Tree-Ring-Memory
llms.txt18 starsChanged 3 months agoMITView on GitHub
Tree Ring Memory is a framework-agnostic, local-first memory lifecycle layer for AI agents. Website: https://terminallylazy.github.io/Tree-Ring-Memory/ Repository: https://github.com/TerminallyLazy/Tree-Ring-Memory Launch release: https://github.com/TerminallyLazy/Tree-Ring-Memory/releases/tag/v0.15.0 Launch discussion: https://github.com/TerminallyLazy/Tree-Ring-Memory/discussions/27 Homebrew tap: https://github.com/TerminallyLazy/homebrew-tree-ring Feedback: https://github.com/TerminallyLazy/Tree-Ring-Memory/issues/26 Feed: https://terminallylazy.github.io/Tree-Ring-Memory/feed.xml License: MIT Status: protocol-preview Current version: 0.15.0 Tree Ring Memory helps AI agents remember useful decisions, warnings, preferences, and evidence without turning memory into raw transcript storage. Fresh memory stays detailed, older learning compresses into rings, important failures remain visible as scars, durable truths become heartwood, and future ideas stay…
- Pipes a download into a shell
- Installs packages
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- crates/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- fixtures/AGENTS.mdAGENTS.md
- marketing/AGENTS.mdAGENTS.md
- plugins/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- tree-ring-memorySkill
The file
Files
# Tree Ring Memory Framework > Tree Ring Memory is a framework-agnostic, local-first memory lifecycle layer > for AI agents. Website: https://terminallylazy.github.io/Tree-Ring-Memory/ Repository: https://github.com/TerminallyLazy/Tree-Ring-Memory Launch release: https://github.com/TerminallyLazy/Tree-Ring-Memory/releases/tag/v0.15.0 Launch discussion: https://github.com/TerminallyLazy/Tree-Ring-Memory/discussions/27 Homebrew tap: https://github.com/TerminallyLazy/homebrew-tree-ring Feedback: https://github.com/TerminallyLazy/Tree-Ring-Memory/issues/26 Feed: https://terminallylazy.github.io/Tree-Ring-Memory/feed.xml License: MIT Status: protocol-preview Current version: 0.15.0 ## Summary Tree Ring Memory helps AI agents remember useful decisions, warnings, preferences, and evidence without turning memory into raw transcript storage. Fresh memory stays detailed, older learning compresses into rings, important failures remain visible as scars, durable truths become heartwood, and future ideas stay as seeds. ## What Ships Now - Rust-native CLI and crates. - Local SQLite/FTS storage. - Explainable recall with ring, scope, confidence, and ranking signals. - Explicit forgetting, redaction, supersession, audit, and maintenance. - Deterministic consolidation without requiring an LLM. - Source-linked evaluated outcomes through `tree-ring evidence`. - Controlled workflow-proof artifacts with explicit model identity and exact structured-output checks. - Same-host multi-agent identity, scoped recall, and exact-retry idempotency. - Optional coordinator authorization for shared writes and lifecycle mutations. - Project-local harness activation with receipt-backed readiness. - DOX and Revolve sync adapters. - Read-only agent-framework discovery. - Terminal onboarding and a Ratatui operator console. - Verified prebuilt bootstrap and scope-preserving CLI updates. ## Verified Prebuilt Install ```bash curl -fsSL https://raw.githubusercontent.com/TerminallyLazy/Tree-Ring-Memory/main/install.sh | sh -s -- --release latest ``` Recommended project-local setup from the project root: ```bash curl -fsSL https://raw.githubusercontent.com/TerminallyLazy/Tree-Ring-Memory/main/install.sh | sh -s -- --project --init --release latest --no-animation ``` macOS ARM64 Homebrew install: ```bash brew tap TerminallyLazy/tree-ring brew install tree-ring ``` Source install requires Rust and Cargo and omits `--release latest`. ## Update ```bash tree-ring update --check tree-ring update tree-ring --root .tree-ring init ``` The updater verifies official assets and preserves the active install scope. Pre-0.15 CLIs must first be upgraded with their existing manager or prefix. ## First Commands ```bash tree-ring init tree-ring remember "Use project-scoped recall before risky release changes." --event-type lesson --scope project tree-ring recall "release changes" tree-ring evidence "The eval passed after the fix." --outcome promoted --evidence-ref evals/run-042 tree-ring tui ``` ## Ring Model - `cambium`: fresh active context. - `outer`: recent summarized learning. - `inner`: older compressed learning. - `heartwood`: durable high-confidence truths. - `scar`: important failures, regressions, and warnings. - `seed`: unresolved ideas and hypotheses. ## Privacy Boundary Tree Ring Memory is local-first by default. It does not scrape transcripts, run a hidden recorder, or turn terminal event pulses into durable memory. Durable writes are explicit. ## Canonical Links - Launch page: https://terminallylazy.github.io/Tree-Ring-Memory/ - Text launch note: https://terminallylazy.github.io/Tree-Ring-Memory/launch/tree-ring-memory-framework.md - Rust article: https://terminallylazy.github.io/Tree-Ring-Memory/launch/rust-native-agent-memory-cli.md - Press kit: https://terminallylazy.github.io/Tree-Ring-Memory/press-kit.md - Repository: https://github.com/TerminallyLazy/Tree-Ring-Memory - Launch release: https://github.com/TerminallyLazy/Tree-Ring-Memory/releases/tag/v0.15.0 - Launch discussion: https://github.com/TerminallyLazy/Tree-Ring-Memory/discussions/27 - Homebrew tap: https://github.com/TerminallyLazy/homebrew-tree-ring - Feedback issue: https://github.com/TerminallyLazy/Tree-Ring-Memory/issues/26 - Atom feed: https://terminallylazy.github.io/Tree-Ring-Memory/feed.xml
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

