Lore Agent
Scholar Agent
LLM общего назначения часто бывают неточными и устаревшими в специализированных областях. Scholar Agent объединяет онлайн-исследования + накопление локальных знаний в устойчивый маховик знаний, со временем делая ваш ИИ умнее в вашей предметной области. Он также создает базу знаний, понятную человеку, для быстрого обучения. Бесшовная интеграция с Claude Code и VS Code Copilot через MCP.
Что он делает
Your question
│
▼
Online research (LLM web search + academic APIs)
│
▼
Structured synthesis (with citations, confidence, uncertainty)
│
▼
Local accumulation (Markdown knowledge cards + BM25 index)
│
▼
Next question: AI checks local first ── hit? ──► use directly, fast & accurate
│ miss
▼
Research again → accumulate → reindex ──► knowledge base keeps growingКаждый цикл дополняет предыдущий. Карточки знаний имеют полный жизненный цикл управления: черновик → проверено → доверено → устарело → не рекомендуется.
Related MCP server: codememory
Конвейер академических исследований
Scholar Agent включает в себя комплексный конвейер для исследования научных статей:
Поиск статей — Поиск статей в arXiv, DBLP и Semantic Scholar. Фильтрация по ведущим конференциям (CVPR, ICCV, ECCV, ICLR, AAAI, NeurIPS, ICML, ACL, EMNLP, MICCAI)
Умная оценка — Четырехмерный механизм оценки (релевантность, актуальность, популярность, качество) ранжирует статьи в соответствии с вашими исследовательскими интересами
Заметки глубокого анализа — Автоматическая генерация markdown-заметок в стиле Obsidian из 20+ разделов с плейсхолдерами
<!-- LLM: -->для завершения с помощью ИИИзвлечение изображений — Извлечение изображений из исходных архивов arXiv и PDF (через PyMuPDF)
Ежедневные рекомендации — Автоматизированный ежедневный поиск статей, оценка, дедупликация и генерация заметок с рекомендациями
Статья → Карточка знаний — Преобразование анализа статей в карточки знаний, которые возвращаются в маховик знаний
Автоматическая расстановка ссылок по ключевым словам — Сканирование заметок на наличие технических терминов и автоматическое создание
[[wiki-links]]
Быстрый старт
Внедрение в существующий проект
cd my-project && git clone https://github.com/zfy465914233/scholar-agent.git
bash scholar-agent/setup.sh
# Restart Claude Code to activateЭто создаст структуру каталогов, скопирует шаблоны конфигурации, установит навыки и построит индекс знаний.
Использование в качестве отдельного проекта
# Clone and install
git clone https://github.com/zfy465914233/scholar-agent.git
cd scholar-agent
pip install -r requirements.txt
# Build the knowledge index
python scripts/local_index.py --output indexes/local/index.jsonMCP-конфигурации уже настроены:
Claude Code:
.mcp.jsonготов. Перейдите в папку проекта (cd) и запустите Claude Code.VS Code Copilot:
.vscode/mcp.jsonготов. Откройте проект, включите режим агента.
Инструменты MCP
Основные инструменты (всегда доступны)
Инструмент | Описание |
| Поиск по локальной базе знаний |
| Сохранение структурированных результатов исследования как карточки знаний |
| Просмотр всех карточек знаний |
| Быстрая фиксация пары вопрос-ответ в виде черновой карточки |
| Добавление URL или необработанного текста в базу знаний |
| Генерация интерактивного графа знаний (vis.js) |
Академические инструменты (установите SCHOLAR_ACADEMIC=1 для включения)
Инструмент | Описание |
| Поиск в arXiv + Semantic Scholar с 4-мерной оценкой |
| Поиск статей конференций через DBLP + обогащение S2 |
| Генерация markdown-заметок глубокого анализа (20+ разделов) |
| Извлечение рисунков из исходников arXiv / PDF |
| Преобразование анализа статьи в карточку знаний |
| Рабочий процесс ежедневных рекомендаций статей |
| Автоматическая привязка ключевых слов как |
Рекомендуемый рабочий процесс
Для наилучшего качества анализа следуйте этому порядку:
Скачивание статьи:
download_paper("2510.24701", title="Название статьи", domain="LLM")Извлечение изображений:
extract_paper_images("2510.24701")(автоматически обнаруживает локальный PDF)Глубокий анализ:
analyze_paper(paper_json)(автоматически обнаруживает локальный PDF, извлекает полный текст)
Совет: Скачивание PDF перед анализом позволяет извлечь полный текст, создавая высококачественные заметки с конкретными данными, формулами и результатами экспериментов. Без локального PDF анализ опирается только на аннотацию.
