Local-first agent memory

Tree Ring Memory Framework

A framework-agnostic memory lifecycle layer for AI agents: fresh work stays detailed, older learning compresses, scars stay visible, and durable truths become heartwood.

Agent-centricMemory that travels, adapts, and evolves with agents.
Framework-agnosticWorks with any agent stack, model, or orchestration framework.
Lifecycle-awareContinuously distills, compresses, and preserves what matters.
Built to lastResilient memory that scales across time, tasks, and tools.

Memory should age, not pile up.

Most agent memory either disappears between runs or grows into raw transcript sludge. Tree Ring Memory gives memory a lifecycle: capture, scope, recall, audit, consolidate, forget, and supersede.

Rust-native runtime

CLI, crates, local storage, recall, import/export, audit, consolidation, maintenance, and terminal UI.

Local SQLite/FTS

No required cloud service. Durable memory stays local by default and remains inspectable.

Explainable recall

Results carry ring, scope, confidence, and ranking signals so memory is not magic.

Forgetting is first-class

Deletion, redaction, supersession, expiry, sensitive audit, and maintenance are core surfaces.

Evidence loop

Use tree-ring evidence for evaluated outcomes that should become scars or heartwood.

Agent-aware adapters

DOX/Revolve sync, read-only framework discovery, and portable skill guidance for agent runtimes.

The rings

The point is not to store more. The point is to keep memory useful as it ages.

Cambium

Fresh active context for the current work.

Outer

Recent summarized learning and decisions.

Inner

Older compressed project knowledge.

Heartwood

Durable, high-confidence truths.

Scars

Failures and regressions worth remembering.

Seeds

Unresolved ideas and future hypotheses.

Try it locally.

Tree Ring Memory is protocol-preview software. Install the Rust CLI, create a local memory root, store one concise lesson, recall it, and tell us where the workflow should go next.

  • No hidden transcript recorder.
  • No required hosted service.
  • Durable writes are explicit.
  • Feedback flows through GitHub issue #26.
# Portable installer
curl -fsSL https://raw.githubusercontent.com/TerminallyLazy/Tree-Ring-Memory/main/install.sh | sh

# macOS ARM64 Homebrew tap
brew tap TerminallyLazy/tree-ring
brew install tree-ring

tree-ring init
tree-ring remember "Use project-scoped recall before risky changes." --event-type lesson --scope project
tree-ring recall "risky changes"
tree-ring evidence "The eval passed after the fix." --outcome promoted --evidence-ref evals/run-042
tree-ring tui

Built for agent builders.

The launch question is practical: what should a portable, local-first memory layer get right before deeper framework bridges land?