godspeed
Use this local MCP server to let an AI agent teach lessons and manage a learner’s godspeed study spaces, files, deadlines, notes, and knowledge graphs.
Receive and respond to work items such as lesson turns, Talk messages, background jobs, and knowledge-graph runs; read long or full work items.
List and read lessons, list and read spaces, and start new agent-taught study lessons.
Search a space’s knowledge graph and import notes as graph facts.
Manage spaces: create, update, archive, add files, link/unlink folders, and switch files between study material and space info.
Search space files by meaning/keywords and read specific passages or file ranges.
Add, update, and remove deadlines; mark them done; link covered files, left-out files, and assignment files.
Edit prep sheets, including date, description, mock settings, and topics.
Save or delete learner notes and lasting teaching-rule preferences.
Why I made it
I was using Claude to study for discrete math and it kept going in circles. I'd get stuck on a counting problem, work through it with Claude, and then ten days later I'd get stuck on basically the same problem in a new chat that had no idea we'd already done this. I even wrote a tutoring skill so it would give me hints instead of answers, but that didn't really help because every new chat still knew nothing about me.
So godspeed keeps all of that outside the chat. It saves your lessons, your answers, how sure you were on each one and a graph of what you know, and whatever agent you use (Claude Code, Codex or anything else with MCP) teaches from that.
Related MCP server: MoeReview
What a lesson looks like
The GIF up top is one topic of a lesson, and it goes like this.
Today tells you what to study next, and one button starts it.
While the teacher gets ready you can watch its plan and the page of your lecture it's reading.
It explains a step at a time and quotes your own lecture.
You answer and say how sure you are.
If you get it right the teacher can give you one sentence to keep, and it shows up again later.
Every topic ends at a stopping point, so you can quit there and pick it back up from Today.
Questions from older lessons come back when they're due, and godspeed asks and grades those itself without calling your agent.
What's in it
Part | What it does |
Spaces | One for each thing you study, like a course, a certification or a language. Each has its own lessons, files, graph, deadlines and cheat sheets. |
Files | PDFs, Word and PowerPoint files, EPUB books, notes, code, transcripts and lecture recordings. Or link a folder, Google Drive works too. |
Deadlines | Exams, homework, quizzes, projects and interviews. Today shows the next one big, with a button to start studying for it, and the week ahead as seven day columns with a Later column after them. |
Paths | No syllabus? Tell your agent your goal, like "I want to become a backend developer", and it writes a path of topics in order. Study takes the next one you haven't got down yet. |
Knowledge graph | What you've learned, as one picture of the space that zooms like a map. Each topic is a figure of its facts, and a fact lights up as you get it right. |
Progress | How ready you are for each deadline, and whether your confidence matches your results. |
Homework | Attach the assignment and the teacher goes through it one problem at a time. It gives you hints but never the answer. |
Mocks | Take a mock on any exam, quiz or interview deadline, timed or not. |
Cheat sheets | Your agent makes a PDF cheat sheet for a deadline, and you tell it what to change. |
Plugins | Small add-ons for a lesson or a space, like one that turns the question you're on into a meme. A plugin can't open your files. Add one in Settings or make your own. They're new, so how they work can still change. |
Calculator | End a calculation with |
Your agent's screen | Click your teacher's name in the top bar to open it. You can ask your agent to set up spaces or add deadlines there. |
How it works

The teacher figures out where your understanding stops, from your answers and how sure you were. It plans the steps from there to your next deadline, and each step builds on something you already get. You predict, read the explanation, then check yourself. After that you get problems where you have to pick the right idea on your own.
What you learn is saved as facts linked back to the lesson they came from, so the next lesson can build on them.
Get started
Download it with the buttons at the top, and it updates itself after that.
Mac needs macOS 14 or newer.
Windows will say "Windows protected your PC" because the app isn't signed there. Click More info, then Run anyway.
Linux also has a .deb for Ubuntu 22.04 or newer and Debian 12 or newer.
