Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures which models earn their seat.
How to install deliberation?
antonbabenko/deliberation
$git clone https://github.com/antonbabenko/deliberationInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install deliberation by running `git clone https://github.com/antonbabenko/deliberation`, then use it for the current task and follow its documentation at https://github.com/antonbabenko/deliberation.
README.md
| 1 | # Deliberation |
| 2 | |
| 3 | Get a second opinion in Claude Code from GPT, Gemini, and Grok - plus 400+ more models through OpenRouter, including Qwen, Kimi, and DeepSeek. Seven domain experts (Architect, Code Reviewer, Security Analyst, and four more) review your plans, find bugs, and debate edge cases until they agree. |
| 4 | |
| 5 | <br>Recent blog post: [Meet Deliberation: 400+ models is easy, knowing which ones earn a place is hard.](https://builder.aws.com/content/3Eaq94hQW8HywInrVaQm9qNih1P/meet-deliberation-400-models-is-easy-knowing-which-ones-earn-a-place-is-hard) |
| 6 | |
| 7 | <details> |
| 8 | <summary>📸 See a full <code>/consensus</code> run: round 1 disagreement to round 5 convergence</summary> |
| 9 | |
| 10 |  |
| 11 | |
| 12 | <details> |
| 13 | <summary>... a few moments later ...</summary> |
| 14 | |
| 15 |  |
| 16 | |
| 17 | </details> |
| 18 | |
| 19 |  |
| 20 | |
| 21 | </details> |
| 22 | |
| 23 | <details> |
| 24 | <summary>📸 See <code>/ask-all</code> stage a 2-round architect debate: three models, three verdicts, then each critiques the others - disagreement matrix included</summary> |
| 25 | |
| 26 |  |
| 27 | |
| 28 | When three models argue, the real bug reveals itself. Round 1 = independent top findings. Round 2 = each model dunks on the others' picks. The disagreement matrix shows where they diverge; the conclusion shows what to actually fix first. |
| 29 | |
| 30 | </details> |
| 31 | |
| 32 | ## What is Deliberation? |
| 33 | |
| 34 | Claude can ask GPT, Gemini, Grok, or any OpenAI-compatible model (via OpenRouter) for help |
| 35 | through MCP. The plugin handles the wiring for each provider so you just write the prompt. |
| 36 | Each expert has a distinct specialty and can advise or implement. |
| 37 | |
| 38 | You can use any subset of the providers. The plugin detects which are configured and routes |
| 39 | accordingly. OpenRouter is advisory-only and config-driven: models are declared in |
| 40 | `~/.config/deliberation/config.json` (Windows: `%APPDATA%\deliberation\config.json`; override |
| 41 | with `DELIBERATION_CONFIG`) and hot-reload without restarting Claude Code. |
| 42 | |
| 43 | | What you get | Why it matters | |
| 44 | |--------------|----------------| |
| 45 | | 7 domain experts | The right specialist for each problem type | |
| 46 | | GPT, Gemini, Grok, or OpenRouter models | Use your preferred provider(s) | |
| 47 | | Dual mode | Experts analyze (read-only) or implement (write) | |
| 48 | | Auto-routing | Claude detects when to delegate from your request | |
| 49 | | Synthesized responses | Claude interprets expert output, never raw passthrough | |
| 50 | |
| 51 | ## Install |
| 52 | |
| 53 | ### Claude Code plugin (recommended): |
| 54 | |
| 55 | **1. Add the marketplace - [antonbabenko/agent-plugins](https://github.com/antonbabenko/agent-plugins)** |
| 56 | ``` |
| 57 | /plugin marketplace add antonbabenko/agent-plugins |
| 58 | ``` |
| 59 | |
| 60 | **2. Install the plugin** |
| 61 | ``` |
| 62 | /plugin install deliberation@antonbabenko |
| 63 | ``` |
| 64 | |
| 65 | **3. Run setup** |
| 66 | ``` |
| 67 | /deliberation:setup |
| 68 | ``` |
| 69 | |
| 70 | Claude now routes complex tasks to your GPT, Gemini, Grok, and OpenRouter experts (Grok and OpenRouter advise; GPT and Gemini can also implement). |
| 71 | |
| 72 | > **Setup is a one-time step.** The MCP servers are registered by the plugin manifest, so they load |
| 73 | > automatically and stay current across updates. |
| 74 | |
| 75 | ### Updating (Claude Code) |
| 76 | |
| 77 | ``` |
| 78 | /plugin marketplace update antonbabenko # pull the new version from the marketplace |
| 79 | /reload-plugins # reconnect the MCP servers (or just restart Claude Code) |
| 80 | ``` |
| 81 | |
| 82 | **Updating on non-Claude hosts:** hosts that run the standalone server via `npx -y |
| 83 | @antonbabenko/deliberation-mcp` get the latest published version on each fresh resolve. `npx` |
| 84 | caches resolved packages, so if a host serves an old build, clear the npx cache |
| 85 | (`rm -rf ~/.npm/_npx`) or pin/refresh the version. |
| 86 | |
| 87 | ### Alternative: Use `deliberation` MCP server (standalone, works with any agents) |
| 88 | |
| 89 | The orchestration server is also published on its own - npm [`@antonbabenko/deliberation-mcp`](https://www.npmjs.com/package/@antonbabenko/deliberation-mcp), Official MCP Registry name `io.github.antonbabenko/deliberation`. |
| 90 | |
| 91 | **One-click install:** |
| 92 | |
| 93 | [](https://cursor.com/en-US/install-mcp?name=deliberation&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBhbnRvbmJhYmVua28vZGVsaWJlcmF0aW9uLW1jcCJdfQ==) [](https://insiders.vscode.dev/redirect/mcp/install?name=deliberation&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40antonbabenko%2Fdeliberation-mcp%22%5D%7D) [](https://kiro.dev/launch/mcp/add?name=deliberation&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40antonbabenko%2Fdeliberation-mcp%22%5D%7D) |
| 94 | |
| 95 | <details> |
| 96 | <summary>Manual config for any MCP clients</summary> |
| 97 | |
| 98 | Add this to your h |
Related
6 picksType
- code-review-graphLocal-first knowledge graph for token-efficient code review through MCP and CLIJul 2026
- repowiseCodebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.Jul 2026
- mcp-server-atlassian-bitbucketNode.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.Mar 2026
- gemini-mcp-toolMCP server for Gemini CLI integrationJul 2026
- socraticodeEnterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra…Jul 2026
- github-mcpProduction-ready Model Context Protocol server providing Claude with complete GitHub integration - comprehensive tools for repository management, branch operations, file handling, issue tracking, and collaboration features with OAuth 2.0 authentication and MongoDB persistence.Jun 2026
