencode-companion. The plugin keeps the installer, updater, and state integration; existing commands and configuration are unchanged.

The optional Companion is a floating desktop status window for live agent activity. It shows the current session state and which agents are active, so background work is easier to follow at a glance.

Companion showing active agents

Left bottom visual companion.

Companion is not part of the regular install. Add it any time after installing the plugin:

bunx oh-my-opencode-slim@latest companion install

This downloads the native binary for your platform and sets "companion": { "enabled": true } in your config. Restart OpenCode to launch it.

See Companion for configuration, positions, sizes, and install details.


📚 Documentation

Use this section as a map: start with installation, then jump to features, configuration, or example presets depending on what you need.

✨ Features & Workflows

Doc What it covers
Council Run multiple models in parallel and synthesize a single answer — keyword-triggered via the orchestrator's Council Mode procedure
Custom Agents Define your own specialists with custom prompts, models, MCP access, and Orchestrator delegation rules
ACP Agents Connect external ACP-compatible agents such as Claude Code ACP or Gemini ACP as delegatable subagents; tool and plan progress streams to the TUI while they work
Multiplexer Integration Watch agents work live in Tmux, Zellij, Herdr, cmux, kitty, WezTerm, or Orca panes
Codemap Generate hierarchical codemaps to understand large codebases faster
Clonedeps Clone selected dependency source into an ignored local workspace for inspection
Worktrees Use .slim/worktrees/ lanes for isolated parallel or risky coding work
Preset Switching Switch agent model presets at runtime with /preset
Interview Turn rough ideas into a structured markdown spec through a browser-based Q&A flow, then implement it with /implement
Companion Floating window companion for parsing, help, and types

⚙️ Config & Reference

Doc What it covers
Installation Guide Install the plugin, use CLI flags, reset config, and troubleshoot setup
OpenCode v2 Compatibility Host contracts, feature matrix, entrypoints and package loading
Runtime Efficiency Shared configuration reads, request-local facts, optional implementation loading and verification
Configuration Config file locations, JSONC support, prompt overrides, and full option reference
Marketplace Install, inspect, activate, and update marketplace agent packages
Project Customization Repository-specific custom agents, prompt overrides, per-agent skills, and precedence
Background Orchestration Scheduler-first orchestrator model built around native background subagents
Maintainer Guide Issue triage rules, label meanings, support routing, and repo maintenance workflow
Developer Evals Source-checkout routing/reliability harness, offline scoring, and advisory model judging
Skills Bundled skills such as simplify, codemap, clonedeps, deepwork, verification-planning, step-back, deanchor, ai-estimates, reflect, worktrees, and oh-my-opencode-slim
MCPs context7, gh_grep, and how MCP permissions work per agent
Tools What Slim adds: background task control, ast_grep search, and the enhanced webfetch

🏛️ Contributors

The builders, debuggers, writers, and wanderers who have earned their place in the pantheon.

Every merged contribution leaves a mark on the realm.