Конфигурация
.scholar.json
Файл .scholar.json настраивает пути к знаниям и параметры академических исследований. См. .scholar.example.json для полного примера с комментариями.
Ключевые разделы:
knowledge_dir— Путь к каталогу карточек знанийindex_path— Путь к индексу поиска BM25academic.research_interests— Ваши области исследований, ключевые слова и категории arXivacademic.scoring— Веса и измерения оценки статей
Переменные окружения
Скопируйте .env.example в .env и настройте:
Переменная | Обязательно | Описание |
| Нет | Установите |
| Нет | API-ключ Semantic Scholar (получить бесплатно) |
| Нет | API-ключ LLM для продвинутого конвейера синтеза |
Структура проекта
scholar-agent/
├── mcp_server.py # MCP server (13 tools)
├── setup_mcp.py # Embed into existing projects
├── pyproject.toml # Package configuration
├── .scholar.json # Project & academic configuration
├── schemas/ # Answer + evidence JSON schemas
├── scripts/
│ ├── academic/ # Academic research modules
│ │ ├── arxiv_search.py # arXiv + Semantic Scholar search
│ │ ├── conf_search.py # Conference paper search (DBLP)
│ │ ├── paper_analyzer.py # Deep-analysis note generation
│ │ ├── scoring.py # 4-dim paper scoring engine
│ │ ├── image_extractor.py # Figure extraction from PDFs
│ │ ├── note_linker.py # Wiki-link discovery + keyword linking
│ │ └── daily_workflow.py # Daily recommendation pipeline
│ ├── scholar_config.py # Configuration reader
│ ├── local_index.py # BM25 index builder
│ ├── local_retrieve.py # Knowledge retrieval
│ ├── close_knowledge_loop.py # Knowledge card builder
│ └── ... # Research, synthesis, governance, graph
├── knowledge/ # Knowledge cards (gitignored, user-generated)
├── indexes/ # Generated indexes (gitignored)
└── tests/ # 247 testsДополнительные возможности
Многоперспективное исследование — Параллельное исследование с 5 точек зрения (академическая, техническая, прикладная, контрарная, историческая)
Совместимость с Obsidian — Стандартный Markdown + YAML frontmatter +
[[wiki-links]]CLI управления знаниями — Проверка frontmatter, обнаружение осиротевших карточек, поиск дубликатов, управление жизненным циклом
Отказоустойчивость провайдеров — Каждый источник поиска работает независимо; при отсутствии сети переключается на локальный поиск
Тестирование
python -m pytest tests/ -v247 тестов, ~13 с. Внешние сервисы не требуются.
Лицензия
MIT — см. LICENSE.
Available Tools
12 toolsbuild_graphA
Build an interactive knowledge graph visualization.
Generates a self-contained HTML file showing all knowledge cards as nodes and their wiki-links as edges. Open the output file in a browser to explore the knowledge graph visually. Compatible with Obsidian vaults.
Returns the path to the generated graph.html file.
Inputs: no named parameters. Returns: result
capture_answerA
Capture a useful Q&A answer as a draft knowledge card.
Use this ONLY when a conversation produces a SUBSTANTIVE answer that is worth persisting — meaning it provides genuine technical insight, a non-obvious explanation, or actionable knowledge that cannot be found in standard references.
