Developer Tools●●Solid
Phone a Friend for Claude Code – GPT, Gemini, DeepSeek via MCP
Claude debates GPT and Gemini in parallel rounds; costs $0.02–0.05 per brainstorm.
Crowd PleaserShip It
spranab
103mo ago
Back to browse
GitHub Repository
Any agent as native Claude Code teammates. Codex, Gemini, Kimi today. GLM, DeepSeek next.
15 starsPython
I made Codex work as a Claude Code teammate
by rosadoft·Apr 24, 2026·3 points·2 comments
AI Analysis
●●●BangerWizardrySolve My ProblemZero to One
Speaks Claude Code's native agent protocol, not a chat wrapper around external APIs.
Strengths
- •Protocol-level integration with mailbox I/O, atomic task claims, and idle notifications
- •Mid-task reactivity via Codex's turn/steer App Server call for in-flight message injection
- •202 passing tests with clean npx install and uv-based Python tool management
Weaknesses
- •Currently only supports Codex, with Gemini and others on the roadmap but not yet available
- •Requires Claude Code subscription, limiting the addressable user base
Category
Target Audience
Developers using Claude Code who want multi-model agent teams
Similar To
Claude Code · Continue · Cline
Similar Projects
Developer Tools●Mid
Metateam: run many Claude/Codex/Gemini CLI instances in one terminal UI
Runs Claude/Codex/Gemini side-by-side with persistent memory, but embedding CLI tools in Rust is table stakes.
Bold Bet
falsename
323mo ago
Developer Tools●Mid
DevSquad – Claude Code Plugin That Works with to Gemini CLI and Codex
Hook-enforced multi-model delegation, but still early and depends on unstable AI API availability.
Ship It
dikshantjoshi
113mo ago
AI/ML●●Solid
Cc-fleet – run other LLMs as Claude Code workers, your sub drives
Swaps LLM backends for Claude Code workers while keeping your main session auth untouched.
Big BrainSolve My Problem
ethanhq
441d ago
AI/ML●●●Banger
Myco – coordinate Claude and DeepSeek and other LLMs in one agent swarm
Mycelium-style bus lets parallel Claude sessions share context without a central orchestrator.
Big BrainZero to One
cezarvil
201mo ago
AI/ML●●●Banger
Council – Run Claude, Codex and Gemini against the same prompt
Surfaces model disagreements instead of averaging them away — that's the real value.
Big BrainSolve My Problem
colinarms
201mo ago