MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Diff two huge text files under a fixed memory limit: summary, hunks and the next difference.
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 4/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 16/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
通过 3/3 项检查 · 在你的电脑上运行
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
用 Rift 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Rift,或回答中出现 Rift 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Rift
Rift 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
Claude Code 暂时无法连接 Rift
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Rift 的应用
Cursor 暂时无法连接 Rift
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Rift 的应用
VS Code 暂时无法连接 Rift
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Rift 的应用
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过 GitHub 账户 rubtsov-stan 验证,该账户拥有此仓库
代码最后更新于今天
使用 Apache-2.0
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/rubtsov-stan-rift-mcp)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于今天,最新版本(0.4.0)于昨天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。
同一分类中有:Puter MCP, XcodeBuildMCP, Vexa, Atlassian Rovo MCP Server, Anki MCP Server
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Connect to Atlassian Jira, Confluence, Loom, and more to search, create, and manage your work.
MCP server for Anki flashcards: adaptive review, notes, media, and deck management via AnkiConnect.
| 本项 Rift | Puter MCP | XcodeBuildMCP | Vexa | Atlassian Rovo MCP Server | Anki MCP Server | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 需要安装在电脑上 |
| 需要密钥 | 否 | 否 | 否 | 是 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 是 | 否 |
| 基础检查 | 3/3 | 4/4 | 3/3 | 2/4 | 4/4 | 3/3 |
| 许可证 | Apache-2.0 | AGPL-3.0 | MIT | Apache-2.0 | Apache-2.0 | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Rift
Diff huge text files under a hard memory limit.
Rift diffs large text files under a heap limit you set on the command line (--mem, 256 MiB by default). It writes a unified diff that patch applies to the first file to get the second, and has a terminal view that lets you jump through the differences before the whole diff is done.
Use it on database dumps before and after a migration, CSV or NDJSON exports, generated fixtures and large golden files: inputs where diff or git diff run out of memory. The largest pair measured so far is 50 GiB.
| Pair, each of A and B | Tool | Time | Peak memory |
|---|---|---|---|
| 256 MiB | rift --mem 256M | 0.21 s | 108 MiB |
| 256 MiB | GNU diff | 1.62 s | 776 MiB |
| 256 MiB | git diff --no-index | 2.58 s | 1.0 GiB |
| 1 GiB | rift --mem 256M | 0.53 s | 109 MiB |
| 1 GiB | GNU diff | killed at a 3 GiB cap | |
| 1 GiB | git diff --no-index | 42.66 s, no diff (binary) | 5 MiB |
| 50 GiB, on a SATA SSD | cat a b (the disk's rate) | 218.7 s, 491 MB/s | 8 MiB |
| 50 GiB, on a SATA SSD | rift --summary --mem 256M | 299.8 s, 358 MB/s | 107 MiB |
| 50 GiB, on a SATA SSD | rift --mem 256M, diff output 1.2 GiB | 456.8 s, 235 MB/s | 113 MiB |
Generated SQL pairs (rift-gen --seed 7, 0.1% of lines changed). Intel i5-10600, 16 GB RAM, Ubuntu 26.04, governor powersave (intel_pstate), Rift at 94bdbb1, 2026-11-14. The 256 MiB and 1 GiB pairs were in tmpfs (medians of five runs). The 50 GiB pair was read from a Samsung SSD 860 (one run each, page cache not dropped, the pair 6.7 times the RAM), so that run is disk-bound. Peak memory is the resident set; Rift's heap stayed under 81 MiB in every row. Command: bench/linux-safe.sh --suite standard --reps 5 --ref main --disk-dir DIR. Source: bench/results/linux-intel-core-i5-10600-2026-11-14/. More rows and the Apple M1 table are on the benchmarks page.
