ranxianglei/billion-context
基本稳定可用 A context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).上下文压缩插件,兼顾小窗口(100k上下文足矣)省token(省5倍token)和超长会话(数月级别几十亿token单会话)。billion-context is all you need
Project Overview项目介绍
billion-context is a universal context compression proxy designed for long-lived AI coding agents. To install it globally on your system, you can run the single command npm install -g billion-context from any terminal with a supported version of Node.js installed. It works with any AI coding agent that supports setting a custom base URL for model APIs, including popular options like Claude Code, Codex, Cursor, Aider, and DSH. It requires no per-agent custom adapter code to get up and running, and supports both OpenAI and Anthropic request formats out of the box for most mainstream model endpoints.
This tool solves the common problem of context window overflow during long multi-day coding sessions, which can degrade model performance or end an active working session entirely. It uses model-driven incremental hierarchical compression to fold older conversation history into high-fidelity layered summaries, letting you run billions of cumulative tokens through a standard 200k-token context window without violations. It is built for developers who work on large long-term coding projects with AI agents, and want to reduce token costs while keeping uninterrupted sessions active over multiple days or even weeks.
billion-context is released under the permissive MIT open-source license, and its accompanying research paper is also hosted in the repository under the same license. It is currently marked as early-stage software, so users should expect minor rough edges and occasional unexpected behavior as active development continues. The project also hosts an open QQ group for community discussion, updates, and user support for all related compression tools. Windows users specifically need to add the default session storage directory to their antivirus exclusion list to prevent file locking errors that block session state saves.
billion-context 是一款通用的 AI 编码代理上下文压缩代理服务,可在任意支持自定义模型基础 URL 的编码代理与 OpenAI/Anthropic 格式的模型 API 之间工作,通过增量分层压缩技术压缩历史对话,支持 Claude Code、Codex、Cursor、DSH 等几乎所有主流 AI 编码代理,无需为每个代理编写专用适配代码。
用户只需将本地运行的代理地址填入编码代理的模型 base URL 配置即可启用,它会自动解析传入请求,运行压缩算法,注入上下文管理工具后转发请求到真实模型 API,适合需要进行长时间、多轮次编码开发,希望避免上下文窗口溢出、降低 token 成本的开发人员使用。
本项目采用 MIT 许可证开源,可通过 npm install -g billion-context 命令全局安装,目前处于早期开发阶段,存在部分粗糙边界问题,Windows 用户需要将会话存储目录加入杀毒软件排除列表,避免写入权限错误导致会话状态保存失败。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:billion-context(ranxianglei/billion-context)
仓库:https://github.com/ranxianglei/billion-context
本站详情页:https://www.yhbd.top/plugins/ranxianglei-billion-context/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 NOASSERTION · ⭐ 496 · 最近提交 2026-10-03 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号(星标、许可证、更新活跃度、清单完整度)
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add github:ranxianglei/billion-context
把 ranxianglei/billion-context 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
billion-context
Context-compression plugin — billion-context is all you need.
small context windows (100K is enough) · 5× fewer tokens · month-long single sessions (billions of tokens) · high compression quality
npm install -g billion-context
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

liangmianya/dsh-synapse
alaliqing/claude-paper
acryldev/acryl
omdsh-dev/dsh-annotation
Anionex/dsh-turn-rewind
Tyan66666/billion-context-dsh
qkycir-123/dsh-run2skill
hanshenmesen/dsh-turn-delete