DeepTutor
92 versions indexed · latest v1.7.4 on Nov 20, 2026
202692
This desktop security update replaces the runtime signing key used by the macOS and Windows apps. On November 20, desktop release credentials were exposed in GitHub Actions artifacts. Those artifacts have been removed.
Building on v1.7.2, v1.7.3 makes reading and book editing more flexible, expands search and agent connections, and improves learning records, model streams, and desktop upgrades.
Building on v1.7.1, v1.7.2 adds selected-text read-aloud, easier model setup, and more reliable guided learning, retrieval, and updates.
Building on v1.7.0, v1.7.1 introduces Open DeepTutor desktop previews, broader localization, and substantial improvements to chat, lessons, accounts, providers, and document handling.
Building on v1.6.15, v1.7.0 brings modular installation, a refreshed learning workspace, block-based notebooks with Dito, and narrated video lessons.
Building on v1.6.14, v1.6.15 improves Guided Learning with reviewed outline changes, independently graded question groups, and bounded tutoring memory.
Building on v1.6.13, v1.6.14 brings original-source visual practice, recoverable knowledge-base indexing, scientific research tools, and managed plugins.
Building on v1.6.12, v1.6.13 expands reading, listening, and question-bank practice, improves document parsing and speech configuration, and brings Polish plus more model providers.
Building on v1.6.11, v1.6.12 lets each workspace place and move its knowledge bases, connects searchable Kiwix archives, and carries source figures into grounded answers.
Building on v1.6.10, v1.6.11 is a wide release: French and Ukrainian join the interface, immersive reading gets folders, figures and in-chat selection actions, Office files preview as real pages, and knowledge bases…
Building on v1.6.9, v1.6.10 gives the native LightRAG engine its own role models and makes a published index state what it was built with.
Building on v1.6.8, v1.6.9 brings folder-based learning workspaces, a daily practice loop, redesigned Settings, and clearer streaming conversations.
v1.6.8 lands twenty-two community pull requests and a sweep of the reports behind them. Where v1.6.7 chased a token budget spent on hidden thinking, this one mostly answers a different complaint: I did a thing and the…
v1.6.7 is a fix release assembled almost entirely from community reports and the pull requests behind them — nineteen merged here. One thread runs through most of it: reasoning models.
v1.6.6 is a fix release, and an unusually clarifying one. Working through the v1.6.5 feedback showed that most of what people reported was not a regression: v1.6.5 mostly removed things that had been masking older…
v1.6.5 gives DeepTutor a folder of your own to work in. You point it at a directory, and the assistant can browse, read, and search what is already there while everything it generates lands in one predictable place —…
v1.6.4 makes the learning workspace lighter to start, clearer while long work is running, and more durable when you move between pages.
v1.6.3 includes a breaking front- and back-end refactor that replaces compatibility routes and stream entry points with strict canonical contracts, alongside learner and guardian accounts, grounded Reading actions…
v1.6.2 adds immersive YouTube learning and a plugin-driven visualizer catalog, then sharpens Reading, Knowledge, Partners, updates, and My Agents.
v1.6.0 connected the learning workspace. v1.6.1 is about the parts you touch every day: model configuration splits into a credential you enter once and a per-purpose assignment, Settings becomes a navigator instead of a…
v1.5.17 made Partners personal and let knowledge bases track GitHub. v1.6.0 connects the rest of the learning workspace: source-faithful reading, Courses and Little Tutor threads, an Ask Questions mode, bounded…
v1.5.16 connected a MarginNote library and put a run of gateway failures to rest. This one changes who a Partner belongs to: they stop being a deployment-wide resource only an admin can touch and become something each…
v1.5.15 added a capture inbox under the Book reader and, in doing so, stopped its pages from turning. That is fixed here, alongside a new connected knowledge source — a MarginNote 4 library that its own add-on fills —…
v1.5.14 put the document next to the conversation. This one is mostly about what sits behind it: PageIndex becomes something you can host yourself and retrieves by reasoning over a document tree, the question bank stops…
v1.5.13 made a book something you read. This one puts the assistant next to what you are reading: a document opens beside the thread, and every claim comes back with the page it came from.
