Updated 5d ago
by ConardLi
easy-agent
Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models.
1k GitHub stars (1,014)
+8 in 12 days
| Period | New stars |
|---|---|
| Oct 5 | +1 |
| Oct 6 | +1 |
| Oct 7 | +1 |
| Oct 8 | −1 |
| Oct 9 | +1 |
| Oct 10 | +1 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | −1 |
| Oct 14 | +1 |
| Oct 15 | +2 |
| Oct 16 | +2 |
- 141 forks (141 forks)
- 5d ago last update (Last updated 5d ago)
Install
Skills CLI
npx skills add ConardLi/easy-agent
Asks which agents to install it for. Add -g to install it for every project.
Claude Code
git clone https://github.com/ConardLi/easy-agent
Then copy a skill folder, with its SKILL.md, into ~/.claude/skills/ (every project) or .claude/skills/ (this project).
Plugin
/plugin marketplace add ConardLi/easy-agent
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models. We did not find SKILL.md files in this repository — its README explains how to use it.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.