Open it and click Start Claude Code, or pick Codex under Use another agent. godspeed runs your agent inside the app in its own ~/godspeed folder, so it stays out of your other chats, and then you can start a lesson.
Any other MCP app works too, and Other app shows the address and token (Streamable HTTP, Authorization: Bearer <token>).
While godspeed is open it runs an MCP server on your computer. Only programs on your computer that hold the token can connect.
While you think, Claude Code waits in a background script, so it spends no tokens until you answer.
A second session of your agent reads your files and builds the graph in the background, so the teacher stays free for you.
Change command under Settings → Connection sets what godspeed runs instead of
claudeorcodex.In Claude Code,
/setup-spacesbuilds your spaces from your course files.Agents can save short notes about you (like "the midterm is over") so the next one knows. You can see and delete them under Settings → Teaching → Remembered.
Your data
It's your own agent on your own plan, so godspeed has no subscription or markup of its own.
Your lessons, graphs, files and settings stay on your computer as plain files you can read.
It isn't offline though, since your agent gets the context it needs for each task and web research fetches pages.
If you paste a Tavily key in Settings, your search words go to Tavily. Otherwise your agent uses its own web search.
The system prompts are visible and you can edit them.
Development
npm install
node scripts/fetch-model.mjs # once
npm run dev # http://localhost:3000
npm run check # everything CI runssrc/ is the React screens and crates/ is the Rust server and the Tauri shell. The development guide and architecture have the rest. Bugs and requests go to Issues.
License
AGPL-3.0. godspeed started as a fork of LearnHarness by Amos Blomqvist, keeps its teaching method, and is under the same license.
Available Tools
25 toolsadd_space_deadlineAdd deadlines to a spaceA
Add one or more deadlines to a space (send all of a space's deadlines in one call): exams, homework, quizzes and projects, each with its date, its time if it has one, and which of the space's files (notes, readings) it covers. godspeed uses this to show the learner what is due and what to work on first. Take the deadlines, their dates and times from the space info files (a syllabus, a schedule), and never make up a date or time. Work out what a deadline covers from the space's own files first: a practice exam or review sheet, the schedule, announcements (search_space_files). Link the files they point to (file_ids), list files from before it that it doesn't cover in left_out_ids, and say in source which file it came from. Ask only when the files don't settle it. File ids come from read_space with files: true. A deadline that is refused is listed under refused with the reason; the others are still added, so send only the refused ones again.
Inputs: space_id (required), deadlines (required).
add_space_fileAdd a file to a spaceA
Copy a file from this computer into a space. Supported: .md .txt, code files (.c .py .java .js and the like), plain text with no extension, .pdf .docx .pptx .epub, .vtt .srt (transcripts) and .mp3 .m4a .wav .mp4 .mov (recordings, transcribed locally with whisper.cpp). Google Docs links (.gdoc) need saving as PDF or Word first. Study files are turned into facts by you, through wait_for_work.
Inputs: kind (required), path (required), space_id (required).
create_spaceCreate a spaceA
Create a space for one thing the learner is studying (a university course, a certification, a language). The description is shown to the teacher in every lesson of the space: level, the book or source they follow, its notation, what they are working toward (a course's exams, an interview). Add the space's deadlines with add_space_deadline.
Inputs: icon (required), name (required), signature, description.
forgetForget a noteADestructiveIdempotent
Delete a saved note by its note_id (from "Where you left off" or from remember). Use it when a note is out of date or the learner asks.
Inputs: note_id (required).
import_notesImport notesA
Add notes to a knowledge graph. godspeed turns them into facts in the background; that work arrives through wait_for_work. Returns right away. With space_id the notes become a study file of that space (to add a file from disk, use add_space_file).
Inputs: name (required), text (required), space_id.
link_space_folderLink a folder to a spaceAIdempotent
Link a folder on this computer to a space. Its supported files are added, and from then on new files dropped there are added automatically and edited files are rebuilt (checked every minute while godspeed is open). godspeed sorts them into study material and space info itself while reading them, and never changes the folder. Use set_space_file_kind only to correct a kind.
Inputs: path (required), space_id (required).
list_lessonsList lessonsARead-onlyIdempotent
List the learner's lessons, newest first, each with its space and kind (study or homework; older ones teach or practice). total says how many match.
Inputs: limit, space_id.
list_spacesList spacesARead-onlyIdempotent
List the learner's spaces, archived ones included, with file and lesson counts.
Inputs: no named parameters.
read_lessonRead a lessonARead-onlyIdempotent
Read one lesson as markdown: everything the teacher and learner said, quizzes and answers included. A long lesson comes in pages; each page says which page it is and how many there are.
Inputs: lesson_id (required), page.
read_passageRead a passage of a space fileARead-onlyIdempotent
Read one passage of a space file by its id from search_space_files, or a file's passages at a place (file_id + range, e.g. a whole page). Returns the text with the ids of the passages before and after it, to keep reading.
Inputs: space_id (required), range, file_id, passage_id.
read_spaceRead a spaceARead-onlyIdempotent
Read one space: its description, how many files are in each status (pending, extracting, ready, failed, needs-whisper) and the files that could not be read, the topics of its knowledge graph with their fact counts, its deadlines (kind, date, time, done, and the files each covers), its lessons, and today's local date and time. A prep (a space made to get ready for one interview, assessment or test) also has its prep sheet: what the learner is preparing for, its day, what it is like, the topics with their ids and how each is going, what a mock is and the mocks taken. With files: true it lists every file instead (id, kind, status, size, path on disk). To find something inside the files, use search_space_files.
Inputs: space_id (required), files.
read_workRead more of a work itemARead-onlyIdempotent
Read one page of a long work item, or (full: true) get the item again in full: its instructions, every tool and the whole conversation, for when you lost track of it. When a work item says it has several pages, read all of them before you respond.
Inputs: work_id (required), full, page.
rememberRemember a noteA
Save a short note about the learner. Every agent that connects to godspeed later sees it under "Where you left off", in any folder. Save what the learner tells you outside lessons that will matter next time: an exam that is over, what they plan to study next, how they like to learn. One fact per note, at most 200 characters. Never save passwords or private details. The learner can see and delete notes in Settings → Connection.
Inputs: text (required), space_id.
remove_space_deadlineRemove a space deadlineADestructiveIdempotent
Remove one deadline from a space (its files and facts are not touched).
Inputs: space_id (required), deadline_id (required).
respondRespond to workA
Answer a work item the way a model would: text for the learner (or the task), and/or calls to the tools listed in the work item. Returns the next work item in the same conversation when the app needs you again right away (for example with tool results), or status "turn_complete".
Inputs: work_id (required), text, tool_calls, wait_seconds.
save_ruleSave a teaching ruleA
Save a rule about how godspeed's teacher teaches this learner, when they tell you a lasting preference ("use Python for code examples", "shorter answers"). It joins the learner's rules in Settings, for every lesson or for one space's lessons, and applies from the next turn. Not for one-off requests or facts about the learner (use remember for those). Don't ask first: the godspeed window shows it with Undo and Edit.
Inputs: rule (required), area, space_id.
search_graphSearch the knowledge graphARead-onlyIdempotent
Search one space's knowledge graph (each space has its own): the facts (propositions) the learner has learned and the reasoning chains connecting them. Without a query, returns the most recent facts.
Inputs: limit, query, space_id.
search_space_filesSearch a space's filesARead-onlyIdempotent
Search all of a space's files (readings, slides, transcripts, syllabus, assignments) by meaning and keywords. Returns the best passages, each with its id, file, place (page, slide, time or lines) and a short snippet. Open the ones you need with read_passage instead of reading whole files.
Inputs: query (required), space_id (required), limit.
set_space_file_kindSet space files' kindADestructiveIdempotent
Switch one or more space files between study material and space info. Study → info removes their facts; info → study builds them. A file that can't be switched is listed under refused; the others still switch.
