CCG Workflow: Claude as the Orchestrator for Codex, Gemini, and Other Model Teams
A multi-model collaboration workflow engine: one command, /ccg:go, and the AI automatically analyzes intent, picks a strategy, and orchestrates Codex, Gemini and Claude to work together.
At a glance
- What is it?
- CCG is a Go-bridged workflow engine that keeps Claude Code in charge while dispatching tasks to Codex, Grok, Kimi, and Antigravity. It targets developers who want multi-model collaboration without leaving their Claude terminal.
- Who is it for?
- Adopt CCG if you live inside Claude Code and want parallel model analysis or review without switching terminals. It suits teams already paying for multiple model APIs.
- Can I use it commercially?
- Yes. MIT is a permissive licence: you can use, modify and sell software built on it, as long as you keep its copyright and licence notices.
- Is it still maintained?
- Yes. The repository last received commits 13 days ago.
- What is it written in?
- Mainly Go, according to GitHub's language statistics.
Answers come from the project's GitHub data, last synced on November 15, 2026, and from our analysis. They are not legal advice.
Star history
- fengshao1227/ccg-workflow5,984 ★ · +103
| Repository | 2026-09-10 | 2026-11-15 |
|---|---|---|
| fengshao1227/ccg-workflow | 5.9k | 6k |
103 Stars in the last 66 days, measured from the daily GitHub snapshot. Compare with other projects
Editorial analysis
The Problem: One Model Is Not Enough, but Managing Many Is a Mess
The repository is written in Go, with a Node.js wrapper for installation. It is open source under the MIT license, so you can modify the bridge or the engine. The author also runs a related plugin directory called DSH Marketplace, which is a separate effort. That context matters because it shows the author cares about tool discoverability, but it is not part of CCG itself.
Architecture: Claude Leads, a Go Binary Bridges the Rest
Claude Code stays the coordinator, and external workers run through the existing wrapper, codeagent-wrapper, which is published as pre-built binaries. On DeepSeek Harness the same role matrix runs natively with no binary bridge, and every ccg_team hire asks you to approve it first.
Installation and First Run: One Command, Then a Menu
If you are not using DeepSeek Harness, you can ignore that part. But the existence of a dsh subcommand suggests the project is actively maintained for that environment. The Go binary codeagent-wrapper is distributed as pre-built binaries, per the release named 'preset'. That means you do not compile Go yourself; you download a binary. That is convenient but raises a question about platform coverage. Verify that a binary exists for your OS before relying on it.
DeepSeek Harness Integration: Model Panels and Live Teammates
The README claims these features are things the Claude Code side cannot do as cleanly. It says there is no external CLI, no binary bridge, no cold-start tax; every hop is a provider API request. In DeepSeek Harness, the integration is native, so it avoids the overhead of spawning a separate process. For a user evaluating CCG, this section matters because it shows the project is not just a Claude Code plugin; it is a broader orchestration concept that adapts to different hosts.
The Workflow in Practice: From Intent to Task File to Hard Stop
One notable detail is the classification step. The engine does not just pass your request to a model; it analyzes intent before choosing a strategy. That is a form of meta-reasoning that adds latency but can prevent overspending on trivial tasks.
Limitations and Wrong Use Cases: Not a Replacement for a Single Model
A wrong use case is a simple task that a single model can handle in one shot. If you just want to rename a variable or fix a typo, the overhead of intent analysis and multi-model orchestration is overkill. Another wrong case is a team that lacks API keys for the external models. CCG depends on Codex, Gemini, and others being reachable. For pure Claude setups, the README says model-action Hooks use native Agents instead, so the multi-model part is absent.
Alternatives: Direct Multi-Agent Frameworks vs. CCG's Claude-Centric Approach
The README also mentions DeepSeek Harness as a host. If you are already in that environment, CCG's native integration may be more efficient than a generic framework that requires a separate bridge. But for a developer outside Claude Code and DeepSeek Harness, a framework like CrewAI might be more portable.
Maintenance and Upgrade Cost: What the Material Shows
The license is MIT, which allows commercial use and modification without copyleft obligations. That is a permissive license, so you can embed the workflow engine in your own tools as long as you preserve the copyright notice. The repository includes CONTRIBUTING.md, CODE_OF_CONDUCT.md and SECURITY.md, and package.json names "CCG Contributors" as author. For a production dependency, you should check the issue tracker and commit history on GitHub to gauge responsiveness. The README includes a badge for DeepWiki and a sponsor section, which indicates community interest, but those are not quality metrics.
Editorial conclusion
Adopt CCG if you live inside Claude Code and want parallel model analysis or review without switching terminals. It suits teams already paying for multiple model APIs. Skip it if you prefer a single-model workflow or if your organization blocks external model calls. Before adopting, verify that the Go binary bridge works on your OS and that your API keys for Codex, Gemini, and others are valid.
Frequently asked questions
What is ccg-workflow and who is it for?
It is an MIT licensed workflow engine for Claude Code, version 3.7.4, requiring Node 20 or newer and installed with npx ccg-workflow. It keeps Claude Code as the lead orchestrator and dispatches specialised work to Codex, Grok, Kimi Code and Antigravity through a compiled Go binary bridge called codeagent-wrapper.
Which strategy does ccg-workflow pick for a small change?
/ccg:go analyzes the intent of the request and picks a strategy automatically, then orchestrates Codex, Gemini and Claude to work together.
Does ccg-workflow edit files before I approve the plan?
The repository description says /ccg:go analyzes intent, picks a strategy and orchestrates the models. On the DeepSeek Harness side, every ccg_team hire asks you to approve it first.
How does ccg-workflow keep state after the conversation is compacted?
CCG registers Hooks, and `npx ccg-workflow doctor --json` validates those Hook registrations along with the selected backends and managed skills.
What is the difference between the ccg-workflow binary and the npm package?
They are separate artifacts. The bridge to external models is a compiled Go binary, codeagent-wrapper, released as pre-built binaries rather than as a versioned npm release, while the npm package is ccg-workflow version 3.7.4. The binary release landed on 2026-11-02, which is also the last push to main.
Can ccg-workflow run outside Claude Code?
Yes, through a separate path inside DeepSeek Harness that ships inside the same package, installed with npx ccg-workflow dsh install and inspected with dsh list. That side offers model panels that render several models answering the same brief side by side, and ccg_team live teammates that stay alive across turns and refuse a hire whose files would collide.
Official sources
Where developers are discussing it
Posts on Hacker News, dev.to and Lobsters that link to this repository, found by our scan of those communities. 0 in the last 30 days; newest first.
- Should I Go Out? A Local Gemma Agent That Picks One Outdoor Plan, Then Tells You to Put Your Phone Awaydev.to · Oct 9, 2026 · 3 points · 2 comments
Add this badge to your README
If you maintain this project, the badge below links readers to this analysis and shows its maintenance status from the daily GitHub snapshot. Paste the markdown into your README; add ?metric=license or ?metric=stars to the image URL for a different field.
[](https://hysenlabs.com/projects/fengshao1227-ccg-workflow)Star history chart for your README
[](https://hysenlabs.com/projects/fengshao1227-ccg-workflow)Was this useful?