Kerneta/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 agentsJavaScript#agent-memory#ai-agents#ai-memory#chatgpt#claude

0.9 Steady Magnitude out of 10. Star growth looks organic. Data as of September 20, 2026.

Open on Seismograph Open on GitHub

About the project

Open plain-text .dai format for AI assistant long-term memory: history lives as files on your disk, readable by any LLM and grep. Ships with an MCP server and hooks for Claude, Cursor, Windsurf, Codex.

Useful for

Connect the MCP server to Claude Code or Cursor so the assistant saves and recalls context across sessions
Convert exported chat history into .dai files and search them with grep or git diff
Run the LongMemEval-S benchmark on your own store and compare memory quality across models

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

1 star so far today, about 2 expected by the end of the day.
The repository is 7 days old and already has 32 stars.
Hacker News: “Show HN: DaiDocs, AI memory as a plain-text file format, not a service” — 8 points, 4 days ago.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 32
Stars in a day: 2
Forks: 0
Issues and pull requests: 0
Watchers: 0
Language: JavaScript
License: Apache-2.0
Latest release: V4.4n32 · September 18, 2026
Created: September 13, 2026
Last push: September 18, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Hacker News discussions

Show HN: DaiDocs, AI memory as a plain-text file format, not a service8 points, September 15, 2026

Spotted in

September 20, 2026Spotted on Hacker News

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/Kerneta/daidocs.svg?lang=en)](https://gitnova.dev/en/r/Kerneta/daidocs)

Similar projects

8.9
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.

BreakoutAI agentsPython+1,954 stars in a day
8.4
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.

BreakoutAI agentsPython+897 stars in a day
8.3
trycua/cua
Open-source toolkit for computer-use agents: cloud and local desktops, an app automation driver, and benchmarks for training and evaluation. For those giving AI agents control of a computer.

BreakoutAI agentsHTML+533 stars in a day
6.8
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…

CoolingAI agentsTypeScript+470 stars in a day
6.6
latent-spaces/brag
An agent skill (Claude Code, Codex, opencode, etc.) that turns a project you just built into a short launch video with music, motion, and share copy — in one command. Rendering is powered by Hyperframes.

BreakoutAI agentsPython+315 stars in a day
6.5
dofastted/vm2api
A proxy service that turns a Setup Token into a Console-compatible Anthropic API: requests run through VMs with a native Claude Code subagent, without prompt injection. For those wanting to use Claude via the standard…

Early signalAI agentsJavaScript+160 stars in a day