malikclaw
Active·★ 15·MIT·Updated 2026-04-24
★ Trending★ Memory & Context★ Security & Safety
Ultra-lightweight AI Agent & Assistant for $10 SBCs & Android. Urdu-first, Go-based, and privacy-focused. 99% smaller memory than typical gateways.
MalikClaw is a high-performance, ultra-lightweight personal AI assistant built in Go. It runs on $10 hardware with less than 10MB RAM, offering fast boot times and privacy-first operation. It supports Urdu-first bilingual interface and multiple chat platforms.
#ai-age#ai-agent-development#andrio#andriod-studio#malikclaw#mcp-server#mcp-servers#multi-platform
01
Features
01Urdu-First bilingual onboarding and RTL UI
02Ultra-lightweight with <10MB RAM footprint
03Lightning fast startup in under 1 second
04Mobile operation via ADB on Android devices
05Built-in business integration with Gmail and Odoo
02
Compatibility
Linux x86_64
x86_64
Verified via docs
Linux ARM64
ARM64
Verified via docs
Linux MIPS
MIPS
Verified via docs
Linux RISC-V
RISC-V
Verified via docs
Android
Android (Termux)
Verified via docs
03
Quick start
1
$ git clone https://github.com/AbdullahMalik17/malikclaw.git
2
$ cd malikclaw
3
$ make deps
4
$ make build
04
Use cases
↳Reviving old Android phones as AI assistants
↳Deploying on ultra-cheap SBCs like Orange Pi Zero
↳Privacy-focused personal AI assistant for daily tasks
05
Alternatives
letta★ 23.0k
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
DesktopCommanderMCP★ 6.1k
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
FunASR★ 16.6k
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
Related searches
Comments
Log in to leave a comment
- OOakley ThompsonMay 18, 2026
Ultra-lightweight AI agent for $10 SBCs and Android with Urdu-first design.
- HHayden ChenMay 2, 2026
Urdu-first approach makes AI accessible to Urdu-speaking users.
- SSutton ZhangApr 10, 2026
Go-based implementation keeps the footprint tiny for constrained hardware.
- DDakota KimMar 13, 2026
Good for developers in Pakistan and South Asian markets building accessible AI.