# Tencent/WeSmartFlow

Every question can open a new path. WeSmartFlow turns learning into conversation, exploration, stories, and hands-on discovery.

Repository: https://github.com/Tencent/WeSmartFlow
Canonical: https://ross.abutalabs.com/products/wesmartflow
Homepage: https://wesmartflow.cn
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-08-31T07:44:03+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 100, release rhythm 35, longevity 7
- inputs: {"age_days": 110, "days_push": 2, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1020, forks 7 (observed 2026-09-01T02:13:57.962859+00:00)

## What it is
WeSmartFlow is an agent-native adaptive learning framework that models the full learning process with ReAct-based tutoring agents, graph memory knowledge tracking, and multi-agent courseware generation. It combines knowledge graph mastery modeling, SM-2 spaced repetition, and automated content pipelines (outlines, slides, quizzes, visuals, audio) into an education-focused agent engineering stack.

## Use cases
- build an AI tutor that tracks learner mastery over time
- generate complete course packages from a single topic
- maintain a personal knowledge graph with spaced repetition review
- orchestrate multi-agent workflows for educational content creation
- create interactive knowledge cards and visualizations for learning
- run adaptive quizzes with automatic mastery updates

## When to choose
- you need an agent framework purpose-built for education and learning-state modeling
- you want long-term learner memory via knowledge graphs rather than stateless chat
- you need automated multi-agent generation of slides, quizzes, and audio lessons

## When to avoid
- you just need a simple chatbot or Q&A assistant without learning-state tracking
- you need a production-grade LMS rather than an experimental agent framework
- your project has no education or tutoring component

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, llm-inference, chatbot, data-visualization, search-engine, tts, prompt-engineering
- domain: artificial-intelligence, education, large-language-models
- platform: python, cross-platform
- tags: adaptive-learning, knowledge-graph, multi-agent, react-agent, spaced-repetition, tutoring, graph-memory, courseware-generation, fastapi, vue3, ai-agents, natural-language-processing, web-server, macos

## Member repositories
- Tencent/WeSmartFlow (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:13:57.962859+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:09:21.195393+00:00, confidence not recorded.
  - readme: https://github.com/Tencent/WeSmartFlow (fetched 2026-09-01T02:13:57.962859+00:00, sha 92fb6f84974b)
- Data as of 2026-08-30T08:39:29.467469+00:00.