What it does
Multi-model AI orchestration with 31 tools, YAML workflows, and 5 token-optimized profiles.
- Connects Runs on your computer
- Account or key Needs PERPLEXITY_API_KEY, GROK_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, OPENROUTER_API_KEY
- Category Developer tools
Use together with
Skills that teach the AI this kind of work; they work alongside this one
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Why it ranks here
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 19/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 12/12 | Full marks for a release or code change within 30 days |
| Still answering | 0/8 | The cloud endpoint answered at the last check |
| Usage score | 31/100 |
Quality: Passed 2/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Install
Pick the AI app you use, then copy the settings.
Let your AI install it with one sentence
Please install Tachibot MCP. Follow https://mcp.popnx.com/i/bypawel-tachibot-mcp.md, show me the commands and wait for my OK before running them.Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads
Passed 2/3 checks · Runs on your computer · ✓ Commands checked Nov 14, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Let AI install it
Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server Tachibot MCP for Claude on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "tachibot": { "command": "npx", "args": [ "-y", "tachibot-mcp" ], "env": { "PERPLEXITY_API_KEY": "your-value", "GROK_API_KEY": "your-value", "OPENAI_API_KEY": "your-value", "GOOGLE_API_KEY": "your-value", "OPENROUTER_API_KEY": "your-value" } } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For PERPLEXITY_API_KEY, GROK_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, OPENROUTER_API_KEY, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the Tachibot MCP tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Install Node.js (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
node -v- A version number such as v26.13.1 = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number:
node -vInstall once; it works for everything that needs Node.js
Sign up and create a Tachibot MCP key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
How to get a key is in the maker’s README below
Open the Claude desktop app’s settings file
SettingsDeveloperEdit Config
Paste these settings and save the file
{ "mcpServers": { "tachibot": { "command": "npx", "args": [ "-y", "tachibot-mcp" ], "env": { "PERPLEXITY_API_KEY": "your-value", "GROK_API_KEY": "your-value", "OPENAI_API_KEY": "your-value", "GOOGLE_API_KEY": "your-value", "OPENROUTER_API_KEY": "your-value" } } } }Paste the key only into the app’s field, never into a chat or to anyone
Quit Claude and open it again
Try it
Use Tachibot MCP and tell me what you can do for me, then show me one thing✓ If Claude says it is using Tachibot MCP or shows a Tachibot MCP tool in the answer, you are connected
1 optional setting(s) (works without them)
The command above works without these. Add them only if you want to change something, following the maker’s description.
TACHIBOT_PROFILETool profile selection: minimal, research_power, code_focus, balanced, or full (default: balanced)
Descriptions are as written by the maker.
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect Tachibot MCP yet
Tachibot MCP runs on your computer, but ChatGPT can only connect servers that run on the web
What you can do instead
A · Use an app that can connect Tachibot MCP
- You need a Tachibot MCP key (create it on the maker’s site) · Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
- You need a Tachibot MCP key (create it on the maker’s site) · Install Node.js on your computer first (one time)
- You need a Tachibot MCP key (create it on the maker’s site) · Install Node.js on your computer first (one time)
- You need a Tachibot MCP key (create it on the maker’s site) · Install Node.js on your computer first (one time)
B · Others in Developer tools that work with ChatGPT
Picked from the most used in the same category, only ones that connect by address with no key
- Sentry✓ ChatGPT
- Compiler Explorer✓ ChatGPT
- GitDiagram✓ ChatGPT
Works with Claude Code, with some setup first
You need a Tachibot MCP key (create it on the maker’s site) · Install Node.js on your computer first (one time)
Let AI install it
Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server Tachibot MCP for Claude Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user tachibot --env PERPLEXITY_API_KEY=your-value --env GROK_API_KEY=your-value --env OPENAI_API_KEY=your-value --env GOOGLE_API_KEY=your-value --env OPENROUTER_API_KEY=your-value -- npx -y tachibot-mcp 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For PERPLEXITY_API_KEY, GROK_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, OPENROUTER_API_KEY, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the Tachibot MCP tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Install Node.js (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
node -v- A version number such as v26.13.1 = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number:
node -vInstall once; it works for everything that needs Node.js
Sign up and create a Tachibot MCP key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
How to get a key is in the maker’s README below
Open Terminal
Mac: press Command+Space and type Terminal · Windows: open PowerShell
Paste this command and press Enter
claude mcp add --scope user tachibot --env PERPLEXITY_API_KEY=your-value --env GROK_API_KEY=your-value --env OPENAI_API_KEY=your-value --env GOOGLE_API_KEY=your-value --env OPENROUTER_API_KEY=your-value -- npx -y tachibot-mcpReplace “your-value” with your key before pressing Enter
Paste the key only into the app’s field, never into a chat or to anyone
Type /mcp in Claude Code
You should see Tachibot MCP listed as connected
Try it
Use Tachibot MCP and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using Tachibot MCP or shows a Tachibot MCP tool in the answer, you are connected
1 optional setting(s) (works without them)
The command above works without these. Add them only if you want to change something, following the maker’s description.