v1.5.12 was about where an answer's material comes from. This one is mostly about Book — the surface that turns that material into something you read rather than something you chat with.
v1.5.11 was about what happens while an answer is being written. This one is about where its material comes from. The web-search layer was rebuilt onto a single table — which is how three defects that had been quietly…
v1.5.10 was about the paths underneath a request holding up; this one is about what happens while the answer is still being written.
v1.5.9 was about providers; this one is about the paths underneath them holding up — a batch upload that stalled every other request, a knowledge-base list that rescanned every index, a tool call dispatched with no…
Where v1.5.8 was about memory, this one is about providers — Gemini's native Embedding 2 endpoint, a per-model reasoning-effort control, a Novita AI gateway — and about the paths that were quietly wrong underneath them…
A maintenance release with one target: memory that stays put instead of climbing. A v1.5.7 source deployment grew past 14 GB before V8 gave up mid-session, and the causes turned out to be independent — a frontend dev…
A follow-up to v1.5.6 that opens the tutor up to tools DeepTutor never shipped: a curated store of hosted MCP services each person installs for themselves, and 101 command-line apps from the CLI-Anything catalog the…
A follow-up to v1.5.5 that finishes what it started: the Codex sign-in it shipped now actually completes on a remote or containerized deployment, and for partners and non-administrators too.
A follow-up to v1.5.4 with two new ways to bring a model — sign in with your own ChatGPT plan, or route through Eden AI's gateway — knowledge bases that can finally say what they actually hold, and GraphRAG indexing…
A same-day maintenance follow-up to v1.5.3, focused on how chat feels: the post-answer 'generating' stall is gone, IM partners render Markdown tables faithfully, and the JSON that models hand back parses more robustly.
A maintenance release on top of v1.5.2: code blocks are now yours to theme, My Agents connects four more coding CLIs, a new LLM provider joins the roster, and a broad sweep of chat, memory, embedding, and parsing…
A maintenance release on top of v1.5.1: chat attachment limits are now yours to tune, PageIndex retrieves by reasoning across your documents, and a broad sweep of provider, Book, and Knowledge Base reliability fixes…
A small release on top of v1.5.0: a knowledge base stuck in an error state is no longer a dead end — you can drop the single document that failed and keep going, instead of deleting and rebuilding the whole base.
v1.5.0 closes out the entire v1.4 line and opens the next. Rather than a single-point delta, this note looks back across the whole arc from v1.4.0-beta to today — the release that turned DeepTutor into an agent-native…
A small release on top of v1.4.14: Partners gain a native Mattermost channel, Guided Learning multiple-choice questions persist and grade correctly, and a configured zero chunk overlap is honored when indexing.
A fixes-and-polish follow-up to v1.4.13: open an assigned partner straight into chat with one click, Deep Research reports flag when a subtopic couldn't be completed, LightRAG indexes without MinerU installed, FAISS…
A fixes-and-polish follow-up to v1.4.12: partners with non-Latin names create correctly and can be handed to specific users, logos render after login in multi-user mode, and small knowledge bases retrieve reliably.
A knowledge-base release on top of v1.4.11: a new LightRAG Server retrieval engine, a lightweight PyMuPDF4LLM parsing engine, and a FAISS vector backend that makes large-KB retrieval dramatically faster.
A fixes-and-polish follow-up to v1.4.10: native tool calling now lights up on every cloud OpenAI-compatible provider, the admin Users page is rebuilt, quiz options render LaTeX, and the container story gains…
A deployment-and-account follow-up to v1.4.9: a self-service profile page with avatars, a hardened container story you can run rootless behind a single port, and tighter MCP tool access in multi-user deployments.
