https://github.com/memovai/mimiclaw
MimiClaw: Run OpenClaw on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS.๐Local-first memory. Shareable. Portable. Privacy-first.
https://github.com/memovai/mimiclaw
ai assistant clawdbot edge-ai-agents memory openclaw
Last synced: 3 months ago
JSON representation
MimiClaw: Run OpenClaw on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS.๐Local-first memory. Shareable. Portable. Privacy-first.
- Host: GitHub
- URL: https://github.com/memovai/mimiclaw
- Owner: memovai
- License: mit
- Created: 2026-02-04T04:25:33.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2026-02-12T14:08:15.000Z (3 months ago)
- Last Synced: 2026-02-12T15:17:22.674Z (3 months ago)
- Topics: ai, assistant, clawdbot, edge-ai-agents, memory, openclaw
- Language: C
- Homepage: https://www.mimiclaw.io
- Size: 3.89 MB
- Stars: 1,431
- Watchers: 16
- Forks: 167
- Open Issues: 32
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-openclaw - MimiClaw - S3 chip without Linux or Node.js | (Community Projects / Deployment & Infrastructure)
- awesome-claw-cn - MimiClaw - S3 ่ฏ็ไธ (ๆกๆถไธ่ก็้กน็ฎ)
- awesome-openclaw - memovai/mimiclaw - Hardware-oriented runtime for ultra-low-cost OpenClaw-style deployments. (โก Alternative Clients & Runtimes)
- awesome-claw-opus - MimiClaw - S3 chips | (Ecosystem / Context Management)
- awesome-personal-ai-assistants - MimiClaw - Run OpenClaw on a $5 chip with no OS, no Node.js, no Linux. Bare-metal C implementation with local-first memory. Portable, shareable, and privacy-first. `C`  (Bare Metal)
- awesome-rainmana - memovai/mimiclaw - MimiClaw: Run OpenClaw on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS. (C)
- awesome-openclaw - memovai/mimiclaw - Macht aus einem kleinen ESP32-S3-Board einen persoenlichen KI-Assistenten.  (Alternative Architekturen)
- awesome-claw - memovai/mimiclaw - Run OpenClaw on a $5 chip โ no OS, no Node.js, no Mac mini required; local-first and privacy-first (Lightweight Alternatives & Forks)
- awesome-claws - MimiClaw - C - Pocket assistant for ESP32-S3 with no OS, low power usage, and local-first memory running continuously on USB power. (Main Projects)
- awesome-claw - **MimiClaw** - | - | - | ESP32-S3 chip, $5 hardware, no OS required | (Lightweight & Embedded Claws / Comparison Table)
README
# MimiClaw: Pocket AI Assistant on a $5 Chip
[](LICENSE)
[](https://deepwiki.com/memovai/mimiclaw)
[](https://discord.gg/r8ZxSvB8Yr)
[](https://x.com/ssslvky)
**[English](README.md) | [ไธญๆ](README_CN.md) | [ๆฅๆฌ่ช](README_JA.md)**
**The world's first AI assistant(OpenClaw) on a $5 chip. No Linux. No Node.js. Just pure C**
MimiClaw turns a tiny ESP32-S3 board into a personal AI assistant. Plug it into USB power, connect to WiFi, and talk to it through Telegram โ it handles any task you throw at it and evolves over time with local memory โ all on a chip the size of a thumb.
## Meet MimiClaw
- **Tiny** โ No Linux, no Node.js, no bloat โ just pure C
- **Handy** โ Message it from Telegram, it handles the rest
- **Loyal** โ Learns from memory, remembers across reboots
- **Energetic** โ USB power, 0.5 W, runs 24/7
- **Lovable** โ One ESP32-S3 board, $5, nothing else
## How It Works
You send a message on Telegram. The ESP32-S3 picks it up over WiFi, feeds it into an agent loop โ the LLM thinks, calls tools, reads memory โ and sends the reply back. Supports both **Anthropic (Claude)** and **OpenAI (GPT)** as providers, switchable at runtime. Everything runs on a single $5 chip with all your data stored locally on flash.
## Quick Start
### What You Need
- An **ESP32-S3 dev board** with 16 MB flash and 8 MB PSRAM (e.g. Xiaozhi AI board, ~$10)
- A **USB Type-C cable**
- A **Telegram bot token** โ talk to [@BotFather](https://t.me/BotFather) on Telegram to create one
- An **Anthropic API key** โ from [console.anthropic.com](https://console.anthropic.com), or an **OpenAI API key** โ from [platform.openai.com](https://platform.openai.com)
### Install
```bash
# You need ESP-IDF v5.5+ installed first:
# https://docs.espressif.com/projects/esp-idf/en/v5.5.2/esp32s3/get-started/
git clone https://github.com/memovai/mimiclaw.git
cd mimiclaw
idf.py set-target esp32s3
```
### Configure
MimiClaw uses a **two-layer config** system: build-time defaults in `mimi_secrets.h`, with runtime overrides via the serial CLI. CLI values are stored in NVS flash and take priority over build-time values.