TACHIBOT_PROFILETool profile selection: minimal, research_power, code_focus, balanced, or full (default: balanced)
Descriptions are as written by the maker.
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor, with some setup first
You need a Tachibot MCP key (create it on the maker’s site) · Install Node.js on your computer first (one time)
Let AI install it
Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server Tachibot MCP for Cursor on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "tachibot": { "command": "npx", "args": [ "-y", "tachibot-mcp" ], "env": { "PERPLEXITY_API_KEY": "your-value", "GROK_API_KEY": "your-value", "OPENAI_API_KEY": "your-value", "GOOGLE_API_KEY": "your-value", "OPENROUTER_API_KEY": "your-value" } } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For PERPLEXITY_API_KEY, GROK_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, OPENROUTER_API_KEY, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the Tachibot MCP tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Install Node.js (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
node -v- A version number such as v26.13.1 = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number:
node -vInstall once; it works for everything that needs Node.js
Sign up and create a Tachibot MCP key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
How to get a key is in the maker’s README below
Fill in your key
In the Tachibot MCP settings, PERPLEXITY_API_KEY, GROK_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, OPENROUTER_API_KEY is empty; add your key and save
Paste the key only into the app’s field, never into a chat or to anyone
Open the AI chat in Cursor in Agent mode
Try it
Use Tachibot MCP and tell me what you can do for me, then show me one thing✓ If Cursor says it is using Tachibot MCP or shows a Tachibot MCP tool in the answer, you are connected
1 optional setting(s) (works without them)
The command above works without these. Add them only if you want to change something, following the maker’s description.
TACHIBOT_PROFILETool profile selection: minimal, research_power, code_focus, balanced, or full (default: balanced)
Descriptions are as written by the maker.
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code, with some setup first
You need a Tachibot MCP key (create it on the maker’s site) · Install Node.js on your computer first (one time)
Let AI install it
Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server Tachibot MCP for VS Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "tachibot": { "type": "stdio", "command": "npx", "args": [ "-y", "tachibot-mcp" ], "env": { "PERPLEXITY_API_KEY": "your-value", "GROK_API_KEY": "your-value", "OPENAI_API_KEY": "your-value", "GOOGLE_API_KEY": "your-value", "OPENROUTER_API_KEY": "your-value" } } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For PERPLEXITY_API_KEY, GROK_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, OPENROUTER_API_KEY, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the Tachibot MCP tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Install Node.js (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
node -v- A version number such as v26.13.1 = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number:
node -vInstall once; it works for everything that needs Node.js
Sign up and create a Tachibot MCP key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
How to get a key is in the maker’s README below
Fill in your key
In the Tachibot MCP settings, PERPLEXITY_API_KEY, GROK_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, OPENROUTER_API_KEY is empty; add your key and save
Paste the key only into the app’s field, never into a chat or to anyone
Open the AI chat in VS Code in Agent mode
Try it
Use Tachibot MCP and tell me what you can do for me, then show me one thing✓ If VS Code says it is using Tachibot MCP or shows a Tachibot MCP tool in the answer, you are connected
1 optional setting(s) (works without them)
The command above works without these. Add them only if you want to change something, following the maker’s description.
TACHIBOT_PROFILETool profile selection: minimal, research_power, code_focus, balanced, or full (default: balanced)
Descriptions are as written by the maker.
