openclacky
OpenClacky is an efficient, open-source AI agent that supports multiple tools and skills.
- Region
- Domestic
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 1.2k
- Views
- 1
- Source
- GitHub
- Added
- 2026-08-12
- Last verified
- 2026-08-12
Overview
OpenClacky is a high-performance open-source AI agent designed to deliver powerful capabilities at low cost. It significantly reduces token costs through high cache hit rates, a minimal tool set, and automatic compression. Users can create and invoke skills using natural language, and these skills can evolve autonomously. OpenClacky supports various instant messaging platforms (e.g., Feishu, WeChat, Discord) and allows free selection of OpenAI-compatible models. Ideal for developers and teams needing automation for task processing.
Key features
- ▪Low token cost
- ▪100% open source (MIT license)
- ▪Supports BYOK and multiple models
- ▪Skill self-evolution
- ▪Integration with multiple instant messaging platforms
Use cases
Pros
- ＋High cost efficiency
- ＋Highly customizable
- ＋Supports multiple platforms
- ＋Easy to install and use
Limitations / notes
- －Requires internet connection
- －Higher learning curve
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
Is it free?
Yes, OpenClacky is completely free and open source.
Does it support Chinese?
Yes, the project provides documentation in Simplified Chinese.
Can it be used commercially?
Yes, the project uses the MIT license, which permits commercial use.
Do I need to use a VPN?
No, but you need access to an OpenAI-compatible API.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.