Skip to content

v1.33.0

Choose a tag to compare

View all tags
@github-actions github-actions released this 28 Aug 14:43
· 77 commits to main since this release
v1.33.0
74afa24

Added

  • Generated sessions/<id>.md pages now surface the originating harness as
    agent frontmatter alongside session_id. The value comes from the
    persisted session row, so LLM rewrites, compaction checkpoints, spool
    drains, and superseding versions do not mistake the later writer for the
    origin; manual page writes remain unattributed. (#494)

Fixed

  • Prevented stored Markdown from automatically fetching external image URLs
    when viewed in the web UI, while preserving clickable external links and
    same-origin relative images (#491).
  • Made managed routing SKILL.md payloads byte-identical across release
    platforms. Windows builds previously embedded CRLF from the runner checkout
    while Linux and macOS builds embedded LF, so one tag returned different
    bytes through CLI installs and memory_install_self_routing. The embedded
    assets now use LF everywhere without rewriting user-authored files. (#502)
  • PowerShell compatibility hooks no longer assign to a local $home variable.
    PowerShell names are case-insensitive, so that collided with the automatic
    read-only $HOME variable and emitted VariableNotWritable for every hook
    payload carrying a cwd. The marker-boundary helper now uses $userHome, with
    native Windows and static shell regressions covering the error stream and
    reserved-name contract (#498).
  • PowerShell compatibility hooks now encode JSON request bodies as explicit
    UTF-8 bytes and declare charset=utf-8. Windows PowerShell 5.1 otherwise
    encoded string bodies using a host-dependent legacy code page, so prompts,
    paths, or tool content containing non-ASCII text could make /hook return
    HTTP 400 and disappear from memory while ASCII events still worked. A native
    Windows loopback test now round-trips Chinese and Portuguese text byte for
    byte (#500).

Checksums (SHA256)

e4c059b327462f21f6ff2be0d61fa3d373978e5795370e7db36350c1259434ca  ai-memory-hooks.tar.gz
448f6cfad616e13692598dd49709ce9dec10eed0f702818ccca4a0c54a79f8c7  ai-memory-install-hooks
6d4c35678d1041106e7ae86226184655da99b03359dce2430d71f94e6be9f77a  ai-memory-linux-aarch64.tar.gz
0b5653bb8a0555230bd7ea753e28e639b7d81a65f81b116dafc343385efe012b  ai-memory-linux-x86_64.tar.gz
9dfdfb02cb8cf4580cdc16b069a205e402b81aecfdd9ddcf53aa6df5ba88db13  ai-memory-macos-aarch64.tar.gz
0e96643b35d5b9038067c67d2667edf3192654c99a8dde81a71c2a859042ed61  ai-memory-macos-x86_64.tar.gz
7ebc829b8afd63734d79fdadb7b5eb31c8bbc2d948c067b6695524fae05ad4c7  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
780415c858edb6dc1e0da5066081cb840566ffa74ddb6b1d613c837541916b97  ai-memory-wrapper.ps1
52afdf14994ae9b4eb3dcfc09f1d5b12a47b8936d2f0ca14fdf03997565bc545  ai-memory-wrapper

Install

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

# Docker
docker pull akitaonrails/ai-memory:1.33.0

# 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 toolchain): download ai-memory-windows-x86_64.zip below,
# extract it, and follow the bundled docs/windows.md.

# From source
cargo install --git https://github.com/akitaonrails/ai-memory --tag v1.33.0
Assets 22
Loading