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
JSON settings are under “For developers” below
For developers: Terminal commands and JSON settings
Installed on your computer
Claude Code
claude mcp add --scope user tachibot --env PERPLEXITY_API_KEY=your-value --env GROK_API_KEY=your-value --env OPENAI_API_KEY=your-value --env GOOGLE_API_KEY=your-value --env OPENROUTER_API_KEY=your-value -- npx -y tachibot-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"tachibot": {
"command": "npx",
"args": [
"-y",
"tachibot-mcp"
],
"env": {
"PERPLEXITY_API_KEY": "your-value",
"GROK_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value",
"GOOGLE_API_KEY": "your-value",
"OPENROUTER_API_KEY": "your-value"
}
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"tachibot": {
"command": "npx",
"args": [
"-y",
"tachibot-mcp"
],
"env": {
"PERPLEXITY_API_KEY": "your-value",
"GROK_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value",
"GOOGLE_API_KEY": "your-value",
"OPENROUTER_API_KEY": "your-value"
}
}
}
}VS Code (mcp.json)
{
"servers": {
"tachibot": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tachibot-mcp"
],
"env": {
"PERPLEXITY_API_KEY": "your-value",
"GROK_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value",
"GOOGLE_API_KEY": "your-value",
"OPENROUTER_API_KEY": "your-value"
}
}
}
}Values you fill in
PERPLEXITY_API_KEYsecret required envPerplexity API key for web search, research, and reasoning (https://www.perplexity.ai/settings/api)GROK_API_KEYsecret required envGrok/xAI API key for code analysis, debugging, and architecture (https://console.x.ai/)OPENAI_API_KEYsecret required envOpenAI API key for GPT-5 analysis and comparison (https://platform.openai.com/api-keys)GOOGLE_API_KEYsecret required envGoogle Gemini API key for brainstorming and code/text analysis (https://aistudio.google.com/apikey)OPENROUTER_API_KEYsecret required envOpenRouter API key for Qwen3 Coder and other modelsTACHIBOT_PROFILEenvTool profile selection: minimal, research_power, code_focus, balanced, or full (default: balanced)
Descriptions are as written by the maker.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
At a glance
Which apps can use it
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Related guides
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account byPawel, which owns the repo
- ✓ Pass
Still maintained
Code last changed 27 days ago
- ! Caution
Has a licence
GitHub could not identify the licence type; open the file to check
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Published vulnerabilities (OSV.dev)
No entries on OSV.dev for tachibot-mcp@2.0.5
Checks only this package version, not every dependency · checked Nov 15, 2026
Makers: ask for a re-check or report wrong info
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/bypawel-tachibot-mcp)Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
User reviews
No reviews yet
Compared with others in Developer toolsi
- More stars than 91% of the other 6182 servers in this category
- Published to the registry more recently than 0% of the other 6182 servers in this category
- Basic checks equal to or better than 45% of the other 6182 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Tachibot MCP safe?
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
You need to fill in: PERPLEXITY_API_KEY, GROK_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, OPENROUTER_API_KEY
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed 27 days ago, and the latest version (2.0.5) reached the registry 12 months ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
What can I use instead?
In the same category: GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
Similar alternatives
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Appllama
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Cloudflare MCP
Cloudflare MCP servers
Omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Repowise
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| This one Tachibot MCP | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| Runs where | Installs on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Cloud or install on your computer |
| Needs a key | Yes | No | No | No | No | No |
| Add with + in Claude | No | No | No | Yes | No | No |
| Basic checks | 2/3 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| License | NOASSERTION | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
TachiBot MCP
Multi-Model AI Orchestration Platform
67 AI tools. 11 providers. One protocol.
Orchestrate Perplexity, Grok 4.6, GPT-6 Astra, Gemini, Qwen, Kimi K3, and MiniMax M3 from Claude Code, Claude Desktop, Cursor, or any MCP client.
Get Started · View Tools · Documentation
If TachiBot helps your workflow, a star goes a long way.
What's New
v2.35.1
- The planner's code analysis runs on DeepSeek V4 Pro instead of Qwen3-Coder-Next, the one small model in the council. That adds a sixth lab. Set
TACHI_PLANNER_TIER=standardfor the cheaper lineup. - The jury's GPT juror is pinned to `gpt-6.1-sol`. It had been silently getting the cheap
gpt-6-lunadefault. Override withTACHI_JURY_OPENAI_MODEL. - Fixes:
- The planner no longer points at tools its profile doesn't register (
code_focuslacksqwen_reason). - The
planner_runner50% gate now sends the right params. - The workflow step guard now checks paths with the file reader's own parsing.
