Tree Ring Memory v0.11.0 launch preview

[TerminallyLazy]

Tree Ring Memory v0.11.0 is live as a launch preview.

Tree Ring Memory is a framework-agnostic, local-first memory lifecycle layer for AI agents. It is meant to help agents remember useful decisions, warnings, preferences, and evidence without turning memory into transcript dumps.

Public surfaces:

• Website: https://terminallylazy.github.io/Tree-Ring-Memory/
• Release: https://github.com/TerminallyLazy/Tree-Ring-Memory/releases/tag/v0.11.0
• Repository: https://github.com/TerminallyLazy/Tree-Ring-Memory
• Press kit: https://terminallylazy.github.io/Tree-Ring-Memory/press-kit.md
• LLM summary: https://terminallylazy.github.io/Tree-Ring-Memory/llms.txt
• Launch feedback issue: Launch feedback: try Tree Ring Memory and tell us where agent memory breaks #26

The current public runtime is Rust-native and local-first: CLI, SQLite/FTS storage, explainable recall, audit, deterministic consolidation, forgetting, DOX/Revolve adapters, framework discovery, and a Ratatui terminal console.

Install:

curl -fsSL https://raw.githubusercontent.com/TerminallyLazy/Tree-Ring-Memory/main/install.sh | sh
tree-ring init
tree-ring remember "Use project-scoped recall before risky release changes." --event-type lesson --scope project
tree-ring recall "release changes"

Feedback wanted:

• Which agent frameworks should get first-class bridge support?
• What should explainable recall show by default?
• Where does the ring model feel too simple or too heavy?
• What privacy or forgetting control is missing?
• What makes the first ten minutes hard?

Use this discussion for launch conversation, or the feedback issue above for concrete bugs and implementation requests.