This product was not featured by Product Hunt yet.
It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).

Product Thumbnail

cc-fleet

Any model as a real Claude Code teammate — no sub

Open Source
Developer Tools
Artificial Intelligence
GitHub
Visit WebsiteSee on Product HuntGithub

Hunted byEthanEthan

Claude Code's Dynamic Workflows, Agent Teams & Subagents only run Anthropic's models. cc-fleet lets any model with an Anthropic- or OpenAI-compatible API — DeepSeek, GLM, Kimi, Qwen, even your Codex subscription — run as a real Claude Code worker, mixed per node in one run. No Anthropic subscription needed; provider keys never touch env, argv, or shell history. Go CLI + Claude Code plugin. Apache-2.0.

Top comment

Hi Product Hunt 👋 I'm Ethan, the maker of cc-fleet. I love Claude Code's multi-agent features — Workflows, Agent Teams, Subagents —but they only run Anthropic's own models. I kept wanting to hand the cheap/bulk work to DeepSeek, GLM, Kimi or Qwen (and reuse my Codex subscription) without giving up the Claude Code experience. cc-fleet does exactly that: each third-party worker is a real `claude` process with its model backend swapped, so Claude Code drives it like a native agent. You can mix providers per node in one workflow, and your main session's own login is never touched — provider keys never enter env, argv, or shell history. Open source (Apache-2.0), runs on Linux/macOS/Windows, installs in two steps. Heads-up so nobody's surprised: cc-fleet drives the official Claude Code CLI, so you need Claude Code + a terminal; the tmux "agent team" lane is macOS/Linux only. It's early (v0.2.x) and I'd genuinely love your brutal feedback — especially on provider compatibility and the workflow API. AMA!

Comment highlights

No comment highlights available yet. Please check back later!

About cc-fleet on Product Hunt

Any model as a real Claude Code teammate — no sub

cc-fleet was submitted on Product Hunt and earned 4 upvotes and 1 comments, placing #160 on the daily leaderboard. Claude Code's Dynamic Workflows, Agent Teams & Subagents only run Anthropic's models. cc-fleet lets any model with an Anthropic- or OpenAI-compatible API — DeepSeek, GLM, Kimi, Qwen, even your Codex subscription — run as a real Claude Code worker, mixed per node in one run. No Anthropic subscription needed; provider keys never touch env, argv, or shell history. Go CLI + Claude Code plugin. Apache-2.0.

cc-fleet was featured in Open Source (68.6k followers), Developer Tools (515.4k followers), Artificial Intelligence (473.1k followers) and GitHub (41.3k followers) on Product Hunt. Together, these topics include over 218.1k products, making this a competitive space to launch in.

Who hunted cc-fleet?

cc-fleet was hunted by Ethan. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.

Want to see how cc-fleet stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.