```bash
cp main/mimi_secrets.h.example main/mimi_secrets.h
```
Edit `main/mimi_secrets.h`:
```c
#define MIMI_SECRET_WIFI_SSID "YourWiFiName"
#define MIMI_SECRET_WIFI_PASS "YourWiFiPassword"
#define MIMI_SECRET_TG_TOKEN "123456:ABC-DEF1234ghIkl-zyx57W2v1u123ew11"
#define MIMI_SECRET_API_KEY "sk-ant-api03-xxxxx"
#define MIMI_SECRET_MODEL_PROVIDER "anthropic" // "anthropic" or "openai"
#define MIMI_SECRET_SEARCH_KEY "" // optional: Brave Search API key
#define MIMI_SECRET_PROXY_HOST "" // optional: e.g. "10.0.0.1"
#define MIMI_SECRET_PROXY_PORT "" // optional: e.g. "7897"
```
Then build and flash:
```bash
# Clean build (required after any mimi_secrets.h change)
idf.py fullclean && idf.py build
# Find your serial port
ls /dev/cu.usb* # macOS
ls /dev/ttyACM* # Linux
# Flash and monitor (replace PORT with your port)
# USB adapter: likely /dev/cu.usbmodem11401 (macOS) or /dev/ttyACM0 (Linux)
idf.py -p PORT flash monitor
```
> **Important: Plug into the correct USB port!** Most ESP32-S3 boards have two USB-C ports. You must use the one labeled **USB** (native USB Serial/JTAG), **not** the one labeled **COM** (external UART bridge). Plugging into the wrong port will cause flash/monitor failures.
>
>
> Show reference photo
>
> 
>
>
### CLI Commands
Connect via serial to configure or debug. **Config commands** let you change settings without recompiling โ just plug in a USB cable anywhere.
**Runtime config** (saved to NVS, overrides build-time defaults):
```
mimi> wifi_set MySSID MyPassword # change WiFi network
mimi> set_tg_token 123456:ABC... # change Telegram bot token
mimi> set_api_key sk-ant-api03-... # change API key (Anthropic or OpenAI)
mimi> set_model_provider openai # switch provider (anthropic|openai)
mimi> set_model gpt-4o # change LLM model
mimi> set_proxy 127.0.0.1 7897 # set HTTP proxy
mimi> clear_proxy # remove proxy
mimi> set_search_key BSA... # set Brave Search API key
mimi> config_show # show all config (masked)
mimi> config_reset # clear NVS, revert to build-time defaults
```
**Debug & maintenance:**
```
mimi> wifi_status # am I connected?
mimi> memory_read # see what the bot remembers
mimi> memory_write "content" # write to MEMORY.md
mimi> heap_info # how much RAM is free?
mimi> session_list # list all chat sessions
mimi> session_clear 12345 # wipe a conversation
mimi> restart # reboot
```
## Memory
MimiClaw stores everything as plain text files you can read and edit:
| File | What it is |
|------|------------|
| `SOUL.md` | The bot's personality โ edit this to change how it behaves |
| `USER.md` | Info about you โ name, preferences, language |
| `MEMORY.md` | Long-term memory โ things the bot should always remember |
| `2026-02-05.md` | Daily notes โ what happened today |
| `tg_12345.jsonl` | Chat history โ your conversation with the bot |
## Tools
MimiClaw supports tool calling for both Anthropic and OpenAI โ the LLM can call tools during a conversation and loop until the task is done (ReAct pattern).
| Tool | Description |
|------|-------------|
| `web_search` | Search the web via Brave Search API for current information |
| `get_current_time` | Fetch current date/time via HTTP and set the system clock |
To enable web search, set a [Brave Search API key](https://brave.com/search/api/) via `MIMI_SECRET_SEARCH_KEY` in `mimi_secrets.h`.
## Also Included
- **WebSocket gateway** on port 18789 โ connect from your LAN with any WebSocket client
- **OTA updates** โ flash new firmware over WiFi, no USB needed
- **Dual-core** โ network I/O and AI processing run on separate CPU cores
- **HTTP proxy** โ CONNECT tunnel support for restricted networks
- **Multi-provider** โ supports both Anthropic (Claude) and OpenAI (GPT), switchable at runtime
- **Tool use** โ ReAct agent loop with tool calling for both providers
## For Developers
Technical details live in the `docs/` folder:
- **[docs/ARCHITECTURE.md](docs/ARCHITECTURE.md)** โ system design, module map, task layout, memory budget, protocols, flash partitions
- **[docs/TODO.md](docs/TODO.md)** โ feature gap tracker and roadmap
## License
MIT
## Acknowledgments
Inspired by [OpenClaw](https://github.com/openclaw/openclaw) and [Nanobot](https://github.com/HKUDS/nanobot). MimiClaw reimplements the core AI agent architecture for embedded hardware โ no Linux, no server, just a $5 chip.
## Star History
[](https://star-history.com/#memovai/mimiclaw&Date)