easy-agent
Terminal coding agent with permission rules, OS sandboxing, MCP, skills and sub-agents, for Anthropic, OpenAI-compatible, Gemini and local models
Agent by ConardLi
IndexedMIT★ 1,016
Get started
Setup steps are in the repository. Repository
About
Easy Agent, run as eagent, reads code, edits files and runs commands in a repository, with actions gated by allow, ask and deny permission rules and workspace trust. Plan Mode proposes a change read-only before anything is carried out, and optional shell sandboxes restrict commands on macOS and Linux. It supports Anthropic, OpenAI-compatible, Gemini and local models, and extends through MCP servers, skills, hooks and plugins.
Use cases: coding, code-generation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Jobs
- codingREADME
- Autonomy
- Supervised: runs multi-step tasks, asks at checkpointsREADME
- Where you use it
- Terminal, IDEREADME
- Hosting
- You run itREADME
- Models
- anthropic, openai, google, local modelsREADME
- Interfaces
- mcp, acp, agent-skills, sdkREADME
- Open source
- Yes
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.
Signals
- Stars
- 1,016
- Forks
- 137
- Open issues
- 31
- Last commit
- Oct 17, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ConardLi/easy-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- READMEgithub-graphql
Cite this page
easy-agent. Agent Mart. https://agentmart.dev/agents/easy-agent (last updated 2026-10-24)