io.github.byPawel/tachibot-mcp
Multi-model AI orchestration with 31 tools, YAML workflows, and 5 token-optimized profiles.
Ask AI about io.github.byPawel/tachibot-mcp
Powered by Claude Β· Grounded in docs
I know everything about io.github.byPawel/tachibot-mcp. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
TachiBot MCP
Multi-Model AI Orchestration Platform
51 AI tools. 7 providers. One protocol.
Orchestrate Perplexity, Grok, GPT-5, Gemini, Qwen, Kimi K2.5, and MiniMax M2.5 from Claude Code, Claude Desktop, Cursor, or any MCP client.
Get Started Β· View Tools Β· Documentation
If TachiBot helps your workflow, a star goes a long way.
What's New in v2.15.0
/blueprint Skill β Multi-Model Implementation Planning
New skill that creates bite-sized TDD implementation plans using a 7-step multi-model council:
/blueprint add OAuth with refresh tokens
Pipeline: Grok search β Qwen+Kimi analysis β Kimi decompose β GPT pre-mortem critique β Gemini final judgment β bite-sized TDD output (exact files, test-first steps, commit points).
Bridges planner_maker's multi-model intelligence with the writing-plans execution format.
31 Prompt Engineering Techniques (was 22)
Added 9 research-backed techniques for coding and decision-making:
| Technique | Source | Category |
|---|---|---|
reflexion | Shinn et al. 2023 | Engineering |
react (ReAct) | Yao et al. 2022 | Engineering |
rubber_duck | Hunt & Thomas 2008 | Engineering |
test_driven | Beck 2003 | Engineering |
scot (Structured CoT) | Li et al. 2025 (+13.79% HumanEval) | Structured Coding |
pre_post (Contracts) | Empirical SE 2025 | Structured Coding |
bdd_spec (Given/When/Then) | BDD 2025 | Structured Coding |
least_to_most | Zhou et al. 2022 | Research |
pre_mortem | Klein 2007 | Decision |
Techniques are embedded directly in tool system prompts for automatic application.
MiniMax M2.5 Upgrade
minimax_codeβ SWE-Bench 80.2%, per-task TECHNIQUE tags (SCoT, reflexion, rubber_duck), per-task temperaturesminimax_agentβ ReAct + least-to-most decomposition protocol, HALT criteria
Enhanced Skills
/breakdownβ now usesleast_to_mostordering +pre_mortemfailure analysis/judgeβ first judge now runs pre-mortem ("assume this FAILED")/decomposeβ deep-dives include pre/post contracts per sub-problem/promptβ auto-recommend flow with 30-intent matching guide, 13 categories
Skills (Claude Code)
TachiBot ships with 9 slash commands for Claude Code. These orchestrate the tools into powerful workflows:
| Skill | What it does | Example |
|---|---|---|
/blueprint | Multi-model planning β bite-sized TDD steps | /blueprint add OAuth with refresh tokens |
/judge | Multi-model council - parallel analysis with synthesis | /judge how to implement rate limiting |
/think | Sequential reasoning chain with any model | /think grok,gemini design a cache layer |
/focus | Mode-based reasoning (debate, research, analyze) | /focus architecture-debate Redis vs Pg |
/breakdown | Strategic decomposition with pre-mortem | /breakdown refactor payment module |
/decompose | Split into sub-problems, deep-dive each one | /decompose implement collaborative editor |
/prompt | Recommend the right thinking technique (31 available) | /prompt why do users churn |
/algo | Algorithm analysis with 3 specialized models | /algo optimize LRU cache O(1) |
/tachi | Help - see available skills, tools, key status | /tachi |
Skills automatically adapt to your configured API keys. Even with just 1-2 providers, all skills work.
Getting started? Type
/tachito see what's available.