DO NOT use this tool for:
Single-sentence answers or brief definitions
Answers that could be found in any standard reference (Wikipedia, docs)
Trivial facts, simple yes/no responses, or content shorter than 150 characters
Paper or topic-level knowledge that requires source verification
If you have structured evidence and claims, prefer save_research instead — it produces higher-quality cards with proper source attribution.
The answer text MUST be at least 150 characters. Write a thorough explanation covering the key insight, context, and practical implications.
Inputs: query (required), answer (required), tags, language. Returns: result
fetch_urlA
Fetch a web URL and return its main content as markdown — first-hand retrieval (G5).
抓取网页正文(已做 HTML→正文提取)返回给调用方,用于在 save_research 之前把
knowledge card 建立在一手出处之上,而非凭记忆或摘要。同时把完整正文存本地
快照 knowledge/_snapshots/<sha1(url)>.md(含 captured_at),防止原链接失效
(招聘 JD、网页易下架)后无法回溯(G2)。
典型用法:fetch_url 抓一手 → 基于正文写带具体数字/机制的深度 answer → save_research 存卡。
Inputs: url (required), max_chars. Returns: result
import_paperpulse_noteA
Import a distilled paper note from PaperPulse SaaS directly into the local Scholar Agent knowledge base.
Inputs: paper_id (required), api_token. Returns: result
ingest_sourceA
Ingest a URL or raw text into the knowledge base as a draft card.
For URLs: fetches the page content, extracts text, and saves as a card. For text: saves the provided text directly as a card.
Use this when you want to add external documents, articles, or notes to the knowledge base without requiring structured JSON.
Inputs: source (required), tags, title, language. Returns: result
lint_knowledgeA
Run read-only content health checks over the local knowledge base.
Reports orphan cards, broken wiki-links, cards not updated within stale_days, and highly overlapping titles. This tool never edits files.
Inputs: stale_days. Returns: result
list_knowledgeA
List all knowledge cards in the local knowledge base.
Returns card metadata (id, title, topic, type) for browsing and discovery.
Inputs: topic. Returns: result
query_knowledgeA
Search the local knowledge base for relevant information.
Returns top-k knowledge cards matching the query, with scores and content. Use this to find existing knowledge before doing web research.
Inputs: query (required), limit, rerank. Returns: result
save_researchA
Save structured research results as a knowledge card in the local knowledge base.
The answer_json must conform to schemas/answer.schema.json: { "answer": "detailed answer text", "supporting_claims": [{"claim": "...", "evidence_ids": ["..."], "confidence": "high|medium|low"}], "inferences": ["..."], "uncertainty": ["..."], "missing_evidence": ["..."], "suggested_next_steps": ["..."], "sources": ["https://example.com/source1", "https://example.com/source2"], "visual_aids": [{"type": "mermaid|image_url|image_path", "content": "...", "caption": "...", "alt_text": "..."}] }
IMPORTANT quality requirements:
The "answer" field MUST be at least 200 characters of substantive content.
You MUST include at least 1 supporting_claim with evidence_ids and confidence.
Each claim text MUST be at least 20 characters — vague one-word claims are rejected.
DO NOT create cards with empty supporting_claims — every card needs evidence-backed claims.
Aim for 3+ supporting claims, inferences, uncertainty, and suggested_next_steps for high-quality cards.
DO NOT use this tool for trivial facts or one-sentence answers — those are not worth persisting.
ALWAYS include a "sources" array with the URLs you referenced during research. These are written to the card's frontmatter source_refs for provenance tracking.
evidence_ids in supporting_claims SHOULD cite the source URL (from "sources") — the card renders them as clickable
[host](url)source links. Opaque ids like "s1" stay as bare text and lose the link.For first-hand depth: call
fetch_urlon key sources BEFORE writing the answer, so it cites concrete numbers/mechanisms from the actual page (not memory). fetch_url also archives a local snapshot (knowledge/_snapshots/) so dead links stay traceable. save_research best-effort snapshots any listed sources in the background even without an explicit fetch_url.When language="zh" (default), the entire answer field MUST be written in Chinese (中文). When language="en", write in English.
