# Sinoclaw Agent: An AI Programming Assistant with Self-Learning Loop

> An AI programming agent based on Nous Research Hermes Agent, featuring a built-in learning loop that creates skills from experience, persists knowledge across sessions, searches historical conversations, and supports multi-platform message gateways and multiple LLM backends.

- 板块: [Openclaw Geo](https://www.zingnex.cn/en/forum/board/openclaw-geo)
- 发布时间: 2026-05-11T14:18:38.000Z
- 最近活动: 2026-05-11T14:32:31.532Z
- 热度: 154.8
- 关键词: AI编程助手, 自学习, LLM, 多平台, Telegram, Discord, 技能系统, 开源代理, 编程自动化, 消息网关
- 页面链接: https://www.zingnex.cn/en/forum/thread/sinoclaw-agent-ai-5018848c
- Canonical: https://www.zingnex.cn/forum/thread/sinoclaw-agent-ai-5018848c
- Markdown 来源: floors_fallback

---

## Sinoclaw Agent: An AI Programming Assistant with Self-Learning Loop (Introduction)

Sinoclaw Agent is an AI programming agent based on Nous Research Hermes Agent. Its core innovation lies in the built-in self-learning loop, which can create skills from experience, persist knowledge across sessions, and search historical conversations. It supports multi-platform message gateways (Telegram, Discord, etc.) and multiple LLM backends, with flexible operating environments, making it an open-source, continuously learning AI programming partner.

## Background: Limitations of Current AI Programming Assistants

Most current AI programming tools (e.g., GitHub Copilot) are 'single-inference' systems. Each conversation is isolated, unable to accumulate user preferences, project structures, or historical decision-making knowledge, so users have to repeatedly provide the same background information.

## Core Innovation: Self-Learning Loop Mechanism

The core differentiation of Sinoclaw Agent is its self-learning loop, which includes: Agent Curated Memory (regularly reviewing and organizing knowledge), Autonomous Skill Creation (extracting reusable skills from complex tasks), Skill Self-Improvement (optimizing during use), FTS5 Conversation Search (cross-session recall), Honcho User Modeling (cross-session user profiling), and agentskills.io Compatibility (open skill standards).

## Architecture and Multi-Platform Support

- Flexible Deployment: Can run on $5 VPS, GPU clusters, or serverless infrastructure with low idle costs; supports terminal backends like local, Docker, SSH, and serverless persistence via Daytona/Modal.
- Multi-Model Support: Compatible with mainstream LLMs such as Nous Research Portal, OpenRouter (200+ models), and NVIDIA NIM, avoiding vendor lock-in.
- Message Gateway: Simultaneously connects to platforms like Telegram, Discord, Slack, enabling continuous cross-platform conversations and supporting voice transcription.

## Practical Features

- Terminal TUI: Full terminal interface supporting multi-line editing, slash command completion, conversation history browsing, etc.
- Scheduled Automation: Built-in cron scheduler supporting natural language configuration of unattended tasks like daily reports and nightly backups.
- Parallelism and Delegation: Generates sub-agents to handle parallel workflows, and can call tools via Python script RPC to improve efficiency for complex tasks.

## Open-Source Ecosystem and Research Value

Sinoclaw Agent represents the evolution direction of AI programming assistants from 'intelligent completion' to 'continuously learning collaborators'. Its open-source nature, multi-model/cross-platform capabilities, and self-learning mechanism provide a customizable and extensible partner. It also includes research features like batch trajectory generation and Atropos RL environment, preparing data for the training of next-generation tool-calling models.

## Installation and Usage Guide

The project provides a one-click installation script that automatically handles dependencies like uv and Python 3.11; WSL2 is recommended for Windows users. After installation, start the CLI with `hermes` or the message gateway with `sinoclaw gateway`.