NagaAgent
Desktop AI assistant with a Live2D avatar, knowledge-graph memory, voice, MCP and skills, under AGPL-3.0 or a commercial license.
Agent by RTGS2017
Get started
Setup steps are in the repository. Website · Repository
About
Use cases: personal-assistant, agent-memory, workflow-automation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Jobs
- personal assistantREADME
- Where you use it
- Desktop app, Voice, otherREADME
- Hosting
- You run itREADME
- Models
- anthropic, google, deepseek, kimiREADME
- Interfaces
- mcp, agent-skillsREADME
- Open source
- YesREADME
- Billing
- Some hosted search and model calls are billed in NagaBusiness points; when signed out or with the gateway off it uses the user's own API keys.README
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.
Built on
Frameworks named in its dependency files.
- 0.753score
LangChain
LangChain
Python framework of interoperable components and integrations for building agents and LLM apps, with LangGraph and Deep Agents layered above it.
HarnessAFreshness: A★ 148.4K↓ 37.3M/wk - 0.714score
LangChain.js
LangChain
JavaScript and TypeScript framework of interoperable components for building LLM apps and agents, with LangGraph.js and Deep Agents above it.
HarnessAFreshness: A★ 18.3K - 0.705score
LangChain4j
LangChain4j
Java library with one API over LLM providers and vector stores, plus tools, RAG and integrations for Quarkus and Spring Boot.
HarnessAFreshness: A★ 13.3K - 0.695score
LangChainGo
LangChainGo
Go implementation of LangChain for writing LLM-based programs from composable building blocks.
HarnessAFreshness: A★ 9.7K - 0.633score
Langchain.rb
Patterns AI
Ruby library for LLM-powered apps with a unified LLM interface, prompt tools, output parsers, RAG and assistants.
HarnessAFreshness: A★ 2K
Signals
- Stars
- 1,544
- Forks
- 164
- Open issues
- 4
- Last commit
- Aug 11, 2026 (2 months ago)
- Last release
- Jul 16, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- AGPL-3.0
- Repository
- github.com/RTGS2017/NagaAgent
- Website
- space.bilibili.com/266938091
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- READMEgithub-graphql
More from RTGS2017
- 0.716score
file-manager
RTGS2017
文件管理技能。用于创建、移动、复制、删除文件和文件夹，整理目录结构。当用户需要管理文件、整理文件夹或批量处理文件时使用。
SkillCFreshness: C★ 1.5KClaude Code +9 - 0.716score
naga-config
RTGS2017
Naga 自身配置管理技能。用于查看和修改 Naga 系统设置、添加 MCP 工具服务、导入自定义技能、搜索可用 MCP 工具。当用户要求修改设置、添加工具或技能时使用此技能。
SkillCFreshness: C★ 1.5KClaude Code +9 - 0.716score
context7
RTGS2017
Context7 MCP via mcporter (stdio).
SkillCFreshness: C★ 1.5KClaude Code +9 - 0.716score
code-review
RTGS2017
代码审查和质量分析技能。用于审查代码、发现潜在问题、提供改进建议。当用户请求代码审查、代码质量分析或最佳实践建议时使用。
SkillCFreshness: C★ 1.5KClaude Code +9 - 0.716score
office-docs
RTGS2017
Extract text and tables from .docx and .xlsx using local scripts (no external deps).
SkillCFreshness: C★ 1.5KClaude Code +9 - 0.716score
openclaw-control
RTGS2017
控制和管理 OpenClaw AI 助手。用于发送消息给 OpenClaw、检查状态、管理配置和安装技能。当用户想要与 OpenClaw 交互或管理 OpenClaw 时使用此技能。
SkillCFreshness: C★ 1.5KClaude Code +9
Cite this page
NagaAgent. Agent Mart. https://agentmart.dev/agents/nagaagent (last updated 2026-10-24)