When to include visual_aids (auto-judge by topic):
Processes / workflows / data flow → mermaid flowchart or sequence diagram
Architecture / system design → mermaid graph or class diagram
Comparisons or hierarchies → mermaid diagram or table
Spatial / geometric concepts → image_url or mermaid
Pure definitions or simple facts → omit visual_aids
When sources contain useful images (charts, diagrams, figures):
If a source page has a relevant diagram/chart with clear explanatory value, include it as visual_aids with type "image_url" and the image's absolute URL
Judge relevance: prefer diagrams explaining mechanisms, architecture overviews, comparison charts, result plots — skip decorative screenshots or generic stock photos
Always provide a descriptive caption explaining what the image shows
For method/procedural content (how-to, implementation, deployment, etc.), also include:
expected_output: Description of what a successful result looks like — output format, shape, key metrics, or acceptance criteria. Synthesize from the answer if sources don't explicitly provide this.
example: A minimal worked example (sample input → processing steps → expected output). Construct synthetically based on the answer if sources lack one. Write '[insufficient data — needs supplementation]' only if impossible to construct.
Visual aids placement (optional after_section field):
"answer" — insert after the main answer paragraph (default for architecture/pipeline diagrams)
"supporting_claims" — insert after claims (default for evidence figures/charts)
"inferences", "uncertainty", "missing_evidence", "suggested_next_steps" — after respective sections
Omit after_section to place at the end of the card (backward compatible)
Inputs: query (required), answer_json (required), domain, language, +1 more. Returns: result
scan_dead_linksA
Diagnose dead source URLs (404/410/connection failure) across knowledge cards.
Probes each unique source_refs URL once (HEAD first, GET fallback) and fans
the result out to every card that cites it. Paywalled domains are reported
as blocked; offline=True marks every URL skipped. Read-only — never
edits cards or snapshots.
Inputs: offline, timeout, concurrency. Returns: result
scan_stale_knowledgeA
Report knowledge cards whose source freshness exceeds domain thresholds.
Unlike lint_knowledge's updated_at check, this uses source_date/captured year with the domain-specific freshness policy used by card validation. This tool is read-only.
Inputs: no named parameters. Returns: result
validate_knowledgeA
Validate local knowledge cards without modifying files.
Runs card frontmatter validation plus body-density/source-freshness checks. Use this before relying on a knowledge base or after bulk imports.
Inputs: verbose. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Most tools have distinct purposes (query, save, ingest, validate, fetch, list, lint, scan, build, import). However, save_research, capture_answer, and ingest_source all persist knowledge cards with different input formats, which could cause confusion despite detailed descriptions.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., query_knowledge, save_research, fetch_url). Verbs are descriptive and the pattern is predictable across all 12 tools.
12 tools is well-scoped for a knowledge management server. The set covers querying, saving, ingesting, validating, listing, linting, scanning dead links, building graphs, and importing notes—no bloat or deficiency.
The tool surface covers create (save, capture, ingest), read (query, list), and checking tools, but lacks update and delete operations for knowledge cards. This is a notable gap that could hinder full life cycle management.
Maintenance
Related MCP Connectors
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
A second brain for your AI agent. Shared memory for your team's AI agents, plus public and private knowledge bases — works with ChatGPT, Claude, Cursor and any MCP client.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Ask your own documents and get answers that cite the source passage. Workspace knowledge bases over MCP for Cursor, Claude and any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI coding agents to retrieve and manage code context with hybrid search, project memory, and observability via MCP tools.30MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to locally search, query, and understand codebases with token-efficient context, dependency graphs, history, architecture diagrams, and metrics through MCP.15 npm3MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to persist and retrieve project knowledge using three MCP tools with local vector and full-text search.MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to persistently store, semantically search, and recall project-specific and cross-project knowledge across sessions, with everything kept local in SQLite. It also exposes project context, guidelines, and preferences as MCP resources for agents to read and write directly.-