AI tools that write, review, refactor or explain code, from editor extensions to terminal agents.
33 repositories in this category
Get this category's best new repositories in the weekly survey.
dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。
The online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it is live.
First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI.
一站式 Coding Agent 插件：从需求、研究、设计、原型到开发、测试、发布的全流程规则、Skills 与 Hooks，助力任何 0-1 的想法
Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Perspective
Ten levels of Jev, from one smart if statement to a coding agent that reaches for Jev on its own
Replay your coding agent sessions as a map and a timeline
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
Orchestrate multiple coding agents from desktop and mobile
An open-source AI coding agent that lives in your terminal.
The first real AI developer
A reliable coding agent for complex software engineering tasks.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
💫 Toolkit to help you get started with SDD or any other process!
A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry
Build an AI Coding Agent from Scratch in Pure Python, Step by Step | 用纯 Python 从零搭建 AI 编程 Agent，边实现边理解其工作原理
Pi Coding Agent 中文学习蓝皮书：从安装与第一个可验收任务开始，逐步掌握 Session、Context、Skill、Extension、Subagent 与长期 Agent 工作流。
400 interactive UI elements you can try live, then copy as an AI prompt or working code: 200 interface parts and 200 website sections and animations. Light/dark, MIT.
Short vertical cut-paper explainer reels, made by your coding agent. Nine Agent Skills plus a Remotion library. Works with Claude Code, OpenCode, Codex, Gemini CLI, Cursor, Copilot and more.
Salesforce DX code review: Apex, LWC, Flows, security (CRUD/FLS), governors, and Bugbot.
Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.
Reusable Codex + Claude Code skill and plugin implementing Anthropic's AI-Native SDLC: Plan → Design → Build → Test → Deploy → Maintain, with human approval gates at every handoff.