Key Features
Multi-Model Intelligence
- 51 AI Tools across 7 providers β Perplexity, Grok, GPT-5, Gemini, Qwen, Kimi, MiniMax
- Multi-Model Council β planner_maker synthesizes plans from 5+ models into bite-sized TDD steps
- Smart Routing β Automatic model selection for optimal results
- OpenRouter Gateway β Optional single API key for all providers
Advanced Workflows
- YAML-Based Workflows β Multi-step AI processes with dependency graphs
- Prompt Engineering β 31 research-backed techniques (including SCoT, ReAct, Reflexion)
- Verification Checkpoints β 50% / 80% / 100% with automated quality scoring
- Parallel Execution β Run multiple models simultaneously
Tool Profiles
| Profile | Tools | Best For |
|---|---|---|
| Minimal | 12 | Quick tasks, low token budget |
| Research Power | 31 | Deep investigation, multi-source |
| Code Focus | 29 | Software development, SWE tasks |
| Balanced | 39 | General-purpose, mixed workflows |
| Heavy Coding (default) | 45 | Max code tools + agentic workflows |
| Full | 51 | Everything enabled |
Developer Experience
- Claude Code β First-class support
- Claude Desktop β Full integration
- Cursor β Works seamlessly
- TypeScript β Fully typed, extensible
Quick Start
Installation
npm install -g tachibot-mcp
Setup
Gateway Mode (Recommended) β 2 keys, all providers:
{
"mcpServers": {
"tachibot": {
"command": "tachibot",
"env": {
"OPENROUTER_API_KEY": "sk-or-xxx",
"PERPLEXITY_API_KEY": "pplx-xxx",
"USE_OPENROUTER_GATEWAY": "true"
}
}
}
}
Direct Mode β One key per provider:
{
"mcpServers": {
"tachibot": {
"command": "tachibot",
"env": {
"PERPLEXITY_API_KEY": "your-key",
"GROK_API_KEY": "your-key",
"OPENAI_API_KEY": "your-key",
"GOOGLE_API_KEY": "your-key",
"OPENROUTER_API_KEY": "your-key"
}
}
}
}
Get keys: OpenRouter | Perplexity
See Installation Guide for detailed instructions.
Tool Ecosystem (51 Tools)
Research & Search (6)
perplexity_ask Β· perplexity_research Β· perplexity_reason Β· grok_search Β· openai_search Β· gemini_search
Reasoning & Planning (9)
grok_reason Β· openai_reason Β· qwen_reason Β· qwq_reason Β· kimi_thinking Β· kimi_decompose Β· planner_maker Β· planner_runner Β· list_plans
Code Intelligence (8)
kimi_code Β· grok_code Β· grok_debug Β· qwen_coder Β· qwen_algo Β· qwen_competitive Β· minimax_code Β· minimax_agent
Analysis & Judgment (11)
gemini_analyze_text Β· gemini_analyze_code Β· gemini_judge Β· jury Β· gemini_brainstorm Β· openai_brainstorm Β· openai_code_review Β· openai_explain Β· grok_brainstorm Β· grok_architect Β· kimi_long_context
Meta & Orchestration (5)
think Β· nextThought Β· focus Β· tachi Β· usage_stats
Workflows (9)
workflow Β· workflow_start Β· continue_workflow Β· list_workflows Β· create_workflow Β· visualize_workflow Β· workflow_status Β· validate_workflow Β· validate_workflow_file
Prompt Engineering (3)
list_prompt_techniques Β· preview_prompt_technique Β· execute_prompt_technique
Advanced Modes (bonus)
- Challenger β Critical analysis with multi-model fact-checking
- Verifier β Multi-model consensus verification
- Scout β Hybrid intelligence gathering
Example Usage
Multi-Model Planning
// Create a plan with multi-model council
planner_maker({ task: "Build a REST API with auth and tests", mode: "start" })
// β Grok searches β Qwen analyzes β Kimi decomposes β GPT critiques β Gemini synthesizes
// Execute with checkpoints
planner_runner({ plan: planContent, mode: "step", stepNum: 1 })
// β Automatic verification at 50%, 80% (kimi_decompose), and 100%
Task Decomposition
kimi_decompose({
task: "Migrate monolith to microservices",
depth: 3,
outputFormat: "dependencies"
})
// β Structured subtasks with IDs, parallel flags, acceptance criteria
Code Review
kimi_code({
task: "review",
code: "function processPayment(amount, card) { ... }",
language: "typescript"
})
// β SWE-Bench 76.8% quality analysis
Deep Reasoning
focus({
query: "Design a scalable event-driven architecture",
mode: "deep-reasoning",
models: ["grok", "gemini", "kimi"],
rounds: 5
})
Documentation
- Full Documentation
- Installation Guide
- Configuration
- Tools Reference
- Workflows Guide
- API Keys Guide
- Focus Modes
Setup Guides
Contributing
Contributions welcome! See CONTRIBUTING.md for guidelines.