- Tool count unchanged at 67.
v2.35.0
- Gemini 4 Argon is the reasoning/judge default (GA Oct 13). In our judge tests it was faster and cheaper than 3.1 Pro even at its Dec 1 price ($4/$20), and on a real diff it caught defects that 3.1 Pro passed as "no defects, 5/5". Switch back without a code change with
TACHI_GEMINI_PRO_MODEL=gemini-3.1-pro-preview. - Model refresh, every ID verified live:
gpt-6.1-sol(SOL tier, now alsoopenai_search)grok-4.7forgrok_searchgemini-3.8-flashfor search and Flashstepfun/step-5-preview, GLM 5.3, and a DeepSeek V4.1 Flash fallback- `jev_decide` works now. It asks TypeSafe Jev for yes/no, choice or score answers as calibrated probabilities, for about $0.00002 per call. Workflows can branch on its answers (
if: "gate.answers.grounded.noul < 0.6"), and/council,/review,/promptand/writeuse it as a calibration check. - Fallbacks are never silent, and can be turned off. An answer from a backup model starts with
[degraded: X unavailable — ; answered by Y].TACHI_MODEL_FALLBACK=offturns backup models off entirely. Running out of credits never triggers a fallback. - Fixes:
- Rescued Gemini answers were being discarded.
- OpenRouter fallbacks fired only on a single error type.
nextThoughtOpenAI steps could silently call no model.- The grok search timeout ignored the response body.
- Security: workflow steps have a trust boundary. Steps run only profile-enabled tools, may read only files inside the working directory (no
.., symlink escapes or secrets such as.envand keys), and can't turn on Grok Heavy. - Removed `ernie_reason` (Baidu left OpenRouter on Oct 8). The
jev_decideaddition andernie_reasonremoval leave the count at 67 tools.
v2.34.0
- GPT-6 Astra is the OpenAI default.
gpt-6-astra(Sep 3, 2026; $10/$50, 1.05M context) now backsopenai_reason,openai_brainstorm,openai_code_review,spec_writer,tachiand the GPT reviewers indiff_review/plan_critique. Astra rolled out to a limited set of orgs first, so calls fall back togpt-5.6-sol, thengpt-5.6-terra, when an org lacks access.openai_explainstays on sol — low-effort explanations don't need the flagship. - GPT-6 models could not be called at all.
callOpenAIonly used the Responses API for names starting withgpt-5., so Astra fell through to Chat Completions withtemperature: 0.7and got a 400.gpt-6-*now goes to the Responses API without temperature, and thenone/minimalreasoning efforts Astra rejects are sent aslow. - `qwq_reason` works again.
qwen/qwq-32bwas retired from OpenRouter (every call returned 404), so the tool now runsqwen/qwen3.8-27batreasoning_effort: mediumwith the 235B thinking model as fallback — correct on a probe problem in 2.0s for $0.0007. Tool name and parameters are unchanged. - Tool count unchanged at 67.
v2.33.0
- The writing family (`storm`, `re3`, `de_generic`). The library had creative *thinking* (
what_if,innovate,alt_view,creative_use) and zero creative *writing*: against a 7-stage pipeline, stage 4 (structure) and stage 5 (draft) were empty, and stage 6 (revise) fell through toreflexion— which optimises toward *correct*, while prose revision is cutting, rhythm and specificity. 85 → 88 techniques. - `blog_writer` — researched long-form in one call, composing
stormandre3rather than carrying a private copy of their text. A copy would drift the moment either template was edited, and drift *silently*, because both paths still emit well-formed prose.research: trueruns the persona interview first and feeds its 3 surprising answers into the four-pass write. 66 → 67 tools; enabled infull,balancedandresearch_power. - `preview_prompt_technique(technique="auto")` had no route for writing intent.
RECOMMEND_RULEScarried no matcher, so "write a blog post" fell through toCORE_TECHNIQUES.slice(0, 3)—chain_of_note/astute_rag/spotlighting— whilelist_prompt_techniquesadvertisedautoas the way in. Writing verbs now route tostorm,re3,de_generic. - `blog_writer` truncated silently at `maxTokens: 8000`. Its output is several full renderings of the same piece (
re3's draft, restructure and line-edit passes, plusstorm's 16 marked answers), unlike sibling tools that emit one artifact. 8000 was already at the ceiling at the word count the docs use as their own example, and nothing errored on truncation. Raised to 16000. - Anti-drift tests could not detect drift. The "uses the template rather than a private copy" tests asserted characteristic phrases that a copy would also satisfy; they now assert the engine's exact live output.
v2.32.0
- Tabular family (7 new techniques) — data-shaped work had no coverage at all, so "filter these rows" fell through to the generic core contracts.