All Contributors


Alvin
Alvin

💻
alvinreal
alvinreal

💻
imw
imw

💻
Adithya Kozham Burath Bijoy
Adithya Kozham Burath Bijoy

💻
ReqX
ReqX

💻
Abhideep Maity
Abhideep Maity

💻
Ruben
Ruben

💻
Gabriel Rodrigues
Gabriel Rodrigues

💻
John Michael Vincent Bambico
John Michael Vincent Bambico

💻
Molt Founders
Molt Founders

💻
Muen Yu
Muen Yu

💻
NocturnesLK
NocturnesLK

💻
Riccardo Sallusti
Riccardo Sallusti

💻
Yan Li
Yan Li

💻
Hoàng Văn Anh Nghĩa
Hoàng Văn Anh Nghĩa

💻
Jacob Myers
Jacob Myers

💻
Kassie Povinelli
Kassie Povinelli

💻
KyleHilliard
KyleHilliard

💻
j5hjun
j5hjun

💻
marcFernandez
marcFernandez

💻
mister-test
mister-test

💻
n24q02m
n24q02m

💻
oribi
oribi

💻
pelidan
pelidan

💻
xLillium
xLillium

💻
⁢4.435km/s
⁢4.435km/s

💻
Drin
Drin

💻
Hakim Zulkufli
Hakim Zulkufli

💻
Simon Klakegg
Simon Klakegg

💻
Kiwi
Kiwi

💻
Raxxoor
Raxxoor

💻
nyanyani
nyanyani

💻
nettee
nettee

💻
Link
Link

💻
Bartosz Łaszewski
Bartosz Łaszewski

💻
huilang021x
huilang021x

💻
Dusan Kovacevic
Dusan Kovacevic

💻
jwcrystal
jwcrystal

💻
Nguyen Canh Toan
Nguyen Canh Toan

💻
Thomas Dyar
Thomas Dyar

💻
zero
zero

💻
Denis Balan
Denis Balan

💻
Gustavo Caiano
Gustavo Caiano

💻

Recent activity

commits and pull requests

Releases and announcements

84 total
  1. v3.0.7v3.0.7Nov 4, 2026

    ## What's Changed * docs: overhaul Pantheon recommended models, align zh-CN hero, and add $40 dual-subscription preset by @zjm54321 in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1669 * refactor(background): dissolve board ceremony — watchdog abort, structured v2 registration, gate trimming (DRAFT, rebase planned onto #1652) by @Jiajun0413 in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1662 * fix(foreground-fallback): send only the internal reminder on replay by @dhaern in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1671 * fix(foreground-fallback): give a stalled replay read one more window by @dhaern in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1665 * fix(tui): hide council agents from sidebar by @Cle2ment in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1673 * fix(agents): stop promising a wake scheduler on v2 hosts by @Jiajun0413 in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1667 * fix(marketplace): honor explicit external-directory guard permissions by @BoysGameStudio in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1675 * feat(herdr): honor main_pane_size and equalize agent panes by @LPX

  2. v3.0.6v3.0.6Oct 24, 2026

    ## What's Changed * refactor(deepwork): drop the speculative claims path; unify the tombstone flip predicate by @Jiajun0413 in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1618 * fix(agents): deny question for subagents by default by @Jiajun0413 in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1631 * fix(companion): stabilize multi-monitor popup and native dragging by @Aveer in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1624 * fix: honor agent display names in sidebar by @giannisCKS in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1619 * chore(companion): sync native v0.1.9 release by @github-actions[bot] in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1632 * refactor(orchestrator): drop the Child sessions block; single-source tool guidance by @Jiajun0413 in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1633 * webfetch(smartfetch): P0 slimming — drop secondary-model chain, inline images, metadata sprawl by @Jiajun0413 in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1638 * fix(v2): triage untracked-session recovery by host outcome, not transcript by @Jiajun0413 in https://github.com/alvinunreal/oh-my

  3. v3.0.5v3.0.5Oct 18, 2026

    ## What's Changed * perf(task-reply): drop the dead v2 answers arg and its caveat sentence by @Jiajun0413 in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1510 * fix(v2): settle revived children after compaction by @guidan-nick in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1512 * fix(foreground-fallback): walk the chain from the head and skip only tried or abandoned providers by @dhaern in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1511 * refactor(prompt): v1 renders the same slim routing lines as v2; table-drive write capability by @Jiajun0413 in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1513 * fix(tasks): let managed Build parents recover their own children by @unsnow-iac in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1516 * fix(release): automatically ship native Companion changes and block stale npm releases by @Aveer in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1514 * test(companion): assert COMPANION_MANIFEST.version instead of hardcoded 0.1.4 by @mhenke in https://github.com/alvinunreal/oh-my-opencode-slim/pull/1525 * perf(task-tools): stop rendering the board generation counter to the model

  4. Companion v0.1.8companion-v0.1.8Oct 18, 20265.6K downloads

    Native companion binary release for oh-my-opencode-slim.

  5. Companion v0.1.7companion-v0.1.7Oct 18, 202628 downloads

    Native companion binary release for oh-my-opencode-slim.

