#121121st of 143 in Coding agents and AI editors
loushang
Terminal coding agent with persistent sessions and method-guided delivery
- Stars
- 1.7k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Loushang is a Python CLI and terminal workbench, `loushang code`, that runs coding turns against a model catalog with built-in tools, resumable sessions and project-level extensions. It also ships `loushang.ai`, an SDK with a model registry, streaming, tool calls and cost helpers. Work is structured through "methods" that define roles, phases and acceptance expectations.
Who it is for: Developers trying an early terminal coding agent with resumable sessions
Strengths
- Sessions can be resumed, forked, exported and diagnosed
- Project-level Python extensions add hooks, tools, commands and resources
- Reusable AI SDK with model registry, streaming and cost helpers
- Apache-2.0 licensed with docs and examples for CLI and SDK
Weaknesses
- README calls it early development; recommended install is from source
- No tagged release published
- Supported providers and models are not listed in the README
- Work, research and ppt surfaces are roadmap only
What it needs
- Needs uv, Python
Also in Coding agents and AI editors
See all 143| Rank | Project | Score |
|---|---|---|
| 1 | ArchonYAML workflow engine that runs AI coding agents through fixed dev steps | 84 out of 100 |
| 2 | claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs | 83 out of 100 |
| 3 | Open SWEAgent that turns issues into pull requests, reviews PRs and monitors CI | 83 out of 100 |
| #4 | piTerminal coding agent with extensions, skills, and an SDK | 80 out of 100 |
| #5 | oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory | 80 out of 100 |