DeepTutor
FrameworkHKUDS/DeepTutor
Agent-native personalized tutoring system with multi-agent AI and RAG.
Overview
DeepTutor is an open-source, agent-native personalized learning assistant that leverages large language models, multi-agent systems, and retrieval-augmented generation (RAG). It provides a rich set of tools including a CLI, SDK, web UI, and plugin model for building interactive tutoring experiences.
README Preview
\n\n\n\n# DeepTutor: Agent-Native Personalized Tutoring\n\n\n\n[](https://www.python.org/downloads/)\n[](https://nextjs.org/)\n[](LICENSE)\n[](https://github.com/HKUDS/DeepTutor/releases)\n[](https://arxiv.org/abs/2604.26962)\n\n[](https://discord.gg/eRsjPgMU4t)\n[](./Communication.md)\n[](https://github.com/HKUDS/DeepTutor/issues/78)\n\n[Features](#-key-features) · [Get Started](#-get-started) · [Explore](#-explore-deeptutor) · [TutorBot](#-tutorbot--persistent-autonomous-ai-tutors) · [CLI](#%EF%B8%8F-deeptutor-cli--agent-native-interface) · [Multi-User](#-multi-user--shared-deployments-with-per-user-workspaces) · [Roadmap](#%EF%B8%8F-roadmap) · [Community](#-community--ecosystem)\n\n[🇨🇳 中文](assets/README/README_CN.md) · [🇯🇵 日本語](assets/README/README_JA.md) · [🇪🇸 Español](assets/README/README_ES.md) · [🇫🇷 Français](assets/README/README_FR.md) · [🇸🇦 العربية](assets/README/README_AR.md) · [🇷🇺 Русский](assets/README/README_RU.md) · [🇮🇳 हिन्दी](assets/README/README_HI.md) · [🇵🇹 Português](assets/README/README_PT.md) · [🇹🇭 ภาษาไทย](assets/README/README_TH.md) · 🇵🇱 [Polski](assets/README/README_PL.md)\n\n\n\n---\n\n> 🤝 **We welcome any kinds of contributing!** See our [Contributing Guide](CONTRIBUTING.md) for branching strategy, coding standards, and how to get started.\n\n### 📦 Releases\n\n> **[2026.5.8]** [v1.3.8](https://github.com/HKUDS/DeepTutor/releases/tag/v1.3.8) — Optional multi-user deployments with isolated user workspaces, admin grants, auth routes, and scoped runtime access.\n\n> **[2026.5.4]** [v1.3.7](https://github.com/HKUDS/DeepTutor/releases/tag/v1.3.7) — Thinking-model/provider fixes, visible Knowledge index history, and safer Co-Writer clear/template editing.\n\n> **[2026.5.3]** [v1.3.6](https://github.com/HKUDS/DeepTutor/releases/tag/v1.3.6) — Catalog-based model selection for chat and TutorBot, safer RAG re-indexing, OpenAI Responses token-limit fixes, and Skills editor validation.\n\n> **[2026.5.2]** [v1.3.5](https://github.c
FAQ (1)
TroubleshootingHow to maintain conversation context across multiple HTTP API calls to a DeepTutor bot?
As of v1.4.0, the execute-stream API does not support session management, context retention, or history writing for HTTP calls, causing each request to be treated independently. A workaround is to build a lightweight gateway that archives messages, concatenates past context with each new query, and passes the combined prompt via the API. This approach adds latency and complexity. The feature request (issue #511) proposes extending the API with bot_id and session_id or adding separate session/history endpoints, but no official implementation exists yet.