MemoHood and MemoBase – local memory and knowledge base for AI agents
MemoBase is a plugin for hermes-agent that creates a local knowledge base from various file types, web pages, YouTube content, audio, and Obsidian notes. It answers queries strictly using the indexed data, providing verbatim citations or a clear refusal when the information is absent. The system combines full‑text search (FTS5) with vector embeddings and a relevance‑fusion reranker, all stored in a local SQLite database.
- ▪MemoBase ingests PDFs, DOCX, HTML, MD, TXT, CSV, URLs, YouTube videos, audio recordings, and Obsidian vaults into a searchable SQLite database.
- ▪Queries are processed through a hybrid pipeline that merges BM25‑style FTS5 results with vector KNN scores using reciprocal rank fusion and a Cohere reranker.
- ▪If the retrieved fragments do not meet a sufficiency gate, the model refuses to answer rather than hallucinate, and any provided citation is verified against the source text.
- ▪The solution runs locally without requiring PyTorch or external cloud services, using fast ONNX embeddings and optional Whisper transcription for audio/video content.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,279 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/mxskorohood-cmd/memobase |
| Publication time | Thu, 23 Jul 2026 06:31:03 +0000 |
| Retrieval time | 2026-07-23T08:18:15.603Z |
| Last seen | 2026-07-23T08:18:15.603Z |
| 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 | NcEHEpfzh_2F |
| 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
📚 MemoBase Плагин для hermes-agent, который превращает ваши файлы (PDF/DOCX/HTML/MD/TXT/CSV), веб-страницы, YouTube-видео и целые каналы, аудиозаписи и заметки Obsidian в локальную базу знаний — и отвечает строго по ней: с дословными проверенными цитатами или честным отказом, если ответа в базе нет. 🌐 Русский · English Зачем · Возможности · Установка · Настройки · Инструменты flowchart TD subgraph ING["Загрузка — memobase_ingest"] FILES["Файлы и URL<br/>PDF / DOCX / HTML / MD / TXT / CSV"] OBS["Obsidian<br/>заметка или vault"] YT["YouTube<br/>видео или канал"] AUD["Аудио / голосовые / видео"] CAPS{"Субтитры<br/>ScrapeCreators → Apify"} STT["Расшифровка STT<br/>Groq Whisper → Gemini<br/>(таймкоды сегментов)"] EXT["Извлечение текста<br/>(SSRF-проверка для URL)"]…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.