📡 MCP Radar

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 serve

⭐ 29 stars
⑂ 0 forks
JavaScript
momentum ▲ 58.0
created 2026-09-13
on radar since 2026-09-15
star trend 22 → 29 since 2026-09-15
agent-memoryai-agentsai-memorychatgptclaudeclaude-codecontext-engineeringcursorfile-formatllmlocal-firstlong-term-memorylongmemevalmcpmcp-servermemoryopen-standardpersistent-memoryplain-text
View on GitHub ↗Homepage ↗

About daidocs

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. &9654; For higher quality, watch the demo live in your browser

A .dai file is three plain-text zones: a YAML header, a fenced JSON block, and the text. No binary, no database, no SDK required to read it.

- Any programming language. The reference engine is Node. A reader in Python, Rust or Go is an afternoon's work, and the spec is normative, written so that two independent implementations agree. - Any model. The store is written once by a cheap observer model and read by whichever model answers. The same store measured with five answering models: 78% to 92%. Change the model, keep the memory. - Any tool. grep, git log, diff, your editor, a shell script. Memory that answers to ordinary tools.

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/Kerneta--daidocs.html)

Related MCP servers

2672243194/agentbrain

Local-first long-term memory for AI agents - plain Markdown vault + thin MCP server. CJK-aware BM25, token-efficient by design.

⭐ 5Python
menot-you/n-memory

Memory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.

⭐ 5Rust
tinhien11/remem-mcp

Long-term memory MCP server for AI coding agents. SQLite + FTS5 + vector search, CodeGraph, error learning, compaction survival. Beats Mem0 on benchmarks. No cloud, no API key.

⭐ 3TypeScript
osaxyz/sepiace

Long-term memory for coding agents. The sepiace plugin for Claude Code and Codex.

⭐ 3TypeScript
tinhien11/tdai-memory-mcp

Local-first MCP memory server — Memory + CodeGraph + Wiki in one SQLite file. Tree-sitter code indexing, markdown wiki, lifecycle hooks, auto-capture. No API key, no cloud.

⭐ 4JavaScript
Masikomoore/agent-memory

One memory for every AI agent — self-hosted long-term memory over MCP/REST for Claude Code, Codex, Cursor, Gemini CLI, VS Code, OpenClaw, and more.

⭐ 3JavaScript

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.