Code frequency

additions and deletions
+120.4K-120.4KWeek of 2026-01-11: +9,688 linesWeek of 2026-01-11: -1,191 linesWeek of 2026-01-18: +18,462 linesWeek of 2026-01-18: -11,142 linesWeek of 2026-01-25: +6,663 linesWeek of 2026-01-25: -5,128 linesWeek of 2026-02-01: +4,579 linesWeek of 2026-02-01: -503 linesWeek of 2026-02-08: +4,134 linesWeek of 2026-02-08: -230 linesWeek of 2026-02-15: +80 linesWeek of 2026-02-15: -38 linesWeek of 2026-02-22: +600 linesWeek of 2026-02-22: -215 linesWeek of 2026-03-01: +393 linesWeek of 2026-03-01: -66 linesWeek of 2026-03-08: +1,249 linesWeek of 2026-03-08: -6,665 linesWeek of 2026-03-15: +562 linesWeek of 2026-03-15: -229 linesWeek of 2026-03-22: +3,592 linesWeek of 2026-03-22: -2,230 linesWeek of 2026-03-29: +10,972 linesWeek of 2026-03-29: -2,635 linesWeek of 2026-04-05: +10,211 linesWeek of 2026-04-05: -211 linesWeek of 2026-04-12: +20,453 linesWeek of 2026-04-12: -2,443 linesWeek of 2026-04-19: +15,935 linesWeek of 2026-04-19: -19,781 linesWeek of 2026-04-26: +5,007 linesWeek of 2026-04-26: -2,034 linesWeek of 2026-05-03: +5,649 linesWeek of 2026-05-03: -2,664 linesWeek of 2026-05-10: +10,401 linesWeek of 2026-05-10: -5,267 linesWeek of 2026-05-17: +5,059 linesWeek of 2026-05-17: -2,540 linesWeek of 2026-05-24: +1,949 linesWeek of 2026-05-24: -4,949 linesWeek of 2026-05-31: +784 linesWeek of 2026-05-31: -297 linesWeek of 2026-06-07: +10,706 linesWeek of 2026-06-07: -5,849 linesWeek of 2026-06-14: +8,413 linesWeek of 2026-06-14: -1,665 linesWeek of 2026-06-21: +9,614 linesWeek of 2026-06-21: -1,425 linesWeek of 2026-06-28: +13,400 linesWeek of 2026-06-28: -5,954 linesWeek of 2026-07-05: +10,056 linesWeek of 2026-07-05: -7,236 linesWeek of 2026-07-12: +17,720 linesWeek of 2026-07-12: -8,306 linesWeek of 2026-07-19: +15,835 linesWeek of 2026-07-19: -4,448 linesWeek of 2026-07-26: +2,368 linesWeek of 2026-07-26: -517 linesWeek of 2026-08-02: +8,783 linesWeek of 2026-08-02: -15,840 linesWeek of 2026-08-09: +25,512 linesWeek of 2026-08-09: -5,063 linesWeek of 2026-08-16: +12,019 linesWeek of 2026-08-16: -3,178 linesWeek of 2026-08-23: +16,891 linesWeek of 2026-08-23: -2,013 linesWeek of 2026-08-30: +6,363 linesWeek of 2026-08-30: -728 linesWeek of 2026-09-06: +10,977 linesWeek of 2026-09-06: -1,268 linesWeek of 2026-09-13: +53,104 linesWeek of 2026-09-13: -22,173 linesWeek of 2026-09-20: +63,295 linesWeek of 2026-09-20: -24,491 linesWeek of 2026-09-27: +45,547 linesWeek of 2026-09-27: -16,606 linesWeek of 2026-10-04: +36,191 linesWeek of 2026-10-04: -10,309 linesWeek of 2026-10-11: +27,285 linesWeek of 2026-10-11: -13,452 linesWeek of 2026-10-18: +42,937 linesWeek of 2026-10-18: -28,867 linesWeek of 2026-10-25: +52,870 linesWeek of 2026-10-25: -25,700 linesWeek of 2026-11-01: +34,027 linesWeek of 2026-11-01: -9,284 linesWeek of 2026-11-08: +22,087 linesWeek of 2026-11-08: -120,354 linesJan 11, 2026Nov 8, 2026
+682.4K lines added, -405.2K removed over the last year.

