Lore Agent
Scholar Agent
범용 LLM은 전문 분야에서 부정확하거나 구식인 경우가 많습니다. Scholar Agent는 온라인 조사 + 로컬 지식 축적을 결합하여 지속 가능한 지식 플라이휠을 구축함으로써, 시간이 지남에 따라 귀하의 도메인에서 AI를 더욱 스마트하게 만듭니다. 또한 빠른 학습을 위해 사람이 읽을 수 있는 지식 베이스를 구축합니다. MCP를 통해 Claude Code 및 VS Code Copilot과 원활하게 통합됩니다.
주요 기능
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 growing각 라운드는 복합적으로 작용합니다. 지식 카드는 초안 → 검토됨 → 신뢰됨 → 오래됨 → 폐기됨의 전체 수명 주기 관리를 거칩니다.
Related MCP server: codememory
학술 연구 파이프라인
Scholar Agent에는 포괄적인 학술 논문 연구 파이프라인이 포함되어 있습니다:
논문 검색 — arXiv, DBLP, Semantic Scholar에서 논문을 검색합니다. 주요 학회(CVPR, ICCV, ECCV, ICLR, AAAI, NeurIPS, ICML, ACL, EMNLP, MICCAI)별로 필터링합니다.
스마트 스코어링 — 4차원 스코어링 엔진(관련성, 최신성, 인기도, 품질)이 귀하의 연구 관심사에 따라 논문 순위를 매깁니다.
심층 분석 노트 — AI 보조 완성을 위한
<!-- LLM: -->플레이스홀더가 포함된 20개 이상의 섹션으로 구성된 Obsidian 스타일의 마크다운 노트를 자동 생성합니다.그림 추출 — arXiv 소스 아카이브 및 PDF에서 이미지를 추출합니다(PyMuPDF 사용).
일일 추천 — 자동화된 일일 논문 검색, 스코어링, 중복 제거 및 추천 노트 생성.
논문 → 지식 카드 — 논문 분석을 지식 플라이휠에 다시 공급되는 지식 카드로 변환합니다.
키워드 자동 연결 — 노트를 스캔하여 기술 용어를 찾고 자동으로
[[wiki-links]]를 생성합니다.
빠른 시작
기존 프로젝트에 포함하기
cd my-project && git clone https://github.com/zfy465914233/scholar-agent.git
bash scholar-agent/setup.sh
# Restart Claude Code to activate이 명령은 디렉토리 구조를 생성하고, 설정 템플릿을 복사하며, 스킬을 설치하고, 지식 인덱스를 빌드합니다.
독립형 프로젝트로 사용하기
# 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 설정은 미리 구성되어 있습니다:
Claude Code:
.mcp.json이 준비되어 있습니다. 프로젝트 디렉토리로cd한 후 Claude Code를 시작하세요.VS Code Copilot:
.vscode/mcp.json이 준비되어 있습니다. 프로젝트를 열고 에이전트 모드를 활성화하세요.
MCP 도구
핵심 도구 (항상 사용 가능)
도구 | 설명 |
| 로컬 지식 베이스 검색 |
| 구조화된 연구 결과를 지식 카드로 저장 |
| 모든 지식 카드 탐색 |
| Q&A 쌍을 초안 카드로 빠르게 캡처 |
| URL 또는 원시 텍스트를 지식 베이스로 수집 |
| 대화형 지식 그래프 생성 (vis.js) |
학술 도구 (SCHOLAR_ACADEMIC=1 설정 시 활성화)
도구 | 설명 |
| 4차원 스코어링을 사용하여 arXiv + Semantic Scholar 검색 |
| DBLP + S2 보강을 통해 학회 논문 검색 |
| 심층 분석 마크다운 노트 생성 (20개 이상의 섹션) |
| arXiv 소스 / PDF에서 그림 추출 |
| 논문 분석을 지식 카드로 변환 |
| 일일 논문 추천 워크플로우 |
| 노트 내 키워드를 |
권장 워크플로우
최상의 분석 품질을 위해 다음 순서를 따르세요:
논문 다운로드:
download_paper("2510.24701", title="Paper Title", domain="LLM")그림 추출:
extract_paper_images("2510.24701")(로컬 PDF 자동 감지)심층 분석:
analyze_paper(paper_json)(로컬 PDF 자동 감지 및 전체 텍스트 추출)
팁: 분석 전에 PDF를 다운로드하면 전체 텍스트 추출이 가능하여 특정 데이터, 공식, 실험 결과가 포함된 고품질 노트를 생성할 수 있습니다. 로컬 PDF가 없으면 분석은 초록에만 의존합니다.
설정
.scholar.json
.scholar.json 파일은 지식 경로와 학술 연구 설정을 구성합니다. 주석이 포함된 전체 예제는 .scholar.example.json을 참조하세요.
주요 섹션:
knowledge_dir— 지식 카드 디렉토리 경로index_path— BM25 검색 인덱스 경로academic.research_interests— 귀하의 연구 도메인, 키워드 및 arXiv 카테고리academic.scoring— 논문 스코어링 가중치 및 차원
환경 변수
.env.example을 .env로 복사하고 구성하세요:
변수 | 필수 | 설명 |
| 아니오 | 학술 도구를 활성화하려면 |
| 아니오 | Semantic Scholar API 키 (무료 발급) |
| 아니오 | 고급 합성 파이프라인을 위한 LLM API 키 |
프로젝트 구조
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 tests추가 기능
다각적 연구 — 5가지 관점(학술적, 기술적, 응용적, 역발상적, 역사적)에서 병렬 연구 수행
Obsidian 호환 — 표준 마크다운 + YAML 프런트매터 +
[[wiki-links]]지식 거버넌스 CLI — 프런트매터 검증, 고아 카드 감지, 중복 찾기, 수명 주기 관리
공급자 내결함성 — 각 검색 소스는 독립적으로 실패하며, 오프라인 시 로컬 검색으로 대체
테스트
python -m pytest tests/ -v247개 테스트, 약 13초 소요. 외부 서비스가 필요하지 않습니다.
라이선스
MIT — LICENSE를 참조하세요.
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.-