ZeroClaw Logo

ZeroClaw

Không chi phí thừa. Không thỏa hiệp.

Hầu hết AI agent ngốn cả gigabyte RAM. Con này chạy trên bốn megabyte. Một binary Rust duy nhất, cold start 10ms, 30+ kênh, mọi mô hình AI. Deploy trên Raspberry Pi $10 hoặc cloud — không Node.js, không Python, không thỏa hiệp.

Bắt đầu nhanh

BETA
# macOS via Homebrew. One command. 🦀
$ brew install zeroclaw

Single Rust binary. No runtime dependencies.

Tính năng

memory

Runtime gọn nhẹ

Dung lượng bộ nhớ <5MB trên bản release. Nhỏ hơn 99% so với OpenClaw. Chạy trên phần cứng $10 — ARM, x86 và RISC-V.

chat_bubble

Mọi kênh

Telegram, Discord, Slack, WhatsApp, Signal, iMessage, Matrix, IRC, Lark, DingTalk, QQ, Nostr, Email và nhiều hơn.

database

Bộ nhớ lai

Tìm kiếm lai vector + từ khóa dựa trên SQLite. Không phụ thuộc bên ngoài — không Pinecone, không Elasticsearch, không LangChain.

swap_horiz

Hoán đổi hoàn toàn

Mọi hệ thống con là một trait — provider, kênh, công cụ, bộ nhớ, tunnel. Hoán đổi triển khai bằng thay đổi cấu hình, không cần sửa code.

shield

Bảo mật từ thiết kế

Gateway pairing, sandbox nghiêm ngặt, allowlist rõ ràng, workspace scoping, mã hóa secret. Chính sách kênh deny-by-default.

bolt

Cold Start nhanh

Runtime Rust binary đơn. Khởi động gần như tức thì cho thao tác hàng ngày. Nhanh hơn 400 lần so với OpenClaw trên phần cứng tương đương.

Mọi người nói gì

@rustacean_dev avatar

"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
@devops_mike avatar

"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
@sarahcodes avatar

"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
@cloud_native_tom avatar

"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
@security_emma avatar

"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
@embedded_chris avatar

"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
@rustacean_dev avatar

"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
@devops_mike avatar

"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
@sarahcodes avatar

"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
@cloud_native_tom avatar

"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
@security_emma avatar

"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
@embedded_chris avatar

"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
@ivanfioravanti avatar

"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
@startup_alex avatar

"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
@data_lisa avatar

"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
@homelab_dan avatar

"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
@mobile_chris avatar

"The Docker sandboxed runtime option is perfect for multi-tenant setups. Each user gets their own isolated ZeroClaw instance. Security without complexity."

@mobile_chris
@backend_ninja avatar

"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
@ivanfioravanti avatar

"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
@startup_alex avatar

"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
@data_lisa avatar

"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
@homelab_dan avatar

"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
@mobile_chris avatar

"The Docker sandboxed runtime option is perfect for multi-tenant setups. Each user gets their own isolated ZeroClaw instance. Security without complexity."

@mobile_chris
@backend_ninja avatar

"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

Câu hỏi thường gặp

Các câu hỏi phổ biến về ZeroClaw và cách hoạt động.

Theo dõi tin mới

Nhận cập nhật về bản phát hành mới, tích hợp và hạ tầng agent chạy bằng Rust. Không spam, hủy đăng ký bất cứ lúc nào.