pollen-robotics/reachy_mini is the SDK and development project for Reachy Mini, an open-source expressive robot for hackers and AI builders. It supports building robot behaviors and applications with Python or JavaScript, including simulated robots and integrations with language models. The catalogue add-ons provide coding guidance for the Reachy Mini SDK.
Borrowing it
Nothing to install: this file belongs to pollen-robotics/reachy_mini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pollen-robotics/reachy_mini/main/AGENTS.mdgit clone --depth 1 https://github.com/pollen-robotics/reachy_miniWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/pollen-robotics/reachy_mini/agents-md)<a href="https://agentmods.dev/instructions/pollen-robotics/reachy_mini/agents-md"><img src="https://agentmods.dev/badge/instructions/pollen-robotics/reachy_mini/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/pollen-robotics/reachy_mini/agents-md"><img src="https://agentmods.dev/badge/instructions/pollen-robotics/reachy_mini/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05137 | $0.05137 |
| Opus 5.5 | $0.02055 | $0.02055 |
| Sonnet 5.5 | $0.01027 | $0.01027 |
| Haiku 4.5 | $0.00514 | $0.00514 |
Grade A, and why
reachy_mini AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachy Mini Development Guide for AI Agents
This guide helps AI agents assist users in developing Reachy Mini applications.
Agent Behavior
FIRST: Check for agents.local.md
Before doing anything else, search for agents.local.md in your working directory (the folder where the app lives or will be created — not the reachy_mini repo clone):
IF agents.local.md exists:
Read it immediately
It contains user configuration and session context
ELSE:
→ Python path: run skills/setup-environment.md to set up the environment
→ JS path: skip it (Node.js is all you need), just create agents.local.md in that working directory
This file stores the user's robot type, preferences, and setup status. Always check it first.
Be a Teacher
Unless the user explicitly requests otherwise:
- Explain concepts as you go
- Encourage questions ("Let me know if you'd like more detail on any of this")
- Guide non-technical users through each step
- Don't assume prior knowledge
Two App Flavours — Default to JS, Python for developers
Reachy Mini supports two app types. Default to a JS (Live/Web) app unless the user explicitly wants on-robot Python, or has a need that only Python can cover (heavy on-robot compute, rich hardware access, deterministic real-time control loops, or bundled offline LAN tooling).
| Flavour | Default for | Where it runs | Constraints |
|---|---|---|---|
| JS app (recommended) | End-users, shareable-by-URL experiences, anyone who wants "open a link, use the robot". Remote launch, zero-install, streaming A/V UIs. | Static HF Space; reaches the robot over WebRTC via the central signaling server. | Runs only while a browser tab is open; needs internet and an HF account for every session; one controlling session per robot. Works on Wireless and Lite. |
| Python app | Developer tools, on-robot control loops, heavy motion sequencing, offline/LAN. | Robot owner's machine (laptop / CM4), optionally with a bundled web UI. | Pick it when the app must run unattended or always-on, work without internet or keep data inside the home network, or be reachable by other local services (e.g. Home Assistant). |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 16d ago Changed · +6 lines · +269 tokens per session 679a12fe6088
- 17d ago Changed · +86 tokens per session 2bae3a386388
- 24d ago Changed · +1 lines · +21 tokens per session df4174d2411d
- 1mo ago Changed · +55 tokens per session 65c7e6bf7ffd
- 2mo ago First seen · 315 lines · 4,706 tokens per session scan A da3752c5447c
reachy_mini AGENTS.md is an instructions file published in the GitHub repository pollen-robotics/reachy_mini (1,643 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,137 tokens to every session, about $0.0205 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
reachy_mini AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reachy_mini AGENTS.mdpollen-robotics/reachy_mini | Instructions file | 1.6k | yesterday | Apache-2.0 | A | 5,137 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |