remindb

Why I built this

Coding agents already have memory. CLAUDE.md, AGENTS.md, your notes folder, that growing pile of project READMEs. Stuff persists just fine.

The problem is how the agent consumes it. Every session starts by re-reading the whole pile from scratch — every Read, every Grep, scanning raw prose the agent has already processed dozens of times. Big context windows don't fix it. A 1M-token window is still paid per call, and still can't tell yesterday's stale note from today's relevant one.

Raw markdown is the wrong shape for memory. Not because it can't hold the words — it can — but because it forces the agent to pay full freight on every read.

remindb is a single SQLite file your agent treats as long-term memory. It parses your notes (Markdown, HTML, JSON, YAML, TOON) into a structured tree, hashes every node, encodes repetitive structures compactly when it saves tokens, and surfaces the whole thing through a tight MCP tool suite.

What you get

Each point is a summary — the full reasoning, with the tradeoffs, lives in docs/.

An ICR the agent can index, not skim. MemoryTree returns the Intermediate Context Representation — typed, labeled, token-counted — in one call instead of a directory walk and a pile of file reads. → The node tree

Hot vs. cold, like a real cache. Every node has a temperature that rises when it's read and decays over time. Hot nodes rank higher in search; cold ones stop crowding the top without ever being deleted. → Temperature

Summarization that happens when it should. When a node crosses the cold threshold the server nudges the agent to compact it in place — same anchor, same history, fewer tokens. No cron, no worker; it's driven by how the memory actually gets used. → Temperature

Git-style versioning, free. Every compile or write lands a snapshot with per-node diffs. A returning agent resyncs with MemoryDelta — a tiny payload instead of a whole-file re-read. → Versioning

TOON encoding where it pays off. Arrays of uniform objects store ~40% smaller in TOON than YAML or JSON. The parser tries both per node and keeps the win only when it's real; irregular prose stays plain text. The same ≥15% rule converts MathML in HTML to compact LaTeX. → TOON encoding · MathML → LaTeX

FTS5 search, not grep. Ranked anchors in milliseconds over a porter-tokenized index — no file rescans, no regex timeouts — trimmed to exactly the token budget you pass. → Search

Knowledge graph from lateral relations. Author [[Architecture; w=2.5]] in any payload and the compiler resolves a directed weighted edge; MemoryRelated traverses it up to 5 hops, ranked by path weight. Forward references self-heal. → Knowledge graph

Portable by design. The whole memory is one .db file. Copy it to another machine, hand it to another agent, commit it into a repo, sync it across devices. No server, no daemon, no external state — any MCP-capable agent can point serve at the same file and share the same knowledge.

Install

One-line install

Linux / macOS:

curl -fsSL https://raw.githubusercontent.com/radimsem/remindb/main/install.sh | bash

By default the binary lands at ~/.local/bin/remindb. Pick a different prefix:

curl -fsSL https://raw.githubusercontent.com/radimsem/remindb/main/install.sh | bash -s -- --prefix /usr/local

Windows (PowerShell 5.1+):

iwr -useb https://raw.githubusercontent.com/radimsem/remindb/main/install.ps1 | iex

Lands at %LOCALAPPDATA%\Programs\remindb\bin\remindb.exe. Override with -Prefix:

./install.ps1 -Prefix C:\tools\remindb

From source (Go 1.26+)

git clone https://github.com/radimsem/remindb.git
cd remindb
go build -o ~/.local/bin/remindb ./cmd/remindb

Verify:

remindb --version

Updating

Two moving parts: the binary (release tags) and the agent-side skills (remind, memorize — the markdown your agent loads to learn how to call the MCP tools). They iterate on different cadences, so they update independently.

Binary

remindb update

Reads the installed version, compares it against the latest GitHub release, and re-runs the install script only when they differ. dev-builds (from go build / go install) always proceed — there's no published version to compare against. Pass --force to reinstall regardless:

remindb update --force

Skills

The public skills live under skills/: remember (the plain-language front door), remind (read path), memorize (write path), and remindb-setup (connectivity/config). remind and memorize use progressive disclosure — a compact SKILL.md plus on-demand references/. They're refreshed by vercel-labs/skills.

First-time install — globally (every detected agent), or scoped to one agent:

# Global — install for all detected agents at once
npx skills@latest add radimsem/remindb/skills

# Scoped — install for one agent
npx skills@latest add radimsem/remindb/skills -a claude-code
# -a codex | gemini-cli | opencode | openclaw | hermes-agent | ...

Refresh later:

npx skills@latest update

Documentation

The README is the trailer. The manual is in docs/ — each page opens with the problem it solves, in plain language.

MCP tools

A Memory* tool suite, registered once, surfaced to any MCP-capable agent (Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, …). The read path is documented in the remind skill, the write path in memorize.