A maintenance follow-up to v1.4.8 that sharpens Settings and wires Mastery practice into your Question Bank. Search settings now show only the connection fields your provider actually uses, connection profiles can be…
A focused follow-up to v1.4.7: the agents you connect under My Agents now include your own Partners, and every Partner gains a private memory of its own.
A focused release on top of v1.4.6: your local coding agents become something DeepTutor can talk to. Connect Claude Code or Codex running on your machine as a knowledge source, and chat consults it live mid-turn.
Heads up: the documentation is still catching up to this release, so some pages may not yet reflect everything below.
A focused release on top of v1.4.4: Guided Learning is rebuilt on the same chat agent loop that powers everything else, on top of a new loop-plugin framework that makes the chat loop extensible.
A focused release on top of v1.4.3: the skill library opens up to the wider Agent-Skills ecosystem — install community skills from ClawHub with one command — and knowledge-base document previews catch up with the chat…
The biggest release since v1.4.0. TutorBot grows up into Partners, Chat collapses into a single agent loop, multi-user gets real per-user isolation, and Visualize, Co-writer, the file viewer, document parsing, and the…
v1.4.2 is a stability and polish release on top of v1.4.1. It unblocks Gemini 2.5+ across Visualize and the chat agent, fixes a ContextVar regression that silently routed authenticated requests to the admin workspace…
v1.4.1 is a security and stability patch on v1.4.0. It locks down the TutorBot tool sandbox, isolates per-user resources, fixes a v1.4.0 chat regression, adds an HTTP API for talking to a specific TutorBot, and ships a…
v1.4.0 is the GA cut of the v1.4 line. It carries the full v1.4.0-beta scope (Auto Mode, three-layer Memory workbench, agentic Deep Research / Deep Solve / Question, LlamaIndex chat refactor, unified capabilities…
v1.4.0-beta is the largest release since the agent-native rewrite. It folds an end-to-end Auto Mode on top of the existing capabilities, ships a three-layer memory subsystem (L1/L2/L3) with a dedicated workbench…
v1.3.10 is a focused reliability release for the issues reported after v1.3.9. It restores smoother remote Docker access, makes self-signed LLM endpoints work consistently across SDK-backed providers, protects code…
v1.3.9 builds on the v1.3.8 multi-user foundation with broader TutorBot deployment options, safer provider routing for thinking models, and a smoother web onboarding path.
v1.3.8 brings DeepTutor's optional multi-user mode into the main release line. It keeps local single-user installs unchanged while adding authenticated shared deployments with isolated user workspaces, admin-managed…
v1.3.7 focuses on thinking-model compatibility, clearer knowledge-base index history, and safer Co-Writer editing. It keeps provider-specific reasoning output under control while making index activity easier to…
v1.3.6 focuses on making model routing explicit across DeepTutor. Users can choose configured LLM profiles from chat and TutorBot flows, runtime services resolve those choices without leaking provider secrets, and…
v1.3.5 focuses on making local setup and knowledge-base chat more reliable. The launcher now follows the same runtime settings users configure in the web app, RAG tool calls are stricter about real search queries, and…
v1.3.4 turns the Book Engine and chat workspace into a tighter learning loop: book pages can now carry their own persistent chat sessions, books can be rebuilt from an existing spine, and regular chat turns can cite…
v1.3.3 is a fast follow-up release after v1.3.2. It expands provider coverage with NVIDIA NIM and Gemini embeddings, makes Space the unified place to attach chat history, notebooks, question-bank items, skills, and…
v1.3.2 is a focused stability release after v1.3.1. It tightens the embedding endpoint contract, makes LlamaIndex RAG recover more cleanly from stale or invalid indexes, and prevents reasoning-model scratchpad output…
v1.3.1 is a stability release after v1.3.0. It focuses on safer RAG routing, stronger embedding validation, more reliable Docker/TutorBot restarts, and a set of small but important Web UX fixes.
Knowledge bases now keep vector indexes per embedding configuration instead of treating one llamaindex_storage/ directory as the whole truth.
Chat attachments are now persisted as first-class session artifacts instead of living only as inline base64 blobs in message rows.
The v1.2.3 document-attachment pipeline has been expanded beyond Office files. Chat attachments now accept the same text-like formats as the Knowledge Base ingestion router: Markdown, plain text, logs, JSON/YAML/TOML…
Chat now accepts non-image file attachments (PDF, DOCX, XLSX, PPTX) alongside images. A new paperclip button in the composer opens a system file picker, and drag-and-drop / paste have been extended from images-only to…
Introduced a full Skills subsystem that lets users create, edit, and activate custom SKILL.md files from the web UI. Each skill lives under data/user/workspace/skills//SKILL.md with YAML frontmatter (name, description…
Promoted the agentic chat pipeline to a first-class config citizen in agents.yaml. A new capabilities.chat block exposes per-stage max_tokens (responding, answer_now, thinking, observing, acting, react_fallback) and a…
Introduced a brand-new Book Engine (deeptutor/book/) that compiles user inputs — chat history, notebooks, knowledge bases, and free-form intent — into structured, block-based, interactive 'living books'.
The Channels tab in the Agents page is no longer hard-coded for Telegram. It now auto-discovers every channel (Telegram, Slack, Discord, Matrix, Email, Feishu, …) and renders a form directly from each channel's Pydantic…
Promoted 'Answer now' from a chat-only affordance to a universal interrupt that respects each capability's output shape. A new shared helper deeptutor/capabilities/answer_now.py provides the gate…
Migrated the chat experience from query-parameter session IDs (/?session=xxx) to a dedicated /chat/[[...sessionId]] catch-all route.
Rewrote the normalizeEditorMdInlineMath pipeline to correctly handle loose block math — content wrapped in single $ delimiters on separate lines (e.g. $\\n\\\\frac{a}{b}\\n$).
Replaced the single-purpose 'Wrong Answer Note' with a full Question Notebook that stores every quiz question (correct and incorrect) with rich metadata — question type, options, explanation, and difficulty.
Removed the explicit consolidation_type parameter — consolidation now runs automatically for any provider that doesn't return its own answer. A new generic fallback formatter handles providers (e.g.
Added a new Visualize capability that turns natural-language data descriptions into interactive Chart.js or inline SVG visualizations.
Added real-time embedding progress reporting during knowledge base initialization — the UI now shows batch N/M complete as documents are embedded.
Replaced the litellm abstraction layer with native openai and anthropic SDKs across both the services and TutorBot layers. Added a new OpenAICompatProvider (covering OpenAI, DeepSeek, Mistral, StepFun, XiaoMi-MiMo…
Model settings changes (API keys, model selection, endpoints) now take effect immediately — no server restart required. The runtime LLM, embedding, and config caches are automatically invalidated after saving via the…
We're thrilled to announce DeepTutor v1.0.0-beta1 — the first beta of the brand new DeepTutor architecture. This is a ground-up rewrite that transforms DeepTutor from a monolithic RAG tutor into an agent-native learning…
Implemented robust session persistence across the application
Added alternative RAG-Anything initialization using Docling as the document parser
Hey everyone! We just released v0.5.1!
We're thrilled to announce DeepTutor v0.5.0! This release delivers unified service configuration, flexible RAG pipeline selection, and major UI/UX improvements across multiple modules.
A maintenance release focused on LLM Provider system optimization, Question Generation robustness, and Docker deployment fixes.
We're excited to announce DeepTutor v0.4.0! This release brings New home page, Expanded provider support for LLM & Embeddings provider, RAG module decoupling, Web improvement, and a bunch of minor improvements.
Release Date: January 6, 2026
Docker Deployment: Added multi-stage Dockerfile and docker-compose configurations for both development and production environments Enhanced WebSocket Security: Improved websocket security with comprehensive documentation