karpathy-llm-wikiPersistent wiki manager based on Karpathy's LLM-Wiki pattern. Builds and maintains a structured, interlinked markdown wiki from your sources — compounding kn...
Install via ClawdBot CLI:
clawdbot install john-ver/karpathy-llm-wikiGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94fAudited Apr 16, 2026 · audit v1.0
Generated May 23, 2026
A researcher or student can ingest multiple papers, articles, and notes into a persistent wiki. The agent compiles summaries, cross-references concepts, and flags contradictions, enabling the user to query across accumulated knowledge over time without re-reading.
A team builds an internal wiki from meeting notes, product specs, and industry reports. The agent maintains structured pages, indexes them, and logs changes, providing a single source of truth that grows with the organization.
A legal professional ingests case law, statutes, and internal memos. The agent creates entity pages for parties, concepts for legal principles, and highlights contradictions between sources, aiding case preparation and research.
A medical researcher aggregates clinical studies and guidelines into a wiki. The agent tracks evolving consensus, flags data gaps, and generates summary pages, supporting evidence-based decision-making.
Offer the agent as a managed service with tiered pricing based on storage (wiki size) and advanced features like custom schemas or batch processing. Revenue from monthly/annual subscriptions.
Sell licenses for enterprises to deploy the agent on their own infrastructure, ensuring data privacy. Revenue from license sales and optional support contracts.
Offer a basic version (limited storage, standard operations) for free. Charge for premium features such as advanced linting, custom integrations, and priority support. Convert free users via upselling.
💬 Integration Tip
Start by setting the wiki root via the configuration file (~/.agent-wiki.json) and create a few test pages to ensure the file structure is correct. Then ingest a small source to verify the agent's pipeline—reading, summarizing, and linking work as expected.
Scored May 23, 2026
Manage a personal knowledge base by adding, searching, organizing, and reviewing articles, links, and notes with tags and natural language queries.
Generate a daily work report by automatically discovering all git repositories the user worked on, collecting commit logs across all branches, and summarizin...
日记引导助手。每日写作引导、感恩日记、反思日记、晨间日记、晚间总结、周总结模板。Journal prompts for daily writing, gratitude, reflection, morning pages, evening review, weekly summary. 日记、写作、反思、感恩。
Use when maintaining RDR2 (Red Dead Redemption 2) playthrough notes — logging an acquisition ("acquired X", "got N gold bars", "finished X"), answering in-game location/crafting questions, or reviewing the notes for duplicate or stale info. Triggers on RDR2, Red Dead Redemption, playthrough, legendary animal, talisman, trinket, valerian root, gold bar, horse, weapon, berry.
Use when a sales rep already has a customer who has expressed some need (from outreach follow-up, account-landing research, customer-initiated contact, or meeting notes) and needs to structurally validate whether that need is real, urgent, whose pain it actually is, and whether it matches the team's capability — before pushing to ROI proofing or buying-intent assessment. Triggers: '验证一下这个需求是不是真的', '需求真不真', '客户说痛但我不确定', '这个客户值不值得跟', '客户说会考虑但是真的吗', '谁拍板', '现有方案是什么', '切换成本', 'need validation', 'pain point validation', 'is this a real need', 'verify customer need'. Do NOT use for: scoring leads at line-item level, building target-customer profiles, calculating ROI, overall buying-intent scoring, opportunity-stage assessment, or writing outreach/cold messages.
Microsoft OneNote integration. Manage Notebooks. Use when the user wants to interact with Microsoft OneNote data.