cc-fleet
Enables teams to leverage multiple vendor LLMs within Claude's native agent framework, reducing dependency on single-model constraints and optimizing cost-to…
Spawns third-party LLMs — DeepSeek, GLM, Qwen, Kimi, MiniMax, and others — as Claude Code teammates or one-shot subagents, so Claude Code can route work to any vendor model.
- Ask Claude to spawn DeepSeek or Qwen models as teammates for parallel code review tasks.
- Generate multi-model agent teams combining Claude with specialized LLMs for complex architecture decisions.
- Automate one-shot coding tasks by routing specific requests to the most cost-effective vendor model.
Enables teams to leverage multiple vendor LLMs within Claude's native agent framework, reducing dependency on single-model constraints and optimizing cost-to-capability tradeoffs for large-scale development workflows.
Engineering teams managing multi-model LLM deployments seeking vendor flexibility and cost optimization in AI-assisted code generation.
https://github.com/ethanhq/cc-fleet
By ethanhq
How to Get It
claude plugins install ethanhq/cc-fleet
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Spawn DeepSeek or Qwen models as teammates for parallel code review tasks
Trust Signals Auto-scanned
Community Pulse Emerging
Discussed on Hacker News
- Show HN: Cc-fleet – run other LLMs as Claude Code workers, your sub drives — Hacker News · 4 pts
- Show HN: Cc-fleet – run other LLMs as Claude Code workers, your sub drives — Hacker News · 3 pts
2 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 110 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 110 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.