Miaotofu01/Study-Mate
Your AI learning companion: helping you plan your studies, understand concepts, and build projects to master a subject.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via npm
Resolves a published tarball rather than cloning the repository.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/desktop/pnpm-workspace.yaml.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 6d agoon DeepSeek Harness 0.2.1-rc.5.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.1-rc.5, 6d ago.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
shell commands (bash, exec, spawn …)
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — StudyMate is a DeepSeek Harness learning mode plugin that helps with planning courses, understanding concepts, and building projects for math and computer subjects.
Who it is for — When using DeepSeek Harness learning mode to learn math or computer subjects and requiring a structured course roadmap and cross-subject shared memory, StudyMate provides structured learning support. If you use other self-study tools or traditional textbook methods without relying on DSH learning mode presets, StudyMate's integration advantage is limited.
Watch out — Sandbox testing passed; it was correctly registered after installation in a fresh profile. The plugin executes shell commands during installation. No other obvious issues found.
The verdict — I would install it because it provides cross-subject shared memory, allowing subsequent subject learning without reintroducing myself, but only if using DeepSeek Harness learning mode.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
Study-Mate is a DeepSeek Harness plugin that turns learning a mathematics or computer-science subject into a file-backed workflow of planning, explanation, practice and project work.
DeepSeek Harness loads Study-Mate through its “learning mode” preset and reading endpoint. A new session can create or resume a subject from a prompt such as “I want to learn C++”. The plugin writes the resulting outline, lessons, progress and records to the configured learning workspace, which defaults to ~/StudyMate; shared memory files retain a learner’s level, effective explanations and recurring difficulties across subjects. Study-Mate can also collect local reference material and online sources into reference/ and sources/, and export a static copy to <workspace>/export/ with npx -y @yunmiao/studymate export.
Study-Mate is intended for learners who want a structured route through a subject rather than an unrecorded chat, particularly in mathematics and computing. It is a poor fit for a general-purpose course platform, or for installations that require the independent web runtime: that runtime has been moved to the web/0.7.0-beta branch. The plugin reaches the terminal through its native tool surface to read supplied local materials, maintain the workspace and run export-related commands, so its installation should be given only the permissions appropriate for those files and operations. It does not require Python; static export additionally needs React available through npm or STUDYMATE_REACT_DIR.
DeepSeek Harness installs Study-Mate as the @yunmiao/studymate package. Its DSH side combines a learning-mode preset, host-side native tools and a client-side reading endpoint. In a new DeepSeek Harness session, selecting “learning mode” and naming a subject starts course discovery or course creation. The reading endpoint renders lesson pages, formulae, illustrations and questions in real time rather than serving pre-generated HTML.
The learning workspace is configured during installation; an existing configuration is retained. The default location is ~/StudyMate. Study-Mate stores subject folders, outlines, lessons, labs, progress and records there. Shared memory files hold information such as the learner’s current level, preferred explanations and recurring difficulties. Supplied local notes, lectures or textbook directories are converted to Markdown under reference/; collected online material is written as Markdown under sources/.
npx -y @yunmiao/studymate export creates an offline-readable copy in <workspace>/export/. Static export needs React, installed globally with npm i -g react react-dom, or located through STUDYMATE_REACT_DIR.npm test runs the project’s self-checks. The tests create temporary subjects and do not use the real learning workspace, DeepSeek Harness, a browser or a model service.DeepSeek Harness requires 0.1.7-alpha.1 or newer. The package advertises Node.js 22.19+ or 24; Python is not required. Web and desktop profiles are documented for DeepSeek Harness. Codex, ChatGPT Work and Google Antigravity support is limited to version v1.0.0; later versions are not guaranteed on those hosts.
Study-Mate’s current mainline does not contain the independent web runtime. The runtime is on the web/0.7.0-beta branch and must be adapted to the current engine before being merged. DeepSeek Harness users should open the reading endpoint from the session sidebar to view generated lessons; exporting is the documented route for an offline copy.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
loopx-project
LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
huangruiteng
LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
Q00
Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
chuspeeism
Embeds the active installed Codex Taskboard runtime in the DeepSeek Harness sidebar, using its launcher runtime descriptor instead of a fixed port.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
NanmiCoder
AgentTeams multi-agent teams.
DeepSeek Harness 0.2.1-rc.5 refuses the latest release
EthanYoQ
Installs a dedicated AI novel-writing preset and workbench: revisioned local project assets, a compact side drawer, and native approval-gated single-file changes.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.