ZeroClaw
Zéro surcharge. Zéro compromis.
La plupart des agents IA consomment un gigaoctet de RAM. Celui-ci tourne avec quatre mégaoctets. Un seul binaire Rust, démarrage à froid en 10 ms, 30+ canaux, n'importe quel modèle IA. Se déploie sur un Raspberry Pi à 10 $ ou en cloud de production — pas de Node.js, pas de Python, aucun compromis.
Démarrage rapide
brew install zeroclaw Single Rust binary. No runtime dependencies.
Capacités
Runtime léger
<5 Mo d'empreinte mémoire en build release. 99 % plus petit qu'OpenClaw. Tourne sur du matériel à 10 $ — ARM, x86 et RISC-V.
Tous les canaux
Telegram, Discord, Slack, WhatsApp, Signal, iMessage, Matrix, IRC, Lark, DingTalk, QQ, Nostr, Email et plus encore.
Mémoire hybride
Recherche hybride vectorielle + mots-clés basée sur SQLite. Zéro dépendance externe — pas de Pinecone, pas d'Elasticsearch, pas de LangChain.
Entièrement modulable
Chaque sous-système est un trait — providers, canaux, outils, mémoire, tunnels. Changez d'implémentation via la configuration, sans modifier le code.
Sécurisé par conception
Appairage gateway, sandboxing strict, listes d'autorisation explicites, portée workspace, secrets chiffrés. Politique de canal deny-by-default.
Démarrage à froid rapide
Runtime Rust en binaire unique. Démarrage quasi instantané pour les opérations quotidiennes. 400x plus rapide qu'OpenClaw sur du matériel équivalent.
Installer arrow_forward
Scripts en une ligne qui font tout. Recommandé pour la plupart des utilisateurs.
Blog arrow_forward
Actualités, releases et récits de la communauté ZeroClaw.
Intégrations arrow_forward
ZeroClaw fonctionne avec vos outils et plateformes préférés. Discutez avec lui depuis n'importe où.
Docs arrow_forward
Tout ce qu'il faut pour utiliser ZeroClaw : installation, options config.toml, commandes CLI, architecture de plugins, modèle de sécurité et référence API.
Contributeurs arrow_forward
Chaque commit affûte ZeroClaw. Découvrez les développeurs qui écrivent le Rust, livrent les fonctionnalités et maintiennent le runtime ultra-rapide.
Ce qu'ils en disent
"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_ninjaQuestions fréquentes
Questions courantes sur ZeroClaw et son fonctionnement.