HybridClaw is a self-hosted AI assistant runtime for teams that need control, security, and operational visibility. It combines sandboxed execution, secure credentials, approvals, persistent memory, and admin surfaces behind a single gateway.
Connect it to Discord, Slack, WhatsApp, Telegram, Microsoft Teams, email, or the web. Run it locally, deploy it for business workflows, and keep your agents, secrets, and data under your control.
Quick Start · Installation · Configuration · Migration · Contributing · Support
- Want the shortest path to a running assistant? Start with Quick Start.
- Want the full setup flow with providers, channels, and admin surfaces? Start with Installation and Authentication.
- Want to migrate from OpenClaw or Hermes? Start with the migration commands.
- Want to contribute from source? Start with CONTRIBUTING.md and the maintainer docs under docs/content/README.md.
hybridclaw migrate openclaw --dry-run
hybridclaw migrate hermes --dry-runPreview and import compatible state from OpenClaw or Hermes in minutes. Imports compatible skills, memory, config, and optional secrets.
HybridClaw is the runtime. HybridAI is the (optional) platform layer around it.
HybridAI adds:
- one-click cloud deployment
- enterprise shared RAG / knowledge
- access to current models from Anthropic, OpenAI, Google, xAI, and others
- observability across multiple agents
- built-in email addresses for your agents
- ready-to-run virtual coworkers
npm install -g @hybridaione/hybridclaw
hybridclaw onboarding
hybridclaw gateway
hybridclaw tuiOpen locally:
- Chat UI:
http://127.0.0.1:9090/chat - Admin UI:
http://127.0.0.1:9090/adminfor channels, scheduler, audit, and config - Agents UI:
http://127.0.0.1:9090/agents - OpenAI-compatible API:
http://127.0.0.1:9090/v1/modelsandhttp://127.0.0.1:9090/v1/chat/completions
Requirement: Node.js 22 (Docker recommended for sandbox)
Release notes live in CHANGELOG.md, and the browsable operator and maintainer manual lives at hybridclaw.io/docs.
Once the gateway is running, open HybridClaw locally:
- Web Chat:
http://127.0.0.1:9090/chat - Admin Console:
http://127.0.0.1:9090/adminfor channels, scheduler, audit, and config - Agent Dashboard:
http://127.0.0.1:9090/agents - or connect Slack, WhatsApp, Telegram, Discord, Microsoft Teams, Email
| Capability | HybridClaw | OpenClaw | Hermes Agent |
|---|---|---|---|
| Self-hosted runtime | ✅ Gateway + sandboxed container runtime | ✅ Self-hosted gateway/runtime | ✅ Self-hosted gateway/runtime |
| Migration support | ✅ Imports from OpenClaw and Hermes | ❌ No comparable import path surfaced | |
| Encrypted secrets | ✅ Encrypted store + SecretRefs | ||
| Approvals / governance | ✅ Approvals, audit trails, sandbox, config history | ||
| Memory / knowledge | ✅ Shared memory + HybridAI knowledge path | ||
| Multi-agent observability | ✅ Built-in audit surfaces + platform path | ||
| Local + cloud deployment model | ✅ Local-first runtime with HybridAI cloud path plus SSH/Tailscale remote access | ✅ Local, VPS, Docker, Modal, Daytona | |
| Multiple UIs | ✅ TUI + Chat UI + Admin UI + Agents UI | ✅ TUI + WebChat + Control UI |
| Comparison point | HybridClaw | LangChain | n8n |
|---|---|---|---|
| Framework vs runtime | Runtime | Framework | Workflow builder |
| Coding required | Low to medium | High | Low |
| Workflow builder vs agent runtime | Agent runtime | Framework for building agent systems | Visual workflow builder |
| Enterprise controls | ✅ Approvals, audit, sandbox, encrypted secrets |
- secure credential storage
- sandboxed execution
- approvals
- audit trails with hash chain
- config versioning and backup/rollback
- observability
- channels
- browser sessions
- office docs
- skills / plugins / MCP
- persistent workspaces
- import from OpenClaw / Hermes
- portable
.clawpackages with bundled knowledge and skills - local-first to cloud-ready path
- Gateway service (Node.js) — shared message/command handlers, SQLite persistence (KV + semantic + knowledge graph + canonical sessions + usage events), scheduler, heartbeat, web/API, loopback OpenAI-compatible API, and channel integrations for Discord, Slack, Microsoft Teams, Telegram, iMessage, WhatsApp, and email
- TUI client — thin client over HTTP (
/api/chat,/api/command) with a structured startup banner that surfaces model, sandbox, gateway, and chatbot context before the first prompt, an interactive approval picker for pending approvals, and an exit summary with a ready-to-run resume command - Container (Docker, ephemeral) — HybridAI API client, sandboxed tool executor, and preinstalled browser automation runtime with cursor-aware snapshots for JS-heavy custom UI
- Communication via file-based IPC (input.json / output.json)
Browse the full manual at hybridclaw.io/docs.
- Getting started: Installation, Authentication, and Quick Start
- Enterprise deployment: Runtime Internals and Architecture
- Operations: Remote Access
- Security: SECURITY.md and TRUST_MODEL.md
- Migration: Commands: Migration and FAQ
- Channels: Connect Your First Channel, Overview, Discord, Slack, Telegram, Email, WhatsApp, iMessage, and Microsoft Teams
- Skills and plugins: Extensibility, Bundled Skills, Plugin System, GBrain Plugin, Honcho Memory Plugin, and MemPalace Memory Plugin
- Configuration: Configuration Reference
- CLI reference: Commands, Diagnostics, and FAQ
Contributor quick start:
npm install
npm run setup
npm run build
npm run typecheck
npm run test:unitUse npm run typecheck, npm run lint, and targeted tests for code changes.
For docs-only changes, verify links, commands, and examples. GitHub issue forms
cover bug reports, setup help, feature requests, and docs fixes, and the PR
template asks for validation and scope boundaries up front. See
CONTRIBUTING.md for the full workflow, check matrix, and
community guidance.
- Discord: discord.gg/jsVW4vJw27
- Issues: github.com/HybridAIOne/hybridclaw/issues
- Discussions: github.com/HybridAIOne/hybridclaw/discussions
- Support guide: SUPPORT.md
- Community standards: CODE_OF_CONDUCT.md