Tree Ring Memory
Tree Ring Memory is a framework-agnostic, local-first memory lifecycle layer for AI agents. It helps agents remember decisions, warnings, preferences, and lessons without turning memory into a transcript dump. It is for developers building AI agents that need persistent, structured memory.
✨ Key features
- Local-first SQLite/FTS storage with no required cloud service.
- Source-linked memories for decisions, scars, lessons, and truths.
- Rust-native CLI with import/export, audit, consolidation, and maintenance.
- Same-host multi-agent correlation and scoped recall filters.
- Optional coordinator capability enforcement for shared writes.
- Privacy defaults that block secret-like memory and hide sensitive details.
🎯 Use cases
- Store project-specific lessons and decisions for AI agents.
- Recall relevant memories with ranked search results.
- Audit memory for stale, sensitive, or contradictory entries.
- Sync memory with DOX/Revolve protocols.
- Run a terminal UI to browse memory rings and evidence.
📦 Installation
🧰 Requirements: Requires macOS ARM64 or Linux x86_64 for prebuilt installs, or Rust and Cargo for source installs. No API keys or accounts needed.
curl -fsSL https://raw.githubusercontent.com/TerminallyLazy/Tree-Ring-Memory/main/install.sh | sh -s -- --release latestcd <project-root>
curl -fsSL https://raw.githubusercontent.com/TerminallyLazy/Tree-Ring-Memory/main/install.sh | sh -s -- --project --init --release latest --no-animationbrew tap TerminallyLazy/tree-ring
brew install tree-ringcurl -fsSL https://raw.githubusercontent.com/TerminallyLazy/Tree-Ring-Memory/main/install.sh | sh🚀 Usage
tree-ring inittree-ring remember "Use project-scoped recall before changing release behavior." \
--event-type lesson \
--scope project \
--project example-service \
--tag release \
--tag workflowtree-ring recall "release behavior" --project example-servicetree-ring tui⚠️ Good to know
Tree Ring Memory is in protocol-preview status; shared activation is supported only for same-host local filesystem processes, and it does not claim safe SQLite sharing across hosts or network filesystems.
❓ FAQ
What is Tree Ring Memory?
It is a framework-agnostic, local-first memory lifecycle layer for AI agents, helping them remember decisions, warnings, preferences, and lessons without turning memory into a transcript dump.
How do I install Tree Ring Memory?
You can use the one-line installer with --release latest for prebuilt binaries, use Homebrew on macOS ARM64, or build from source with Rust and Cargo.
Does Tree Ring Memory require cloud services?
No, it uses local SQLite/FTS storage and has no required cloud service.
What is the current status of the project?
It is in protocol-preview status, with version history up to v0.15.3.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.