search
LLM coding agents
Trends
- 1
Alibaba has released open-code-review, a Go-based code review tool it says is battle-tested at the company's scale. The tool combines deterministic analysis pipelines with an LLM agent, produces line-level comments, and ships with rulesets covering null pointers, thread-safety, XSS and SQL injection. It is compatible with OpenAI and Anthropic models, making it usable with common commercial AI providers.
Repos
- mhtsec/ARTEX AI 自主渗透测试系统 | 百度“agent+”攻防挑战赛冠军项目
- earendil-works/pi AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
- pbakaus/impeccable The design language that makes your AI harness better at design.
- alibaba/open-code-review Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipe
- JuliusBrussee/caveman 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking l
- twostraws/SwiftUI-Agent-Skill SwiftUI agent skill for Claude Code, Codex, and other AI tools.
- newliver666/apk-reverse Suitable for Android APK reverse engineering analysis
- sshah03/perspica Review code changes by what they do, not line by line.