MimiClaw

Citation review, September 16, 2026: corrected the FreeRTOS and cloud-inference distinctions. Other status and adoption figures retain the June 11 review baseline.

September 23, 2026 refresh: stars (5.8K), last push (August 21, 2026), open issues (54), Feishu/Lark docs, ARCHITECTURE.md staleness, and XDA/HN source accessibility updated below.

Executive Summary

MimiClaw is the most extreme OpenClaw alternative: it runs on a $5 ESP32-S3 microcontroller. No Linux. No Node.js. No VPS. Just pure C firmware, 0.5W power consumption, and Telegram control. Feishu/Lark appears in docs/im-integration and the v0.1.1 notes; the English README is still Telegram-first.^[1][2][3] Plug it into USB power, connect to WiFi, and talk to it — it handles tasks and remembers everything on local flash storage. The project is run by MemoV, Inc.,^[4] which has a hardware-kit waitlist at mimiclaw.io; funding is not publicly disclosed.

Status (as of September 2026): Active but slowing. The repo is not archived and sits at 5.8K stars (up from 2.8K in February and ~5.5K in June), but only two releases have shipped — v0.1.0 (Feb 9, 2026) and v0.1.1 (Mar 17, 2026) — and the last push to the repo was August 21, 2026 (not April 21). Open issues: 54.^[3]

---

Key Capabilities

Memory Files

Tools

• web_search — Tavily or Brave Search API^[3]
• get_current_time — Sync system clock
• cron_add/list/remove — AI manages its own schedule

---

Strengths

• Cheapest hardware — $5-10 for the entire device
• Lowest power — 0.5W, runs continuously on USB
• True portability — Thumb-sized, pocket-friendly
• Local-first memory — Memory files persist on device flash; prompts are sent to the configured LLM API^[5]
• Self-scheduling — AI creates its own cron jobs
• Heartbeat autonomy — Proactively acts on task list

---

Cautions

• Slowing development — Last release still v0.1.1 (Mar 17, 2026); last push August 21, 2026 (not April 21); 54 open issues as of September 2026^[3][2]
• API costs add up fast — XDA's reviewer hit 50% of token budget in an hour with the hardcoded Opus model; switching to Haiku is recommended^[6]
• Limited compute — ESP32-S3 is a microcontroller, not a computer
• C expertise needed — Flashing firmware requires ESP-IDF v5.5 knowledge
• Telegram-first English README — The English README still leads with Telegram plus a LAN WebSocket gateway; Feishu/Lark is in docs/im-integration and the v0.1.1 notes. ARCHITECTURE.md is stale vs the README for channels/cron.^[3][1][5]
• WiFi required — No offline LLM capability^[3]
• No sandboxing — Limited security isolation

---

What Developers Say

From XDA Developers' hands-on review (Samir Makwana, April 2026) — page is accessible as of September 2026:^[6]

"The response times of about 3 to 8 seconds for simple questions are quite acceptable."

"After running MimiClaw on ESP32-S3 for an hour, I wanted to check the token usage. To my shock, it was already at 50 percent."

"This isn't a plug-and-play style product. I had to build and flash the firmware."

On Hacker News — page is accessible as of September 2026 — the thread has 1 point and 3 comments;^[7] the most-voted reply was skepticism of the "no Linux, no Node" framing — "Pretty sure Anthropic uses both Linux and node somewhere in their stack" (cap11235) — to which the creator responded that the point is no OS on the device itself. Beyond press coverage, organic developer testimonials remain scarce relative to the project's star count.

---

Bottom Line

MimiClaw is the ultimate minimalist statement: your AI assistant can run on $5 hardware drawing half a watt. It's not for everyone — flashing ESP32 firmware requires technical skill, API costs on the default Opus model burn fast, and development has visibly cooled (latest release still v0.1.1 Mar 17; last push August 21, 2026) — but for tinkerers who want the smallest, cheapest, most power-efficient option, MimiClaw remains remarkable.

Tembo is unrelated / weakly adjacent at most: MimiClaw is $5 ESP32 firmware for a personal Telegram/Feishu assistant, while Tembo is a team coding-agent execution platform. They do not compete, and no integration was verified. Disclosure: Ry Walker is Tembo's co-founder and CEO.^[8]

Recommended for: Hardware tinkerers who want the cheapest, smallest, most power-efficient AI assistant possible.

Not recommended for: Users who want easy setup, multiple channels, or enterprise features.

---

Research by Ry Walker Research • methodology