DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.

1,180+ deals tracked  ·  22 AI investment memos  ·  Updated daily

← Back to leaderboard

Memoriki

Show HN: Memoriki – LLM Wiki+MemPalace for persistent personal knowledge bases

52 AI Score
Show_hn other Added Apr 10, 2026

Details

Sector
other
Total Funding
$0
Last Round
$0

About

Memoriki is a template for building personal knowledge bases where the LLM does all the maintenance work.<p>It combines Karpathy&#x27;s LLM Wiki pattern (structured markdown wiki maintained by an LLM) with MemPalace (an MCP server that adds semantic search and a temporal knowledge graph).<p>Three layers: - Wiki pages with [[wiki-links]] and YAML frontmatter - the LLM creates and maintains these - Semantic search via embeddings (ChromaDB) - find things by meaning, not keywords - Knowledge graph with typed relationships and date validity - &quot;what changed since last month?&quot;<p>It&#x27;s not RAG. RAG re-derives answers from raw chunks every time. Here the LLM compiles knowledge into wiki pages once, keeps them current as new sources arrive, and the graph tracks how everything connects.<p>Works with any MCP-compatible agent (Claude Code, OpenAI Codex, Cursor, Gemini CLI).<p><a href="https:&#x2F;&#x2F;github.com&#x2F;AyanbekDos&#x2F;memoriki" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;AyanbekDos&#x2F;memoriki</a>

AI Score Reasoning

Memoriki presents a technically sophisticated approach to AI-native knowledge management by moving beyond standard RAG into structured, LLM-maintained wikis. While the product architecture is innovative and leverages modern standards like MCP, it currently lacks commercial traction, team pedigree, and a clear path to monetization beyond being an open-source template.

Source

Show_hn — View original →