Show HN: A self-organizing digital Zettelkasten for research
Funes is a Git-based framework designed to transform raw sources into organized knowledge with the help of an AI Librarian. This system ingests, compiles, and manages information, producing various outputs while maintaining a structured knowledge base. The project is inspired by Borges's character Funes, who remembers everything but struggles with abstraction, aiming to preserve raw data and abstract it into usable concepts.
- ▪Funes uses an AI Librarian to manage and compile raw sources into a structured Markdown wiki.
- ▪The workflow allows users to provide sources and questions while the Librarian handles writing and organization.
- ▪The project is named after Borges's character Funes, emphasizing the importance of both memory and abstraction in knowledge management.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/ulyssestenn/funes |
| Publication time | Wed, 27 May 2026 16:59:32 +0000 |
| Retrieval time | 2026-05-27T17:08:01.967Z |
| Last seen | 2026-05-27T17:08:01.967Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | mzdKrSgT4wJC |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Funes Funes is a Git-based framework for turning raw sources into durable, cited knowledge work with an AI Librarian. The Librarian ingests raw sources, preserves them as an immutable record, compiles them into an interlinked Markdown wiki, and uses that wiki to produce cited answers, reports, analyses, routines, and other reusable outputs. You provide the sources and questions; the Librarian handles the writing, linking, indexing, health checks, and upkeep. Everything lives in plain Markdown inside a Git repo, so your knowledge base is versioned, diffable, portable, searchable, and usable from GitHub or any editor. The workflow adapts Andrej Karpathy's "LLM Knowledge Bases" idea to a plain Git repo instead of Obsidian.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.