Self-host NextClaw
nextclaw@0.59.3Long-term AI partner running on your own infrastructure
- Stars
- 262
- CPU
- 2 vCPU
- RAM
- 2 GiB
- Port
- 55667 (HTTP web interface)
What is NextClaw?
NextClaw is a self-hosted AI workspace designed as a long-term personal partner instead of a task-focused helper. You can run it on macOS, Windows, Linux, Docker, or cloud VMs, keeping full control of your data. It connects to hosted models such as OpenAI, Anthropic, and Gemini, plus local models through Ollama and vLLM. Messaging integrations cover WeChat, Feishu, Telegram, Discord, Slack, and email. Core features include dedicated agents with persistent memory, scheduled tasks, browser automation, local file handling, image generation, and Panel Apps that keep interactive tools next to conversations. A built-in free tier works without an API key. The codebase is MIT-licensed and under active development toward a 1.0 release with proactive analysis and self-improvement.
Should you self-host NextClaw?
NextClaw scores 49/100 on selfhost.directory (how scoring works) and ranks #47 of 120 in AI Assistant. It has 262 GitHub stars.
It shipped 1 stable release in the past year. The latest, nextclaw@0.59.3, came out on 19 October 2026.
Setup is moderate: expect some configuration beyond a single command. It is MIT-licensed and written mostly in Typescript.
Its closest alternative on selfhost.directory is hermes-agent (89/100, 257 989 stars). It scores higher overall, so compare the two before you pick. See NextClaw vs hermes-agent side by side.
Features
- Agent runtime selection
- Browser Automation
- Built-in free trialLimits and models may change; not for sensitive data
- CLI Interface
- Dedicated agents
- Doc Browser
- Image Generation
- Local file processing
- Messaging channel integrations
- Multi-Model Support
- Panel Apps
- Proactive background delivery
- Remote Access
- Scheduled Tasks
- Skills and MCP Servers
NextClaw README
FAQ
What is the difference between NextClaw and OpenClaw?
NextClaw is inspired by OpenClaw and stays compatible with its plugin ecosystem. Key differences: one-command startup with built-in UI for configuration, smaller codebase (~1/20 of OpenClaw) for easier maintenance, and better support for Chinese domestic channels like QQ, Feishu, and DingTalk.
More in AI Chat
nextcloud-mcp-serverA self-hosted, open-source MCP server that lets AI assistants interact with your Nextcloud instance — managing notes, calendars, contacts, files, and more.
nextgptNextGPT is a self-hosted AI chatbot with document processing, RAG search, and web search. Deploys via Docker Compose or to AWS/GCP.
nextjs-vllm-uiSelf-hosted, open-source web interface for vLLM and Ollama that provides a ChatGPT-like experience with local chat storage, dark mode, and responsive design.
novaSelf-hosted personal AI with a measured memory loop and 70+ autonomous monitors building living dossiers — all local, zero cloud.
obrew-studio-serverSelf-hosted, open-source AI engine that runs LLMs locally with RAG, agents, and workflow automation — no cloud dependency, all data stays on your device.
Ollama GUIOpen-source, self-hosted single-page chat front end for models served by your own Ollama, with streamed answers, vision uploads, model pulling and browser-side history.
OllamaUIOllama UI is a self-hosted, open-source web interface for exploring, pulling, and managing Ollama models with chat, tool calling, and Telegram bridge.
omadiaSelf-hosted, open-source agentic OS for running multi-agent AI teams on your own infrastructure with privacy controls and audit trails.
OmniOmni is a self-hosted, open-source AI agent connecting to workplace tools like Google Workspace, Microsoft 365, Slack, and Jira to gather context and execute tasks.
Onyx Community EditionOpen-source, self-hosted AI enterprise search and chat: connectors index 50+ apps with permissions, then RAG search, custom agents and LLM chat run on any provider.
OpenAgentdOpenAgentd is a self-hosted, open-source desktop application that runs a local coding agent, displaying every tool invocation, code change, and token cost as it works.
openclaw-voiceSelf-hosted browser voice interface for AI assistants. Runs Whisper locally, uses ElevenLabs or local TTS, connects to OpenAI, Claude, or custom agents.
0 comments