#320 · Primary category： AI Coding Assistants
loushang
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
Project last updated：08/29/26
GitHub Stars
1.3K
Forks
212
Contributors
2
License
Apache-2.0
Why we included this project
Loushang is a terminal workbench for running software development tasks through an AI agent. Its core idea is to treat the whole workflow as structured runtime objects rather than a simple chain of model calls, which makes long coding work more recoverable when context gets lost or execution is interrupted. Sessions persist, so you can resume a task after a break instead of starting over, and you can fork or export a session when you need to branch the work or move it elsewhere. A provider-aware SDK routes requests across GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax, so a team is not tied to one model vendor. The project is still early and meant to be run from source.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.