პოპულარული: მონაცემები განახლდა: 16 ნოემბერი, 2026

კატეგორიები

ინტერნეტი1415
კომუნიკაცია328
აუდიო და ვიდეო937
გრაფიკა და დიზაინი561
ოფისი და პროდუქტიულობა1177
დეველოპერის ხელსაწყოები3280
ხელოვნური ინტელექტი605
უსაფრთხოება და კონფიდენციალურობა407
სისტემური ხელსაწყოები3183
თამაშები544
განათლება და მეცნიერება241
ქსელი და IT292

Open DeepTutor for Windows: ძველი ვერსიები და ყველა ვერსია

Desktop app that runs DeepTutor, an agent-native open-source personalized tutor, with a bundled runtime.

Open DeepTutor for Windows — აქ ჩამოთვლილია 2 ვერსია: პირველი 6 ნოემბერი, 2026, მიმდინარე 1.7.3. თითოეული ვერსია გამომცემლის საკუთარ საინსტალაციო ფაილზე მიუთითებს.

2026: 2 2 26
ვერსიათარიღიზომაფაილები
1.7.3უახლესი 15 ნოემბერი, 2026 — 64-ბიტიანი EXE (NSIS)
ცვლილებების აღწერა
DeepTutor v1.7.3 Release Notes
Release Date: 2026.11.16
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.
What's New
Read, zoom, and revisit question help
The PDF reader adds continuous zoom, text-fit controls, and an image viewer. Annotation updates and multi-material selection are more reliable. Reading quizzes keep answer keys on the server and preserve question-linked help separately from attempts; authorized guardians can review reading progress, quiz records, and help activity.
Review book changes before applying them
Edit generated chapters and sections without rebuilding the whole book. Structure changes and page-chat proposals show a reviewable diff before application, and the most recent unchanged edit can be undone. New empty sections generate when opened; math rendering and page-chat continuation also receive fixes.
More search providers and connected agents
Search adds DeepSeek, SpecStream, and SearchApi, including SearchApi web, news, and scholar modes. Web Fetch gains a selectable DeepSeek backend, and Standard Compute joins model setup. A configured Agent Client Protocol (ACP) process can be consulted as a local subagent. MCP OAuth refresh and reconnection are more reliable after consent and restarts.
Conversations and practice retain their context
Choose supported reasoning effort per conversation. Untouched chat sessions inherit ready workspace knowledge bases, saved side-chat tabs reopen for the same account, and question-bank sources support search and pagination. Mastery fixes preserve explanations across failed attempts, keep issued questions gradable after re-indexing, and improve reference answers and narrow-screen navigation.
Better document parsing and language support
Docling preserves structured page content and exposes optional formula and picture enrichments. Upload validation follows the available parser formats, GitHub knowledge sources accept MDX, and retrieval respects exact source paths. Italian and Hungarian join the interface and reply-language options, while Hindi becomes a reply language.
More reliable model streams and desktop upgrades
Provider calls handle stalled streams, incomplete terminal events, tool identifiers, and replayed reasoning more carefully. History that still exceeds its plan after condensation stops with a clear error. Installing a newer desktop app adopts its newer bundled core with backup and rollback; macOS Finder launches also discover host CLIs in common install locations. Launcher and updater readiness waits respect configured limits.
Upgrade Notes
- Full app: stop DeepTutor and back up the runtime home, then run python -m pip install --upgrade "deeptutor[full]==1.7.3". Keep the same DEEPTUTOR_HOME; verify with python -m pip check and deeptutor module list before restarting. Additional feature wheels must also match 1.7.3.
- Legacy installations: versions 1.6.15 and earlier require uninstalling the old deeptutor-cli package before installing the modular family. Use the manual migration in v1.7.0; an old update worker cannot acquire the new migration logic retroactively. Recover a full app with optional parsing using "deeptutor[full,parse]==1.7.3" in the same environment.
- Source and Docker: source users install requirements/full.txt, then python -m pip install -e . --no-deps, and refresh web/ with npm ci --legacy-peer-deps on Node.js 22. Docker users pull ghcr.io/hkuds/deeptutor:1.7.3 or :latest and recreate the container with its existing data volume.
- Desktop: use the matching Apple Silicon or Intel DMG, Windows installer, or portable ZIP. Windows builds remain unsigned. Automatic update discovery is not connected; replacing the app now trials a newer bundled core and preserves a workspace backup.
- Embeddings: indexed OpenAI-compatible embedding responses are now restored to input order. If a gateway previously returned reordered ve
1.7.2 6 ნოემბერი, 2026 — 64-ბიტიანი EXE (NSIS)
ცვლილებების აღწერა
DeepTutor v1.7.2 Release Notes
Release Date: 2026.11.06
Building on v1.7.1, v1.7.2 adds selected-text read-aloud, easier model setup, and more reliable guided learning, retrieval, and updates. Desktop releases now require Apple Silicon and Intel Mac installers alongside both Windows downloads.
What's New
Complete desktop downloads and sturdier Windows support
GitHub Releases provide Apple Silicon and Intel DMGs, a Windows installer, and a Windows portable ZIP. The release workflow checks every platform and all versioned downloads and stable aliases. Windows fixes cover session and migration locks, plugin environments, Python executable discovery, non-UTF-8 output, and paths containing spaces.
Read just the passage you need
Select text in Chat, Mastery Path, or Reading and choose Read aloud to hear it through your configured speech provider. Chat read-aloud also remembers playback speed per conversation in the current browser. Voice rendering handles escaped percent signs and degree notation more naturally, and Video Lesson's Edge fallback selects a voice matching the lesson language.
Easier provider setup and broader compatibility
Settings discovers available models after credential edits and lets you import several at once. New custom providers default to automatic protocol selection. NVIDIA NIM adds text retrieval embeddings with distinct query and passage roles; newer DashScope image models use their matching generation protocol, with 4K restricted to wan2.7-image-pro. Responses API tool arguments, structured output, replayed history, and Codex custom headers receive compatibility fixes.
Guided learning that keeps the context
Choose a model before a Mastery Path outline starts. Follow-up clarifications and missing parts are assessed with the explanation they complete, while stale card replies and duplicate retries are handled more carefully. Source quotation mismatches receive a bounded retry, and mastery navigation, board scrolling, and tutoring-memory recovery are more reliable.
More accessible conversations and retrieval
Korean is available as a partial interface translation, with English fallback for untranslated text. More labels and dates follow the selected interface language. Little Tutor threads appear in the command palette, document readers load on demand, and socket failures and cancellation recover more predictably. BM25 preserves dotted identifiers, document extraction stays off the API event loop, and notebook and favorite tools support read-only record retrieval.
Safer updates and bounded reasoning recovery
Package updates keep installed feature modules on the target core version and record launch failures instead of remaining stuck at restart. Detached launches avoid stale source-tree imports, and failed CLI-app rollbacks preserve backups. The shared agent loop can stop or make one explicitly bounded higher-budget retry when reasoning exhausts the output budget without a visible answer.
Upgrade Notes
- Full app: stop DeepTutor and back up the runtime home, then run python -m pip install --upgrade "deeptutor[full]==1.7.2". Keep the same DEEPTUTOR_HOME; verify with python -m pip check and deeptutor module list before restarting. Any additional feature wheels must also match version 1.7.2.
- Legacy installations: upgrades from 1.6.15 or earlier must uninstall the legacy deeptutor-cli package before installing the modular package family. Follow the migration commands in v1.7.0.
- Source installs: install requirements/full.txt, then python -m pip install -e . --no-deps. Stop active servers and CLI turns before changing modules.
- Docker: pull ghcr.io/hkuds/deeptutor:1.7.2 or :latest and recreate the container with the existing data volume.
- Desktop: use the matching installer or portable ZIP on this GitHub Release. Windows builds remain unsigned. Automatic desktop update discovery is not connected; the shell supports manually supplied signed core updates.
- NVIDIA NIM: select its embedding binding explicitly an

ყველაზე პოპულარული — AI ასისტენტები და LLM

ყველას ნახვა
  1. Claude CodeAI ასისტენტები და LLM · Anthropic PBC
  2. Codex CLIAI ასისტენტები და LLM · OpenAI, Inc.
  3. ChatGPT by lencxAI ასისტენტები და LLM · lencx
  4. GPT4AllAI ასისტენტები და LLM · Nomic
  5. JanAI ასისტენტები და LLM · Jan
  6. oh-my-piAI ასისტენტები და LLM · Can Bölük
  7. T3 CodeAI ასისტენტები და LLM · T3 Tools
  8. CC SwitchAI ასისტენტები და LLM · farion1231
  9. WSL ManagerAI ასისტენტები და LLM · Bostrot
  10. LobeHubAI ასისტენტები და LLM · LobeHub

ტეგები

გაზიარება