Each GitHub release has binaries for macOS and Linux on x86_64 and arm64, and a shell installer:
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/rubtsov-stan/rift/releases/latest/download/rift-diff-installer.sh | sh
On Debian and Ubuntu, download the .deb for your architecture (amd64 or arm64) from the release page and install it with apt, which also resolves its dependencies:
sudo apt install ./rift-diff_VERSION-1_amd64.deb
It installs rift and its man page. There is no apt repository. Each .deb has a checksum file next to it on the release page:
sha256sum -c rift-diff_VERSION-1_amd64.deb.sha256
From source, with Rust 1.97 or later:
cargo install --git https://github.com/rubtsov-stan/rift rift-diff
Add --no-default-features to build without the terminal interface; -i and rift tui then exit with status 2.
Each release archive carries a build provenance attestation. To check one you downloaded, with the GitHub CLI:
gh attestation verify rift-diff-x86_64-unknown-linux-gnu.tar.xz --repo rubtsov-stan/rift
The binary is called rift.
rift a.sql b.sql > changes.patch # unified diff, as diff -u prints it
patch a.sql changes.patch # a.sql is now b.sql
Exit codes follow diff: 0 when the files are identical, 1 when they differ, 2 on an error. Both operands must be regular files, or both directories (see below); symbolic links given as operands are followed. Rift reads at offsets, so a pipe, a FIFO or <(command) is refused with exit 2. Write the input to a file first. - is a file name, not standard input.
New in 0.4. Given two directories, Rift compares the trees and prints what diff -r prints: Only in lines for files in one tree, a unified diff under a diff -r A/x B/x header for each changed file, and Binary files ... differ for a file with a NUL byte in its first 8 KiB. A file only in A and a file only in B with the same bytes are one Renamed: line. Symbolic links are compared by target, not followed. --summary prints one status per path (A, D, M, R, T) and the counts.
rift old-dump/ new-dump/ > changes.diff
The whole tree runs under one --mem, one directory at a time: a tree can hold millions of files, but one directory's listing must fit in a quarter of the limit, 8 bytes per entry plus its name, on each side. At the default 256M that is about 2 million entries with 8-byte names in a directory both trees have. A directory that does not fit is refused with a limit to rerun with. Files that change during the run are not detected. For pg_dump -Fd, dump with -Z0 (--compress=0), or every table shows as Binary files ... differ; reading the .gz files is #73.
The site has a guide to every mode (the terminal view, --summary, key mode, moved blocks, --mem, exit codes), pages for common searches, how Rift works, the benchmarks with their commands, and the man page: https://rubtsov-stan.github.io/rift/. The design and its invariants are in DESIGN.md.
What's next: https://rubtsov-stan.github.io/rift/roadmap/
--mem. Rift reserves every allocation on the data path from the budget first and reads files with pread into fixed buffers, never mmap. The tests and CI check the peak with a counting allocator.approx: and the reason after the hunk header, where diff -p puts a function name and patch ignores it. The terminal view draws the region in yellow, and --stats counts it by reason.git, it can show a change as larger than the smallest possible one.rift-gen low-entropy profiles, seed 7, rift --stats --mem 256M, Intel i5-10600, Linux, 2026-11-14.)--summary, --stats and the terminal view name moved blocks, but only those that contain a sampled line, so they can miss some.--mem. The resident set also holds the binary, thread stacks and whatever page cache the kernel counts against the process.rift git-diff is git's external diff command, for files git would call binary. It ships in 0.3.0. The git guide has the .gitattributes setup, the LFS behaviour and the cost of the temporary copy git makes.
rift-mcp serves a diff to an MCP client, so the client reads a few kilobytes about two huge files instead of the files. Besides the line diff it compares CSV, NDJSON and pg_dump records by key: counts of added, removed and changed keys, and pages of changes with the fields that differ. It is released next to rift; see the MCP guide.
An extension shows the difference map and the moved blocks of two huge files in a side panel and opens each difference in VS Code's diff editor, on just that excerpt. It is built on rift serve, the same engine and --mem limit as the command line. See the extension README. Install it from the Visual Studio Marketplace or Open VSX.
Rift is dual-licensed under MIT and Apache 2.0, like Rust itself, so you can use it under whichever fits your project. See LICENSE-MIT and LICENSE-APACHE.