data_assertstates the downstream purpose first, then checks the data with executable assertions carrying counts, because a filter that silently matched zero rows is indistinguishable from one that worked. Pluschain_of_table,sub_table_first,sql_stages,xlsx_map,table_format,self_debug. - Retrieval family completed (3 new) —
astute_raganswers from memory first, then marks each source agrees/fills/conflicts and resolves every conflict out loud;craggrades sources correct/ambiguous/wrong and acts on the grade, since search always returns its nearest neighbours and has no way to return nothing;hydedrafts the answer you wish existed, searches with *its* vocabulary, then discards it. - Spotlighting fences carried 24 bits of entropy, not 32.
untrustedFence()calledrandomBytes(3)while its own comment block had reasoned its way to 4. Spotlighting's entire security property is that an attacker cannot guess the delimiter needed to close your block, so the shortfall was load-bearing. Now 8 hex characters, as documented. - The literal `37` survived three expansions of the catalogue (37 → 74 → 85) inside the
list_prompt_techniquesdescription — the text a model reads to decide whether to call the tool at all. It is now derived fromFLAT_TECHNIQUES.length. - 74 → 85 techniques. Tool count unchanged at 66.
v2.31.0
- Prompt technique library goes 37 → 74, closing three families that were at zero coverage. Retrieval (4): TachiBot ships five search tools and had no discipline for what to do with what they return — retrieved text went straight into reasoning unfiltered, which is where confidently-miscited sources come from. Prompt-injection defence (1): those same tools ingest untrusted web text with no isolation contract, so a page saying "ignore previous instructions" was read exactly like our own prompt;
spotlightingfences it and states the rule. Few-shot (5): nothing touched example selection or ordering, despite this moving accuracy more than most reasoning tricks. - Eight trace-management techniques from Jun–Aug 2026 research, including
hourglass(compress to a rule, discard the exploration, regenerate from the rule instead of appending errors) andbacktrack(rewind to the last validated checkpoint rather than restarting or patching). - Twelve original prompts rewritten to read as instructions. The early set used telegraphic shorthand that reads as a label rather than a request, leaving the model to infer the task.
- Recommendation rules for all of it — 74 techniques is past the point where anyone recalls names, so
RECOMMEND_RULESgained eight groups matched to how people actually phrase the situation. Without these the new techniques were reachable only by knowing their name in advance.
v2.30.1
- Tool descriptions no longer name-drop model versions. 19 descriptions were rewritten to name the provider and the task instead of pinned strings like "GPT-5.2", "Kimi K3" or "424B MoE" — those silently rot on every model bump and then actively mislead the routing model. Two were outright wrong:
openai_reasonandopenai_searchadvertised "GPT-5.2" while the code calls the current OpenAI flagship tier. - `grok_search` finally says why to pick it. Its entire description was "Web search" — no way to choose it over the four other search tools. It now states its live X/news grounding edge and cross-references
grok_search_liteas the cheaper path. The five OpenRouter reasoners (deepseek_reason,glm_reason,stepfun_reason,ernie_reason,qwen_reason) likewise differed only by vendor trivia; each now carries an actual routing rule for when to pick it. - Claude Desktop manifest corrected — it advertised 65 tools (actual: 66), omitted the
heavy_codingprofile from theTACHIBOT_PROFILEhelp, and itsOPENAI_API_KEYhint claimed that key powers the Qwen and QwQ tools (those route via OpenRouter). - Packaging no longer breaks the working tree.
scripts/package-extension.shrannpm install --production, pruning devDependencies and leavingtscunable to build afterward. It now restores the full dependency tree when it finishes. - The server introduced itself as v2.0.0.
serverInfo.versionwas hardcoded from a 12-tool era ~28 minor versions ago, so Claude Desktop's connector panel misidentified every install. It now reads the real version frompackage.json. The/setupwizard's profile sizes were stale in the same way and now match the six real profiles. - Correction to v2.30.0: `grok_search_lite` is not broken, and is staying. That release claimed
grok-4.3"does not invoke web search either" — which would have made the cheap search tier pointless. Re-probed Aug 15 asking today's date: grok-4.3 ran 2 web searches and returned a citation in 10.4s; grok-4.6 did the same in 36.4s. Lite is grounded, cheaper, and 3–4x faster — prefer it for high-volume lookups.grok-4.5is still the one that doesn't ground. The cheap tier now has its own grounding test, since nothing previously covered i