DaiDocs: AI memory as a plain-text file format, not a service
English · 简体中文 .dai An open plain-text format for AI memory (launched Sep 2026). Your assistant's memory becomes files on your disk that you can open, grep and keep. Second on the LongMemEval-S leaderboard among memory systems anyone can re-run, 22.40 points above the same model with no memory, reading 10x fewer tokens per question.
- ▪English · 简体中文 .dai An open plain-text format for AI memory (launched Sep 2026).
- ▪Your assistant's memory becomes files on your disk that you can open, grep and keep.
- ▪Second on the LongMemEval-S leaderboard among memory systems anyone can re-run, 22.40 points above the same model with no memory, reading 10x fewer tokens per question.
Hacker News (AI / LLM) files mainly under ai. We currently carry 5,045 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/Kerneta/daidocs |
| Publication time | Tue, 15 Sep 2026 17:18:06 +0000 |
| Retrieval time | 2026-09-15T17:36:52.486Z |
| Last seen | 2026-09-15T17:36:52.486Z |
| 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 | 06o9KeQwcq3M · 1 stories |
| 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
English · 简体中文 .dai An open plain-text format for AI memory (launched Sep 2026). Your assistant's memory becomes files on your disk that you can open, grep and keep. Second on the LongMemEval-S leaderboard among memory systems anyone can re-run, 22.40 points above the same model with no memory, reading 10x fewer tokens per question. Every number here ships with its per-question judge verdicts and a sha256 manifest. Quickstart · The guide · Benchmark · The format · Reproduce it Launch release V4.4n32, 12 September 2026. What is in it. If .dai is useful to you, a star helps other people find it. The whole product, in one loop. Install, build, remember, recall: one store, every model, about a tenth of the tokens. The recording uses invented data.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.
Discussion
0 commentsMore from GitHub