Commits per week

last 52 weeks
2490Week of 2025-11-16: 0 commitsWeek of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 29 commitsWeek of 2026-01-18: 70 commitsWeek of 2026-01-25: 21 commitsWeek of 2026-02-01: 5 commitsWeek of 2026-02-08: 5 commitsWeek of 2026-02-15: 5 commitsWeek of 2026-02-22: 6 commitsWeek of 2026-03-01: 4 commitsWeek of 2026-03-08: 7 commitsWeek of 2026-03-15: 8 commitsWeek of 2026-03-22: 7 commitsWeek of 2026-03-29: 33 commitsWeek of 2026-04-05: 27 commitsWeek of 2026-04-12: 58 commitsWeek of 2026-04-19: 82 commitsWeek of 2026-04-26: 35 commitsWeek of 2026-05-03: 31 commitsWeek of 2026-05-10: 62 commitsWeek of 2026-05-17: 41 commitsWeek of 2026-05-24: 10 commitsWeek of 2026-05-31: 14 commitsWeek of 2026-06-07: 45 commitsWeek of 2026-06-14: 77 commitsWeek of 2026-06-21: 52 commitsWeek of 2026-06-28: 93 commitsWeek of 2026-07-05: 159 commitsWeek of 2026-07-12: 134 commitsWeek of 2026-07-19: 102 commitsWeek of 2026-07-26: 19 commitsWeek of 2026-08-02: 85 commitsWeek of 2026-08-09: 56 commitsWeek of 2026-08-16: 39 commitsWeek of 2026-08-23: 81 commitsWeek of 2026-08-30: 26 commitsWeek of 2026-09-06: 47 commitsWeek of 2026-09-13: 155 commitsWeek of 2026-09-20: 218 commitsWeek of 2026-09-27: 166 commitsWeek of 2026-10-04: 181 commitsWeek of 2026-10-11: 244 commitsWeek of 2026-10-18: 152 commitsWeek of 2026-10-25: 249 commitsWeek of 2026-11-01: 155 commitsWeek of 2026-11-08: 87 commitsNov 16, 2025Nov 8, 2026
3.2K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 12 commitsSun 1:00 — 15 commitsSun 2:00 — 8 commitsSun 3:00 — 6 commitsSun 4:00 — 2 commitsSun 5:00 — 4 commitsSun 6:00 — 44 commitsSun 7:00 — 4 commitsSun 8:00 — 23 commitsSun 9:00 — 26 commitsSun 10:00 — 15 commitsSun 11:00 — 16 commitsSun 12:00 — 33 commitsSun 13:00 — 29 commitsSun 14:00 — 24 commitsSun 15:00 — 32 commitsSun 16:00 — 21 commitsSun 17:00 — 18 commitsSun 18:00 — 16 commitsSun 19:00 — 55 commitsSun 20:00 — 28 commitsSun 21:00 — 25 commitsSun 22:00 — 32 commitsSun 23:00 — 19 commitsMon 0:00 — 9 commitsMon 1:00 — 11 commitsMon 2:00 — 17 commitsMon 3:00 — 1 commitsMon 4:00 — 2 commitsMon 5:00 — 2 commitsMon 6:00 — 1 commitsMon 7:00 — 13 commitsMon 8:00 — 14 commitsMon 9:00 — 19 commitsMon 10:00 — 28 commitsMon 11:00 — 26 commitsMon 12:00 — 20 commitsMon 13:00 — 43 commitsMon 14:00 — 43 commitsMon 15:00 — 47 commitsMon 16:00 — 11 commitsMon 17:00 — 19 commitsMon 18:00 — 22 commitsMon 19:00 — 34 commitsMon 20:00 — 21 commitsMon 21:00 — 26 commitsMon 22:00 — 23 commitsMon 23:00 — 25 commitsTue 0:00 — 22 commitsTue 1:00 — 9 commitsTue 2:00 — 3 commitsTue 3:00 — 0 commitsTue 4:00 — 2 commitsTue 5:00 — 3 commitsTue 6:00 — 5 commitsTue 7:00 — 5 commitsTue 8:00 — 12 commitsTue 9:00 — 22 commitsTue 10:00 — 15 commitsTue 11:00 — 15 commitsTue 12:00 — 18 commitsTue 13:00 — 27 commitsTue 14:00 — 19 commitsTue 15:00 — 36 commitsTue 16:00 — 