akitaonrails/ai-memory v3.4.2

on GitHub

Upgrade notes

• Projects split by a git remote that arrived after capture began (#1993). 3.4.1's repair renamed the two projects but left the repository identity on the archived one, so capture and later launches could still route there. Upgrade the server, then run ai-memory repair-split --project-id <session project> --from-project-id <empty remote project> for any pair repaired with 3.4.1 or renamed by hand. Newly found splits are repaired from the ai-memory run prompt.
• OMP and Pi users (#1990): regenerate the extension after upgrading (ai-memory upgrade, or ai-memory install-hooks --agent omp --apply / --agent pi) so ranged reads and @/file:// paths of ignore_paths files are dropped.
• Restore no longer undoes a session purge (#1989). Restoring a purged session's summary is now refused; git history and backups remain the recovery path.

Notes

• ai-jail: checked against ai-jail 2.15.0, the latest release. This release adds its --map / --rw-map folder mounts and documents that --github now also shares the gh token.
• Benchmarks carried forward: nothing in v3.4.1..v3.4.2 touches retrieval. The store reader change is the #1989 restore precheck, the capture-policy change only drops excluded OMP/Pi paths, and ranking, consolidation, embeddings and evals/ are untouched. The 3.4.0 LongMemEval-S numbers stand: hit@5 0.951 zero-LLM, 0.940 local embeddings.

Checksums (SHA256)

0399553bab27d1ee08cda13731d86c191d4a83be63f87dcbb337e2407d1c612d  ai-memory-3.4.2-1.aarch64.rpm
41b17b731cf3c13cc7927ec6d224eeae74df4e469484df1800cff98d6795d53b  ai-memory-3.4.2-1.x86_64.rpm
9040ee922b90e9c368849f117414b92ac3bf52992425dc6bd041061a9a2dce4c  ai-memory-claude-plugin.zip
647969524c84a8146b6170e57f76a17d0f6885df9193b5e04f467465a5176b7c  ai-memory-hooks.tar.gz
5b8b9030c247b091ac2bacbf181f52f8fdba9d4ed47cdef23faab874d4c94d9f  ai-memory-install-hooks
164f7c38bb9bafca218dd958c3c60febcd5d2f5200ad138c6f128576cedebfb6  ai-memory-linux-aarch64.tar.gz
15a4f4a346a27e6fd63a36d1b3de23c5cbe142b80b3bce561e21b1f225a1e645  ai-memory-linux-x86_64.tar.gz
afefdfa7bac1dcbb9d4358f812825bba823470831a3e72ba804e9de5fada159b  ai-memory-macos-aarch64.tar.gz
93f7c5d644e6de539e2ec9efb65c9596fda95b3f9470cab20645e4c7e673214a  ai-memory-macos-x86_64.tar.gz
df4db331663a08099dbb27864f362776ef560781a20cf206bb85555c24d9476e  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
5e405aa237a2399f13084f71ae89545cbca77683c8251b4c4572cb51aedc8de4  ai-memory-wrapper.ps1
c91a788f20456d066f6678ede33184172916bd53046de730b96566ba968d3d68  ai-memory-wrapper
6b105e4c8e6bcb3a2561a5316615a5c577b4074df24a1414ea45d306c1c7b89a  install.ps1
758c5d19348120619bbf8246b18975685daea2a2443017b47cd69ee64d6340bd  install.sh

Install

# Linux/macOS, no root: checksum-verified release binary under ~/.local, then one-step setup
curl -fsSL https://github.com/akitaonrails/ai-memory/releases/download/v3.4.2/install.sh | AI_MEMORY_VERSION=3.4.2 sh
ai-memory setup

# Arch Linux (AUR)
yay -S ai-memory-bin      # prebuilt Linux x86_64/aarch64 binary
yay -S ai-memory          # builds from source

# Fedora: download the matching RPM below, then run sudo dnf install ./ai-memory-<version>-1.<arch>.rpm

# Docker
docker pull akitaonrails/ai-memory:3.4.2

# macOS aarch64/x86_64 (no toolchain): download the matching ai-memory-macos-<arch>.tar.gz below,
# extract it, and follow the bundled docs/macos.md.

# Windows x86_64, no admin (PowerShell): checksum-verified release under %LOCALAPPDATA%\Programs, then one-step setup
$env:AI_MEMORY_VERSION='3.4.2'; irm https://github.com/akitaonrails/ai-memory/releases/download/v3.4.2/install.ps1 | iex
ai-memory setup

# Windows (Scoop)
scoop bucket add akitaonrails https://github.com/akitaonrails/scoop-bucket
scoop install ai-memory
ai-memory setup

# From source
cargo install --locked --git https://github.com/akitaonrails/ai-memory --tag v3.4.2