GitHub Repository

Lightweight AI agent runtime targeting Raspberry Pi Zero 2W and low-end VPS. File-based memory, MCP tool support, Telegram integration — all in a single binary.

19 starsRust

Neko – AI agent runtime that fits on a Raspberry Pi Zero 2W

Name: Neko – AI agent runtime that fits on a Raspberry Pi Zero 2W
Availability: InStock
Author: harshdoesdev

by harshdoesdev·Feb 17, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerNiche GemZero to OneWizardry

Persistent AI agent on Pi Zero 2W with MCP, markdown memory, and cron scheduling—genuinely novel.

Strengths

•File-based markdown memory (short/long/recall layers) forces deliberate curation over token-dumping, enabling long-running agents on minimal memory
•First-class cron jobs—agent can create scheduled tasks mid-conversation, routed back through Telegram; no parallel in consumer runtimes
•Single static binary (Rust) ships to $4/mo VPS or Pi Zero 2W; eliminates container/orchestration overhead for personal agents

Weaknesses

•Very early (7 stars, 1 fork, no releases); no evidence of production use or long-term agent stability
•Markdown memory lacks search index; full-text search likely slow on larger histories

Post Description

I wanted a personal AI agent I could leave running on cheap hardware, a Pi Zero 2W or a $4/mo VPS, without much infrastructure overhead. So I built Neko.

Memory is markdown files the agent reads and writes itself. There's a short-term layer for today's and yesterday's session logs, a long-term MEMORY.md capped at 2000 chars that forces the agent to compact and curate rather than just accumulate, and a searchable recall folder for older conversations. The files are plain text you can read, edit, and commit to git.

It also supports MCP for connecting external tools, and Telegram as a messaging front-end.

Cron jobs are first-class. You can schedule them from the CLI, or the agent can create them itself mid-conversation. If a user on Telegram says "remind me every morning at 9am", the agent creates the job and routes the results back to that chat.

Ships as a single static binary written in Rust.

Similar Projects

AI/ML●●Solid

Max Headbox, a local agent that fits on a Raspberry Pi 5

Animated desk toy runs gemma3:1b locally without cloud dependencies.

CozyNiche Gem

syx

402mo ago

AI/ML●Mid

Pi, written in Rust

The repo looks like an agent framework implemented in Rust (Cargo.toml, src, examples) with explicit Slack webhook and Claude integration notes — sensible if you want a Rust-native assistant runtime. It's low-star and the README/landing copy don't make the unique selling point clear, so buyers will need to dig into examples to judge whether it beats established Python/JS agent toolkits.

Niche GemShip It

yajatgulati

103mo ago

AI/ML●●Solid