From 8bcbd3dc8bcd61f11775f628493879fb76124fc2 Mon Sep 17 00:00:00 2001 From: Fahad Date: Thu, 12 Jun 2025 15:29:21 +0400 Subject: [PATCH 1/4] Updated readme --- README.md | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 3d54a2b..a741329 100644 --- a/README.md +++ b/README.md @@ -16,14 +16,15 @@ task and let it orchestrate between models automatically. Claude stays in contro but gets perspectives from the best AI for each subtask. Claude can switch between different tools _and_ models mid-conversation, with context carrying forward seamlessly. -**Example Workflow:** -1. Claude uses Gemini Pro to deeply [`analyze`](#6-analyze---smart-file-analysis) the code in question -2. Switches to O3 to continue [`chatting`](#1-chat---general-development-chat--collaborative-thinking) about its findings -3. Uses Flash to validate formatting suggestions from O3 -4. Performs the actual work after taking in feedback from all three -5. Returns to Pro for a [`precommit`](#4-precommit---pre-commit-validation) review +**Example Workflow - Claude Code:** +1. Performs its own reasoning +2. Uses Gemini Pro to deeply [`analyze`](#6-analyze---smart-file-analysis) the code in question for a second opinion +3. Switches to O3 to continue [`chatting`](#1-chat---general-development-chat--collaborative-thinking) about its findings +4. Uses Flash to evaluate formatting suggestions from O3 +5. Performs the actual work after taking in feedback from all three +6. Returns to Pro for a [`precommit`](#4-precommit---pre-commit-validation) review -All within a single conversation thread! Gemini Pro in step 5 _knows_ what was recommended by O3 in step 2! Taking that context +All within a single conversation thread! Gemini Pro in step 6 _knows_ what was recommended by O3 in step 3! Taking that context and review into consideration to aid with its pre-commit review. **Think of it as Claude Code _for_ Claude Code.** @@ -212,6 +213,11 @@ Just ask Claude naturally: - "Think deeply about this and get o3 to debug this logic error I found in the checkOrders() function" → Uses O3 specifically - "Brainstorm scaling strategies with pro. Study the code, pick your preferred strategy and debate with pro to settle on two best approaches" → Uses Gemini Pro specifically +> **Remember:** Claude remains in control — but **you** are the true orchestrator. +> You're the prompter, the guide, the signal. +> Your prompt decides when Claude brings in Gemini, Flash, O3 — or handles it solo. +> This MCP isn't magic. It's just **super-glue**. + ## Available Tools **Quick Tool Selection Guide:** From ce22d58def9f9cbc62a472d7f83fe5d841a41952 Mon Sep 17 00:00:00 2001 From: Fahad Date: Thu, 12 Jun 2025 15:30:00 +0400 Subject: [PATCH 2/4] Updated readme --- README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/README.md b/README.md index a741329..a4ac94e 100644 --- a/README.md +++ b/README.md @@ -27,7 +27,7 @@ with context carrying forward seamlessly. All within a single conversation thread! Gemini Pro in step 6 _knows_ what was recommended by O3 in step 3! Taking that context and review into consideration to aid with its pre-commit review. -**Think of it as Claude Code _for_ Claude Code.** +**Think of it as Claude Code _for_ Claude Code.** This MCP isn't magic. It's just **super-glue**. ## Quick Navigation @@ -216,7 +216,6 @@ Just ask Claude naturally: > **Remember:** Claude remains in control — but **you** are the true orchestrator. > You're the prompter, the guide, the signal. > Your prompt decides when Claude brings in Gemini, Flash, O3 — or handles it solo. -> This MCP isn't magic. It's just **super-glue**. ## Available Tools From d4a054053ce61802358ed812e720a2f115883ad7 Mon Sep 17 00:00:00 2001 From: Beehive Innovations Date: Thu, 12 Jun 2025 15:35:34 +0400 Subject: [PATCH 3/4] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index a4ac94e..9b52768 100644 --- a/README.md +++ b/README.md @@ -214,8 +214,8 @@ Just ask Claude naturally: - "Brainstorm scaling strategies with pro. Study the code, pick your preferred strategy and debate with pro to settle on two best approaches" → Uses Gemini Pro specifically > **Remember:** Claude remains in control — but **you** are the true orchestrator. -> You're the prompter, the guide, the signal. -> Your prompt decides when Claude brings in Gemini, Flash, O3 — or handles it solo. +> You're the prompter, the guide, the puppeteer. +> Your prompt decides when Claude brings in Gemini, Flash, O3 — or handles it solo. ## Available Tools From 1f90d051060601472fa74395392cc3e755bf2839 Mon Sep 17 00:00:00 2001 From: Beehive Innovations Date: Thu, 12 Jun 2025 15:45:55 +0400 Subject: [PATCH 4/4] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 9b52768..29ef0ee 100644 --- a/README.md +++ b/README.md @@ -564,7 +564,7 @@ These only apply to models that support customizing token usage for extended thi ### AI-to-AI Conversation Threading -This server enables **true AI collaboration** between Claude and multiple AI models (Gemini, O3, GPT-4o), where they can coordinate and question each other's approaches: +This server enables **true AI collaboration** between Claude and multiple AI models (Gemini, O3), where they can coordinate and question each other's approaches: **How it works:** - **Gemini can ask Claude follow-up questions** to clarify requirements or gather more context @@ -946,4 +946,4 @@ Built with the power of **Multi-Model AI** collaboration 🤝 - [MCP (Model Context Protocol)](https://modelcontextprotocol.com) by Anthropic - [Claude Code](https://claude.ai/code) - Your AI coding assistant & orchestrator - [Gemini 2.5 Pro & 2.0 Flash](https://ai.google.dev/) - Extended thinking & fast analysis -- [OpenAI O3 & GPT-4o](https://openai.com/) - Strong reasoning & general intelligence +- [OpenAI O3](https://openai.com/) - Strong reasoning & general intelligence