How TachiBot thinks.
From intent to a verified answer: how routing, planning, deliberation and verification fit together — and what happens on every single tool call.
Smart Routing & tachi
The tachi auto-router reads intent from your query, picks a mode, and assembles the right tool chain — so you never have to memorize 51 tool names.
The Planner Pipeline
planner_maker runs a 5-stage council — each step handled by a different model — then planner_runner executes the plan against goal-oriented verification gates that catch drift early.
planner_maker is a coordinator: instead of one model writing the whole plan, it returns one tool at a time and routes each stage to the model that's best at it. A single model would carry its own blind spots through every step; a relay lets a fresh perspective correct the previous one.
How Seven Minds Think Together
A structured reasoning pipeline — ground in data, decompose, explore alternatives, stress test for holes, then judge.
Search real-time data from 4 providers. No thinking starts without facts.
Decompose into atomic parts. Map dependencies, constraints, and execution order.
Generate alternative approaches from different training data and perspectives.
Attack assumptions. Find holes, blind spots, and failure modes in every path.
Synthesize the best elements from every model. Resolve conflicts. Score everything. Not 10? Here's why — and how to fix it.
Each model was chosen for a specific strength. Different training data, different benchmarks, different blind spots.
5 Models. One Answer.
Real GPT-5 → GPT-5.5 migration analysis, ~3 minutes
"Should I migrate from GPT-5 to GPT-5.5? Differences, breaking changes, migration steps."
GPT-5.5 released Nov 12 — automatic migration, backward compatible
2 modes, 8 personalities, 25% better coding, 15% better factuality
No breaking changes — backward compatible until Q1 2026
30% latency reduction, 10% fewer hallucinations
Low-risk upgrade — enable in staging, test 1 week, then production
Six profiles
Load only the tools you need. Set TACHIBOT_PROFILE to scale the surface from a lean 12 to the full 51.
Core reasoning, one strong model per job.
The full coding & analysis suite.
Search, research & multi-source synthesis.
All major tools across every capability.
Code, testing, architecture & decomposition.
Everything enabled — maximum capability (default).
How a tool call flows
From your prompt to a frontier model and back, every request passes through the same six layers. The request flows down; the answer streams back up.
Who parses “ask grok & perplexity, then let gemini judge”?
How it holds together
Registry-driven, SOLID, and obsessive about token economy.
Auto-routing dispatcher
tachi + focus read intent and orchestrate the right tools, modes and models for you.
Provider & mode registries
ModelProviderRegistry maps 40+ aliases to tools; FocusModeRegistry adds reasoning modes without touching the core (OCP).
One tool per step
The planner returns a single nextTool at a time — fully user-interruptible, with visible progress.
Distillation discipline
2.5k chars between steps, 6k for synthesis, truncated on clean boundaries — beating lost-in-the-middle recall loss.
YAML state machine
Variable interpolation, dependency resolution, parallel steps, retries and live manifest artifacts.
Cost & usage aware
Every call wrapped by safeAddTool() — token tracking, validation, heartbeat to keep MCP alive.
tachi vs focus
Both orchestrate many models — they differ in how much you decide. One picks the tools for you; the other hands you the controls.
The concierge
Describe the goal in plain language. tachi reads your intent, picks the right task mode, and runs a pre-baked tool chain — zero config.
- →Auto-routes by keyword priority (ties resolve to the higher-stakes mode)
- →Each mode is an outcome recipe — generate, then verify
- →One-shot & stateless — returns the answer plus what it ran
› tachi "debug this null-pointer error"› tachi "microservices vs monolith for 10M users"› tachi "which is best — React, Vue or Svelte?"The cockpit
You pick the reasoning strategy and the panel. focus runs a controlled, multi-round deliberation exactly the way you specify.
- →You choose a process mode — how the models think together
- →Knobs: domain · rounds · models · temperature · ping-pong style
- →Multi-round & stateful — sessions resume via continue_focus
› /focus architecture-debate Redis vs Memcached› /focus research React 19 new features› /focus deep-reasoning scale to 10k connections| tachi | focus | |
|---|---|---|
| You provide | a query | a query + a chosen mode |
| Picks the mode | automatically (intent routing) | you do, explicitly |
| Mode type | task outcomes — solve, judge… | reasoning processes — debate, deep… |
| Rounds | one-shot recipe | multi-round (default 5), ping-pong |
| Config knobs | almost none | domain · rounds · models · temp · style |
| State | stateless | session-based, resumable |
| Reach for it when | “just handle this — pick the tools” | “reason this way, with these models” |
Built in public. Actively maintained.
TachiBot is open source and actively maintained — new releases ship regularly. If it helps your workflow, a star helps others find it.