Inputs: kind (required), file_ids (required), space_id (required).
start_lessonStart a lessonA
Start a new study session in godspeed taught by you: you teach what is new and give problems on what needs practice. The topic becomes the learner's first message. With space_id the lesson belongs to that space: it opens with the space's card and its facts go into that space's graph. In a prep, a topic named exactly like one on its sheet counts for that topic. You teach it through wait_for_work; the learner follows along in the godspeed window.
Inputs: topic (required), space_id.
unlink_space_folderUnlink a space's folderADestructiveIdempotent
Unlink the space's folder: its files leave the space together with their facts. The folder itself is not touched.
Inputs: space_id (required).
update_prepChange a prep sheetAIdempotent
Change a prep's sheet when the learner asks (read_space shows it): move or clear its day, replace what it is like, change what a mock is, add topics, or remove topics by id. Only what you send changes. Refused while the sheet is being written.
Inputs: space_id (required), date, mock, about, +2 more.
update_spaceUpdate a spaceAIdempotent
Rename a space, change its description, signature or icon, or archive / unarchive it (archiving hides it from the space switcher but keeps everything; an archived space takes no new lessons).
Inputs: space_id (required), icon, name, archived, +2 more.
update_space_deadlineUpdate a space deadlineAIdempotent
Change a deadline's kind, name, date, time, covered files, left-out files, source or assignment file, or tick it done (done: true) or not done (done: false). file_ids and left_out_ids each replace the whole list (a file is never in both); time: null, source: null and assignment_file_id: null remove them. Work out coverage from the space's own files as add_space_deadline says; ask the learner when the files don't settle it.
Inputs: space_id (required), deadline_id (required), date, done, +7 more.
wait_for_workWait for workA
Wait for the next request from godspeed (a lesson turn, a Talk message, a background job, or a knowledge-graph run). Returns a work item, or status "idle" if nothing arrived in time — then call again.
Inputs: helper, lesson_id, full_context, timeout_seconds.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 25 tools
Most tools target clearly distinct resources and actions, and the descriptions explicitly steer apart the riskiest pairs (remember vs save_rule, import_notes vs add_space_file, read_space vs search_space_files). A few clusters still require careful reading — the three 'save something' tools (remember, save_rule, import_notes) and the several read_* tools differ mainly by object, so a careless agent could pick wrong.
The dominant convention is a consistent verb_noun snake_case pattern (list_spaces, read_space, create_space, add_space_deadline, update_space_deadline, remove_space_deadline, link_space_folder). Three bare verbs (remember, forget, respond) deviate, but the overall pattern is predictable and readable.
At 25 tools the surface is at the heavy edge of the scale, spanning five sub-areas (work loop, spaces, files, deadlines, lessons, plus notes/rules). Each tool maps to a real operation, but the set is large enough that an agent must navigate several distinct workflows, pushing it past the comfortable 3-15 range.
Coverage is strong: full deadline CRUD, space create/read/update/list, file add/search/read/kind-switch/link-unlink, lesson list/read/start, graph search/import, and a complete work loop. Gaps are minor — no way to delete a space (only archive), no per-file removal, and save_rule has no list/delete counterpart — but these are workable around or handled in the app's Settings UI.
Maintenance
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Shared memory and mail for your AI agents. Verified with Claude Code; other MCP clients in testing.
An agent-first office suite Claude & ChatGPT read and write over one MCP URL.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA multi-agent AI tutor that delivers personalized lessons, resolves doubts with RAG, generates quizzes, and tracks progress, all accessible via MCP for Claude Desktop.6-
- AlicenseNot gradedqualityCmaintenanceA local-first study workspace for MCP agents, providing a web UI for learning, quizzing, and review, independent of agent lifecycle.4GPL 3.0
- FlicenseCqualityDmaintenanceA local-first flashcard and quiz app with an MCP server for Codex, enabling users to manage decks, cards, quizzes, and reviews through natural language.19-
- AlicenseNot gradedqualityDmaintenanceLocal Leitner flashcard MCP server enabling AI clients to create decks, manage cards, study with spaced repetition, and track progress.MIT