ZeroClaw
오버헤드 제로. 타협 제로.
대부분의 AI 에이전트는 1GB RAM을 잡아먹습니다. 이건 4MB로 돌아갑니다. 단일 Rust 바이너리, 10ms 콜드 스타트, 30개 이상 채널, 어떤 AI 모델이든. $10 Raspberry Pi부터 프로덕션 클라우드까지 — Node.js 없이, Python 없이, 타협 없이.
빠른 시작
brew install zeroclaw Single Rust binary. No runtime dependencies.
주요 기능
경량 런타임
릴리스 빌드 기준 <5MB 메모리 사용. OpenClaw 대비 99% 작음. $10 하드웨어에서 실행 — ARM, x86, RISC-V.
모든 채널
Telegram, Discord, Slack, WhatsApp, Signal, iMessage, Matrix, IRC, Lark, DingTalk, QQ, Nostr, Email 등.
하이브리드 메모리
SQLite 기반 벡터 + 키워드 하이브리드 검색. 외부 의존성 제로 — Pinecone 없음, Elasticsearch 없음, LangChain 없음.
완전 교체 가능
모든 서브시스템이 trait입니다 — Provider, Channel, Tool, Memory, Tunnel. 설정 변경만으로 구현체를 교체할 수 있습니다.
설계부터 안전하게
Gateway 페어링, 엄격한 샌드박싱, 명시적 허용 목록, 워크스페이스 스코핑, 암호화된 시크릿. 기본 거부 채널 정책.
빠른 콜드 스타트
단일 바이너리 Rust 런타임. 일상 작업에서 거의 즉시 시작. 동일 하드웨어에서 OpenClaw 대비 400배 빠름.
설치 arrow_forward
모든 것을 처리하는 원라인 스크립트. 대부분의 사용자에게 추천합니다.
블로그 arrow_forward
ZeroClaw 커뮤니티의 뉴스, 릴리스, 이야기.
연동 arrow_forward
ZeroClaw는 좋아하는 도구와 플랫폼에서 작동합니다. 어디서든 대화할 수 있습니다.
문서 arrow_forward
ZeroClaw 실행에 필요한 모든 것: 설치, config.toml 옵션, CLI 명령어, 플러그인 아키텍처, 보안 모델, API 레퍼런스.
기여자 arrow_forward
커밋 하나하나가 ZeroClaw를 더 날카롭게 만듭니다. Rust를 쓰고, 기능을 만들고, 런타임을 극한까지 빠르게 유지하는 개발자들을 만나보세요.
사용자 후기
"ZeroClaw uses 4MB of RAM. OpenClaw uses over 1GB. That's not an optimization — that's a completely different class of software. Running it on my Raspberry Pi Zero with zero issues."
@rustacean_dev"Deployed ZeroClaw on a $10 Orange Pi. It handles Telegram + Discord + Slack channels simultaneously with <5MB memory. My OpenClaw setup needed a $599 Mac mini for the same thing."
@devops_mike"The trait-driven architecture is brilliant. Swapped from OpenAI to a local Ollama model by changing one line in config.toml. No code changes, no recompile. Just works."
@sarahcodes"Cold start in under 10ms. I measured it. My Node.js agent takes 8 seconds. ZeroClaw's single binary approach is exactly what edge deployment needs."
@cloud_native_tom"Finally an AI agent that takes security seriously. Gateway pairing, deny-by-default allowlists, workspace scoping, symlink escape detection. This is how it should be done."
@security_emma"Running ZeroClaw on ARM64, x86, and even RISC-V boards. Same binary workflow everywhere. The portable architecture is a game changer for IoT agent deployments."
@embedded_chris"ZeroClaw uses 4MB of RAM. OpenClaw uses over 1GB. That's not an optimization — that's a completely different class of software. Running it on my Raspberry Pi Zero with zero issues."
@rustacean_dev"Deployed ZeroClaw on a $10 Orange Pi. It handles Telegram + Discord + Slack channels simultaneously with <5MB memory. My OpenClaw setup needed a $599 Mac mini for the same thing."
@devops_mike"The trait-driven architecture is brilliant. Swapped from OpenAI to a local Ollama model by changing one line in config.toml. No code changes, no recompile. Just works."
@sarahcodes"Cold start in under 10ms. I measured it. My Node.js agent takes 8 seconds. ZeroClaw's single binary approach is exactly what edge deployment needs."
@cloud_native_tom"Finally an AI agent that takes security seriously. Gateway pairing, deny-by-default allowlists, workspace scoping, symlink escape detection. This is how it should be done."
@security_emma"Running ZeroClaw on ARM64, x86, and even RISC-V boards. Same binary workflow everywhere. The portable architecture is a game changer for IoT agent deployments."
@embedded_chris"The hybrid memory system blew my mind. SQLite vector search + FTS5 keyword search, zero external dependencies. No Pinecone, no Elasticsearch. Just a single file."
@ivanfioravanti"Migrated from OpenClaw to ZeroClaw in 20 minutes. 'zeroclaw migrate openclaw --dry-run' showed exactly what would change. Memory, config, everything carried over cleanly."
@startup_alex"17 channels supported out of the box. Telegram, Discord, Slack, WhatsApp, Signal, Matrix, IRC, Lark, DingTalk, QQ, Nostr... I've never seen this level of integration coverage."
@data_lisa"ZeroClaw as a systemd service on my home server. Always on, <5MB footprint, handles all my home automation through natural language. This is the future of personal AI."
@homelab_dan"The Docker sandboxed runtime option is perfect for multi-tenant setups. Each user gets their own isolated ZeroClaw instance. Security without complexity."
@mobile_chris"Built by Harvard and MIT students, and it shows. The code quality, the architecture decisions, the documentation — everything is production-grade from day one."
@backend_ninja"The hybrid memory system blew my mind. SQLite vector search + FTS5 keyword search, zero external dependencies. No Pinecone, no Elasticsearch. Just a single file."
@ivanfioravanti"Migrated from OpenClaw to ZeroClaw in 20 minutes. 'zeroclaw migrate openclaw --dry-run' showed exactly what would change. Memory, config, everything carried over cleanly."
@startup_alex"17 channels supported out of the box. Telegram, Discord, Slack, WhatsApp, Signal, Matrix, IRC, Lark, DingTalk, QQ, Nostr... I've never seen this level of integration coverage."
@data_lisa"ZeroClaw as a systemd service on my home server. Always on, <5MB footprint, handles all my home automation through natural language. This is the future of personal AI."
@homelab_dan"The Docker sandboxed runtime option is perfect for multi-tenant setups. Each user gets their own isolated ZeroClaw instance. Security without complexity."
@mobile_chris"Built by Harvard and MIT students, and it shows. The code quality, the architecture decisions, the documentation — everything is production-grade from day one."
@backend_ninja자주 묻는 질문
ZeroClaw에 관한 자주 묻는 질문과 작동 방식.