HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
Kerneta
daidocs
Python2026–2026
Kerneta / daidocs

daidocs

Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP server + hooks for Claude Code, Claude Desktop, Cursor, Windsurf, Codex. 83% LongMemEval-S (GPT-4o), 92% (Claude Fable 5), 10x fewer tokens.

AI & Machine LearningSystems & InfrastructureScience & EngineeringMobile & Desktop
Explore on GitHubRead Hacker News discussions
2Distinct people
4Mentions
0Explicit recommenders
55GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP server + hooks for Claude Code, Claude Desktop, Cursor, Windsurf, Codex. 83% LongMemEval-S (GPT-4o), 92% (Claude Fable 5), 10x fewer tokens.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by day4 dated mentions

Observed mentions: 2026-09-15 17:18:06 UTC to 2026-10-08 11:50:56 UTC.

012026-09-15 00:00:00 UTC to 2026-09-16 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsSep 152026-09-16 00:00:00 UTC to 2026-09-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-17 00:00:00 UTC to 2026-09-18 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-18 00:00:00 UTC to 2026-09-19 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-19 00:00:00 UTC to 2026-09-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-20 00:00:00 UTC to 2026-09-21 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-21 00:00:00 UTC to 2026-09-22 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-22 00:00:00 UTC to 2026-09-23 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-23 00:00:00 UTC to 2026-09-24 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-24 00:00:00 UTC to 2026-09-25 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-25 00:00:00 UTC to 2026-09-26 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2026-09-26 00:00:00 UTC to 2026-09-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsSep 262026-09-27 00:00:00 UTC to 2026-09-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-28 00:00:00 UTC to 2026-09-29 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-29 00:00:00 UTC to 2026-09-30 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-30 00:00:00 UTC to 2026-10-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-10-01 00:00:00 UTC to 2026-10-02 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-10-02 00:00:00 UTC to 2026-10-03 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-10-03 00:00:00 UTC to 2026-10-04 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-10-04 00:00:00 UTC to 2026-10-05 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-10-05 00:00:00 UTC to 2026-10-06 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-10-06 00:00:00 UTC to 2026-10-07 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-10-07 00:00:00 UTC to 2026-10-08 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-10-08 00:00:00 UTC to 2026-10-09 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsOct 8

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Sep 152026-09-15 00:00:00 UTC2026-09-16 00:00:00 UTC110
Sep 162026-09-16 00:00:00 UTC2026-09-17 00:00:00 UTC000
Sep 172026-09-17 00:00:00 UTC2026-09-18 00:00:00 UTC000
Sep 182026-09-18 00:00:00 UTC2026-09-19 00:00:00 UTC000
Sep 192026-09-19 00:00:00 UTC2026-09-20 00:00:00 UTC000
Sep 202026-09-20 00:00:00 UTC2026-09-21 00:00:00 UTC000
Sep 212026-09-21 00:00:00 UTC2026-09-22 00:00:00 UTC000
Sep 222026-09-22 00:00:00 UTC2026-09-23 00:00:00 UTC000
Sep 232026-09-23 00:00:00 UTC2026-09-24 00:00:00 UTC000
Sep 242026-09-24 00:00:00 UTC2026-09-25 00:00:00 UTC000
Sep 252026-09-25 00:00:00 UTC2026-09-26 00:00:00 UTC110
Sep 262026-09-26 00:00:00 UTC2026-09-27 00:00:00 UTC000
Sep 272026-09-27 00:00:00 UTC2026-09-28 00:00:00 UTC000
Sep 282026-09-28 00:00:00 UTC2026-09-29 00:00:00 UTC000
Sep 292026-09-29 00:00:00 UTC2026-09-30 00:00:00 UTC000
Sep 302026-09-30 00:00:00 UTC2026-10-01 00:00:00 UTC000
Oct 12026-10-01 00:00:00 UTC2026-10-02 00:00:00 UTC000
Oct 22026-10-02 00:00:00 UTC2026-10-03 00:00:00 UTC000
Oct 32026-10-03 00:00:00 UTC2026-10-04 00:00:00 UTC000
Oct 42026-10-04 00:00:00 UTC2026-10-05 00:00:00 UTC000
Oct 52026-10-05 00:00:00 UTC2026-10-06 00:00:00 UTC000
Oct 62026-10-06 00:00:00 UTC2026-10-07 00:00:00 UTC000
Oct 72026-10-07 00:00:00 UTC2026-10-08 00:00:00 UTC101
Oct 82026-10-08 00:00:00 UTC2026-10-09 00:00:00 UTC110

What Hacker News says

4 sources
aly33·Oct 8, 2026Submission

Show HN: Open-Source DaiDocs now beats Graphify by 218x low tokens, 83% on LME

We have been working on making an Open-Source standard documents for AI LLM's and Agents. Just like an excel file, .dai (Document AI) is a new standard to keep memory local and use with any AI agents and LLM's. This new standard comes with lots of features such as more than 10x tokens savings (tested on LongMemEval-S) when comapred the .dai to raw files and scored 83% with gpt-4-0 and 92% with Fable 5! (This shows how well it remembers a very long conversation), as well as an increased context window (fitting more than 1m tokens chat in a model which has a max of 1m context window) and much more. Then we moved to coding agents and make the .cai (Code AI) file standard and when compared to Grpahify, these savings were 218x and compared to a raw file it were 2976x! That's a LOT! We have all the codes and reproduceable numbers on our github
Read the rest
.com/kerneta/daidocs. We urge the community to try it and contribute as much as they can, as no vendor (like Anthropic or OpenAI) would ever develop this and this is all community driven!
4 points · Open discussion
aly33·Oct 7, 2026
Hi Everyone! I'm the Co-Founder of DaiDocs (daidocs.com). The claim that daidocs beats graph DB (technically graphify) by x218 less tokens is very bold and I'm sure you would like to test this out yourself. We have put the full details and the recreateable files for our claims on our github repo here: github.com/kerneta/daidocs. Let us know about your honest feedback, we'd appreciate it!
In Show HN: Plain-text code memory that beats a graph DB at x218 fewer tokens

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.