NanoClaw

Active
GitHub TypeScript MIT

Description

A lightweight AI assistant platform running securely in containers. Connects to WhatsApp, Telegram, Slack, Discord, Gmail with memory, scheduled jobs, and built on Anthropic's Agents SDK.

Key Features

  • Container-level Isolation — Agents run in dedicated Linux containers with filesystem isolation, no host escape
  • Multi-channel Messaging — Supports WhatsApp, Telegram, Discord, Slack, Teams, WeChat and 12+ platforms
  • Flexible Isolation Model — Per-channel independent agents, shared agents, or cross-channel sessions
  • Scheduled Tasks — Configure recurring Claude jobs that auto-execute and return results
  • Skills Extension — Add channels and providers on-demand via /add-telegram commands, zero bloat
  • Credential Security — Agents never hold API keys; OneCLI Agent Vault injects credentials per-request

Use Cases

💡 Individuals deploy AI assistants to WhatsApp/Telegram for daily task automation and info queries
💡 Teams deploy shared agents via Slack/Teams for project coordination and knowledge sharing
💡 Families create multi-channel agents on Discord for news digests and schedule reminders
💡 Developers safely run code execution tasks in container isolation without host security concerns
💡 Content creators auto-generate daily briefings from Hacker News/TechCrunch via scheduled tasks

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (30.7k stars)
  • Permissive open-source license (MIT)

Categories

Quick Start

# Clone and start NanoClaw
git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2
cd nanoclaw-v2
bash nanoclaw.sh

# nanoclaw.sh auto-installs Node, pnpm, Docker
# Registers Anthropic credentials, builds agent container
# Configures messaging channels (Telegram/Discord/WhatsApp/CLI)

# Talk to your agent
# @Andy send a sales pipeline overview every weekday at 9am
# @Andy review git history for the past week each Friday

Related Projects

LangBot

17.6k · Python
Active A+

Production-grade platform for building agentic IM bots supporting Discord, Slack, LINE, Telegram, WeChat, Feishu, DingTalk, QQ, and more with Agent orchestration, knowledge base, and plugin system.

chatbotagentpython +2
  • · Supports 10+ IM platforms including Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Feishu, DingTalk
  • · Built-in agent orchestration, tool calling, multimodal support, streaming output, and RAG knowledge base
  • · Deep integration with Dify, Coze, n8n, Langflow and other major LLMOps platforms

XiaoZhi ESP32

29.6k · C++
Active A+

An MCP-based open-source chatbot for ESP32 embedded devices, supporting voice interaction, multi-model integration, and IoT control for building smart hardware agents.

chatbotvoicemcp +2
  • · MCP protocol device control — Device-side MCP controls speaker, LED, servo, GPIO; cloud-side MCP extends to smart home, email, and more
  • · Offline voice wake-up & recognition — ESP-SR offline wake-word detection, OPUS audio codec, streaming ASR + LLM + TTS architecture
  • · 70+ open-source hardware support — Compatible with ESP32-C3/S3/P4, LiChuang, ESP-BOX3, M5Stack, LILYGO and 70+ dev boards

Witsy

2.0k · TypeScript
Stale C

Witsy: desktop AI assistant and universal MCP client that connects to multiple AI models and tool services via the Model Context Protocol.

typescriptmcpagent +3
  • · Universal MCP client supporting any LLM provider including OpenAI, Anthropic, Google, Ollama, and more
  • · Prompt Anywhere feature generates content directly in any application via global keyboard shortcut
  • · AI Commands provide quick text-processing helpers (summarize, translate, rewrite) on selected text

Langchain-Chatchat

38.6k · Python
Stale B

A local knowledge base RAG and Agent application platform built on Langchain with support for ChatGLM, Qwen, Llama and other LLMs, offering conversation, knowledge base management, and agent capabilities.

ragllmpython +3
  • · Local knowledge base QA — Document loading, text splitting, vectorization and semantic retrieval via Langchain with BM25+KNN hybrid search
  • · Multi-framework model inference — Supports Xinference, Ollama, FastChat, LocalAI for GLM-4, Qwen2, Llama3 and more
  • · Agent tool calling — Optimized for ChatGLM3/Qwen with auto tool selection, single tool parameter parsing, and multimodal image chat