隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载，只有在你同意后，Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
Source control for agents. Use multiple coding agents, track they change, and query them in one place
这个仓库详情页已经具备足够的原创分析、来源证据和同类对比，可以作为 Git-Stars 的可索引评测页。
100
评测分
解决的问题
Atlas solves the problem of agents starting from zero each session and losing context when switching between different coding agents. It also addresses the lack of visibility into agent actions by recording and making queryable all changes, decisions, and history, which is not provided by existing agent tools.
部署现实
当前可用的安装信号是：Download from https://github.com/pacifio/atlas/releases。这只能作为起点，正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 MIT。这是重要的商业使用信号，但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build complex multi-agent workflows where multiple coding agents collaborate on the same codebase with shared memory and context. They can track every change, query past sessions, and integrate agent knowledge into prompts. The ceiling includes running parallel agent sessions, maintaining a persistent knowledge base, and enabling seamless agent switching without loss of context, suitable for large-scale software projects.
Git-Stars 是独立产品，不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
pacifio/atlas 被追踪为 TypeScript 项目，主要属于 AI Agent, MCP Server, AI App, Developer Tool 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则，而不是复制项目文档。
增长检查：该仓库目前有 1.0k Star，今日 +123，本周 +0，本月 +0。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查：当前活跃度为 一般；最近一次推送距今 60 天，未关闭 Issue 为 24，约占总 Star 的 2.31%。这只是采用信号，不替代工程尽调。
采用检查：177 Fork 和 1.0k Watcher 反映项目被复用和关注的程度。许可证信号：MIT。商业或内部使用前请核验许可证兼容性。
适用判断：当你需要「AI 原型、LLM 工作流和 Agent 类应用」时，这个项目更值得评估；如果「需要法律审查、安全审计或生产 SLA 保证」，则需要谨慎。
来源检查：Git-Stars 当前为这份报告保留了 2 个明确来源引用，近期增长信号为 123。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
充分已附带仓库元数据和 README/来源引用。
许可证
充分已记录 MIT，可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
1.0k 星标
复用
177 复刻
关注
1.0k 关注者
维护
moderate
许可证
MIT
未解决 Issue
24
Atlas is an open-source source control tool for coding agents, enabling parallel execution of multiple agents like Claude Code and Codex while tracking their changes, sessions, and decisions. It provides shared memory and context across agents, ensuring continuity and queryability of agent activity.
核心特性
- Run multiple agents in parallel with independent streaming sessions. - Shared memory across agents: decisions and plans from one agent are visible to others. - Local-first storage with on-device embedding and queryable session history.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
MCP Server
Model Context Protocol servers, clients, and integrations
AI App
End-user AI applications and AI-native product examples
Developer Tool
Tools that improve coding, testing, build, and local workflow
Download from https://github.com/pacifio/atlas/releases63
健康评分
一般
提交活跃度
May 14, 2026
创建于
Aug 15, 2026
最近提交
每日同步积累数据后，Star 历史将在此显示。
复刻
未解决
关注者
pacifio
GitHub 主页codecrafters-io/build-your-own-x
Master programming by recreating your favorite technologies from scratch.
openclaw/openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
practical-tutorials/project-based-learning
Curated list of project-based tutorials
obra/superpowers
An agentic skills framework & software development methodology that works.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
Atlas solves the problem of agents starting from zero each session and losing context when switching between different coding agents. It also addresses the lack of visibility into agent actions by recording and making queryable all changes, decisions, and history, which is not provided by existing agent tools.
能力范围
Developers can build complex multi-agent workflows where multiple coding agents collaborate on the same codebase with shared memory and context. They can track every change, query past sessions, and integrate agent knowledge into prompts. The ceiling includes running parallel agent sessions, maintaining a persistent knowledge base, and enabling seamless agent switching without loss of context, suitable for large-scale software projects.
结论
Atlas is ideal for developers and teams who rely heavily on AI coding agents and need robust tracking, shared memory, and multi-agent coordination. It is not for those who prefer minimal tooling or work with a single agent without need for persistent context. The key trade-off is the added complexity of managing a source-control layer for agents versus the benefit of enhanced continuity and visibility.