Devon:开源结对程序员
ai-software-engineer 开源项目推荐(30 个)
ai-software-engineer 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 30 个仓库TypeScript AI platform with AI chat, Autonomous agents, Software developer agents, chatbots and more
ATLAS:Claude Code 的高级工程师层。用线框图和原型来探索,澄清要点,用活生生的HTML捕捉,然后让Claude Code的原生计划/目标/工作流程循环逐步构建。少点代币,少些仪式感,比大家想象的更快。吻/雅格尼/干,语境决定。不要过度设计。干净且有效的建筑。
A simplified version of Devin the AI software engineer
Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven, evidence-gated, parallel feature voyages.
Autonomous AI Agent orchestrator for software development. Multi-instance AI coding agents (gnomes) automate SDLC pipelines, pick tasks from GitHub/Jira trackers, and run securely in container sandboxes.
Kevin is an advanced AI Software Engineer designed to streamline various tasks related to programming and project management. With sophisticated capabilities in code generation, Kevin can assist users in translating ideas into functional code efficiently.
codinit.dev demo AI app builder
Reason Agent, the autonomous software engineer: how to use it, releases and benchmark results.
The Reason command line: start, follow and steer Reason Agent sessions from your terminal.
Open-source Claude Code plugin: a team of AI agents (product manager, architect, developer, QA, security, DevOps, FinOps) that builds software through review and approval gates.
The official open-source repository for community-built prototypes and tools powered by the Oxlo API
Autonomous AI-powered cloud agent — generates code fixes, validates in isolated cloud sandboxes (AWS Fargate/Docker), and opens pull requests automatically. Multi-LLM support (Claude, GPT-4, Groq). Built for developers, SREs, and platform engineers.
A Claude Code plugin that runs a multi-agent AI software team. A CEO interviews you, a CTO plans the build, developers build it phase by phase, and QA tests every phase. Each agent runs in a fresh claude -p session, and you watch and steer it all from a live dashboard.
An agentic AI software engineering platform built around a shared Project Brain for code intelligence, security analysis, intelligent code reviews, bug memory, and living documentation.
Enhance your AI-assisted development in Copilot or Cursor with this advanced system prompt. 🤖✨ It provides a detailed playbook that transforms your AI into a methodical 'Minion', ensuring more systematic execution and higher quality software engineering.
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 51.6% tasks (pass@3) in SWE-bench verified with each task costs less than $0.7.
Let Kore Agents handle the core of your work while you focus on the details
Autonomous AI Software Engineering Agent & Rust/Python Multi-Model Coding Runtime. Features native AST code synthesis, tool-calling execution loop, multi-LLM API routing (Gemini, Claude, NVIDIA NIM), and terminal/IDE automation.
🧠 Organized OpenAI/Codex workspace starter featuring local seed memory systems, standardized research archiving, and structured AI agent rules.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/ai-software-engineer。
- 该话题在 GitHub 上共有 30 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 5358 Star,覆盖 6 种主要语言,数据更新于 2026-11-11。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。