ZeroClaw
Zero Overhead. Zero Compromessi.
La maggior parte degli agenti AI consuma un gigabyte di RAM. Questo gira con quattro megabyte. Singolo binario Rust, cold start in 10ms, oltre 30 canali, qualsiasi modello AI. Deploy su un Raspberry Pi da 10$ o nel cloud di produzione — niente Node.js, niente Python, nessun compromesso.
Guida Rapida
brew install zeroclaw Single Rust binary. No runtime dependencies.
Funzionalità
Runtime Leggero
Meno di 5MB di memoria nelle build release. 99% più piccolo di OpenClaw. Gira su hardware da 10$ — ARM, x86 e RISC-V.
Qualsiasi Canale
Telegram, Discord, Slack, WhatsApp, Signal, iMessage, Matrix, IRC, Lark, DingTalk, QQ, Nostr, Email e altri.
Memoria Ibrida
Ricerca ibrida vettoriale + keyword basata su SQLite. Zero dipendenze esterne — niente Pinecone, niente Elasticsearch, niente LangChain.
Completamente Modulare
Ogni sottosistema è un trait — provider, canali, strumenti, memoria, tunnel. Cambia implementazione con una modifica al config, zero modifiche al codice.
Sicuro per Design
Pairing del gateway, sandboxing rigoroso, allowlist esplicite, scoping del workspace, secret cifrati. Policy deny-by-default per i canali.
Cold Start Rapidi
Runtime Rust a binario singolo. Avvio quasi istantaneo per le operazioni quotidiane. 400 volte più veloce di OpenClaw su hardware equivalente.
Installa arrow_forward
Script in una riga che gestiscono tutto. Consigliato per la maggior parte degli utenti.
Blog arrow_forward
Notizie, release e storie dalla community di ZeroClaw.
Integrazioni arrow_forward
ZeroClaw funziona con i tuoi strumenti e piattaforme preferiti. Chatta da qualsiasi posto.
Docs arrow_forward
Tutto ciò che serve per usare ZeroClaw: installazione, opzioni config.toml, comandi CLI, architettura plugin, modello di sicurezza e riferimento API.
Contributors arrow_forward
Ogni commit affila ZeroClaw. Scopri gli sviluppatori che scrivono Rust, rilasciano funzionalità e mantengono il runtime ultraveloce.
Cosa Dice la Gente
"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_ninjaDomande Frequenti
Domande comuni su ZeroClaw e come funziona.