30 commitsTue 17:00 — 17 commitsTue 18:00 — 12 commitsTue 19:00 — 16 commitsTue 20:00 — 29 commitsTue 21:00 — 38 commitsTue 22:00 — 18 commitsTue 23:00 — 13 commitsWed 0:00 — 9 commitsWed 1:00 — 17 commitsWed 2:00 — 5 commitsWed 3:00 — 1 commitsWed 4:00 — 3 commitsWed 5:00 — 0 commitsWed 6:00 — 7 commitsWed 7:00 — 7 commitsWed 8:00 — 20 commitsWed 9:00 — 7 commitsWed 10:00 — 14 commitsWed 11:00 — 11 commitsWed 12:00 — 30 commitsWed 13:00 — 30 commitsWed 14:00 — 33 commitsWed 15:00 — 31 commitsWed 16:00 — 19 commitsWed 17:00 — 19 commitsWed 18:00 — 14 commitsWed 19:00 — 16 commitsWed 20:00 — 33 commitsWed 21:00 — 20 commitsWed 22:00 — 12 commitsWed 23:00 — 10 commitsThu 0:00 — 8 commitsThu 1:00 — 7 commitsThu 2:00 — 14 commitsThu 3:00 — 17 commitsThu 4:00 — 7 commitsThu 5:00 — 5 commitsThu 6:00 — 8 commitsThu 7:00 — 10 commitsThu 8:00 — 19 commitsThu 9:00 — 20 commitsThu 10:00 — 29 commitsThu 11:00 — 24 commitsThu 12:00 — 13 commitsThu 13:00 — 24 commitsThu 14:00 — 20 commitsThu 15:00 — 40 commitsThu 16:00 — 21 commitsThu 17:00 — 27 commitsThu 18:00 — 22 commitsThu 19:00 — 34 commitsThu 20:00 — 24 commitsThu 21:00 — 31 commitsThu 22:00 — 25 commitsThu 23:00 — 16 commitsFri 0:00 — 6 commitsFri 1:00 — 9 commitsFri 2:00 — 9 commitsFri 3:00 — 12 commitsFri 4:00 — 2 commitsFri 5:00 — 5 commitsFri 6:00 — 6 commitsFri 7:00 — 4 commitsFri 8:00 — 19 commitsFri 9:00 — 8 commitsFri 10:00 — 15 commitsFri 11:00 — 11 commitsFri 12:00 — 17 commitsFri 13:00 — 13 commitsFri 14:00 — 25 commitsFri 15:00 — 31 commitsFri 16:00 — 20 commitsFri 17:00 — 16 commitsFri 18:00 — 13 commitsFri 19:00 — 14 commitsFri 20:00 — 22 commitsFri 21:00 — 26 commitsFri 22:00 — 44 commitsFri 23:00 — 29 commitsSat 0:00 — 12 commitsSat 1:00 — 25 commitsSat 2:00 — 12 commitsSat 3:00 — 12 commitsSat 4:00 — 15 commitsSat 5:00 — 33 commitsSat 6:00 — 15 commitsSat 7:00 — 20 commitsSat 8:00 — 13 commitsSat 9:00 — 31 commitsSat 10:00 — 16 commitsSat 11:00 — 37 commitsSat 12:00 — 25 commitsSat 13:00 — 48 commitsSat 14:00 — 40 commitsSat 15:00 — 40 commitsSat 16:00 — 34 commitsSat 17:00 — 30 commitsSat 18:00 — 15 commitsSat 19:00 — 28 commitsSat 20:00 — 38 commitsSat 21:00 — 26 commitsSat 22:00 — 19 commitsSat 23:00 — 25 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Who is committing

last 52 weeks
Maintainer commits1,753 (43%)
Community commits2,346 (57%)

4,099 commits in total over the last year.

DateListRankStars gained
Jan 17, 2026daily#22+145
  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • anomalyco/opencode

    The open source coding agent.

    228.3K stars · TypeScript

  • n8n-io/n8n

    Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

    211.6K stars · TypeScript

  • firecrawl/firecrawl

    Knowledge infrastructure to make your agents smarter. Search, scrape and access 550+ data providers through one API.

    205.3K stars · TypeScript