ai-memory 2.1.1

A patch release: correctness and cost fixes on top of 2.1.0. No new features, no
migrations, no config changes — safe to upgrade in place.

Fixed

• serve no longer re-archives the whole data dir on every start (#669). The
  OKF-conformance backup gate flagged the frontmatter-less monthly log-YYYY-MM.md
  event ledgers as pre-OKF, so a full tar.gz of the data dir was taken on every
  boot once a ledger existed. Ledgers are now excluded from that scan (the flip-side
  of 2.1.0's indexer fix). High-impact for long-running servers.
• Promptless internal sessions no longer flood the wiki (#662). A session is now
  synthesized into a sessions/<id>.md page only when it logged real work (a user
  prompt or a tool use). OpenCode's internal session.idle/branch-naming events —
  which emit only a stop — stop creating ephemeral no-op pages. Provider-agnostic;
  applied on both the router and the atomic store check.
• Wiki commits stop re-hashing the entire tree (#665). Since the #594 guard,
  every commit cleared the git index and re-read every page, so session-end cost
  grew with the wiki. Staging now uses libgit2's stat cache and re-hashes only on
  the rare tree-write failure; concurrent commits are serialized instead of dropping
  a snapshot.
• A capture-only .ai-memory.toml marker no longer resets scope to default
  (#668). A subdirectory marker added only to exclude paths from capture used to
  shadow an ancestor marker's workspace/project, filing pages under the wrong
  scope. Such a marker is now scope-transparent — fixed across all three front doors
  (POSIX/PowerShell scripts, the native binary, and the generated TypeScript
  integrations).
• Typed relations preserved in multi-page consolidation (#667). Batch updates
  now carry the closed causes/fixes/contradicts edges into frontmatter and the
  link index instead of silently discarding them.
• A leading UTF-8 BOM on a frontmatter-less page is dropped (#663), so the H1
  title is detected and the OKF conform pass doesn't push a stray marker into the
  body.

Changed

• The managed routing snippet notes that ai-memory is the cross-harness memory of
  record: durable project facts belong here, not duplicated in a harness's own local
  memory store that other agents can't see (#671).

See CHANGELOG.md
for the full list.

Checksums (SHA256)

b2425e64566e455473e067345054d006803e8090e828eb938b77ba8668518bd6  ai-memory-hooks.tar.gz
60cdc739c21f38b017c89f7fdc5708eb8d08fec715dfa62f364c23698094b074  ai-memory-install-hooks
72da124c2a9ab3843e44bef2d1b66a0f2313a4b557ad31578d99b2470c6be96c  ai-memory-linux-aarch64.tar.gz
5057d229e9bdcc488e284a11b9606b130b6ed6ccac79e541f42b6dfeb045ea73  ai-memory-linux-x86_64.tar.gz
1cc2acdbbd62cc7ecf6e1fe91515ea77786910b2c102f1fe8781aa6c0357eb64  ai-memory-macos-aarch64.tar.gz
3c2ca543abdf964c7fe4471e54824876d7327a04d0f222327ad6a8f010f78910  ai-memory-macos-x86_64.tar.gz
d65c989dbac7cceb6e8c587756db92dd3c145ec8743da591968992fb4e1babc3  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
2d35c2f1fba28a1aee3ffeb58e3deaec772803f3dc6fd159de6ae0a47ba797ac  ai-memory-wrapper.ps1
127282baf003aec6a5e3a8c73c5186ff785c2a412c93e5538141ceb9b04909d9  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:2.1.1

# 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 --locked --git https://github.com/akitaonrails/ai-memory --tag v2.1.1

ai-memory 2.1.0

The 2.1 feature train, on top of every 2.0.x fix.

Highlights

Ordered LLM provider fallback chains (#648). Configure [[llm_fallbacks]] in
config.toml with additional providers (each with its own model, optional
base_url, and api_key_env). On a transient failure — 429, 5xx, timeout, or
connection error — the chain advances to the next provider, preserving the
original request, schema, and operation id; deterministic failures (bad request,
auth, unsupported schema) stop immediately. Per-candidate circuit breaker,
resolved-once credentials that never inherit the primary's env var, and passive
per-candidate health in ai-memory status — labels and status only, never keys
or response bodies.

bootstrap --resume (#621, #635). An interrupted bootstrap resumes from
durable per-chunk progress instead of re-paying for every LLM call. It adopts
only the contiguous completed prefix and re-runs from the first gap, so a resumed
run can never diverge from a clean one. Complements the transient-retry from
2.0.3.

First-party OpenCode 2.0 beta (#622). install-mcp --client opencode2,
install-hooks --agent opencode2, and ai-memory run opencode2 — full lifecycle
capture, handoff injection, and managed launch/resume/import against the V2
plugin shape. Shares v1's config dir and session store; no store migration.

Codex native SessionEnd (#604, #605). install-hooks --agent codex now wires
Codex's first-class SessionEnd event (Codex CLI 0.145.0+), so a finished Codex
session gets the same automatic end-of-session summary and cross-agent handoff
Claude Code already gets.

Operator LLM headers (#606). AI_MEMORY_LLM_HEADERS / llm_headers attaches
caller-identifying HTTP headers to every LLM request, validated once at the config
boundary and marked sensitive on the wire.

Also in 2.1.0 (fixes forward-merged from the 2.0.x line)

• Auth-disabled servers stop returning 401 for a stale bearer (#639); invalid
  bearers still rejected whenever any auth mode is enabled.
• Cursor sessions are filed under their repo and the cursor agent instead of
  default/scratch + claude-code (#651).
• reindex no longer aborts on a scope created after startup — the manifest is
  written with the scope's first page, and a missing manifest names its path
  instead of a bare os error 2 (#643).
• purge-session removes the on-disk wiki page so a later reindex can't
  resurrect a forgotten session (#653).
• [briefing] max_chars now bounds the whole brief, never just the bodies, and
  the mandatory untrusted-history scaffold is always preserved (#657).
• Static-vs-session MCP client routing guidance prevents another session's active
  project from capturing an unscoped write (#372).
• Podman-without-Docker support in the bin/ai-memory wrapper (#636).
• Self-contained build (vendored Tailwind default, no build-time network) and a
  faster two-tier dev test loop (#645).

See CHANGELOG.md
for the full list.

Checksums (SHA256)

815fdb3ff32d630aaf7778af7bc01b18ed6fb3fdf2d43de28de57b21bb46312b  ai-memory-hooks.tar.gz
60cdc739c21f38b017c89f7fdc5708eb8d08fec715dfa62f364c23698094b074  ai-memory-install-hooks
3eafda7afaba63008c2b0e27713c1076dff3b366c377c30f43a7b04a0d78b6c1  ai-memory-linux-aarch64.tar.gz
b4d911f392fea7f151c9c1ff83521922417570e5104ffb02a5e82253afc877ac  ai-memory-linux-x86_64.tar.gz
61811954da0ee1519024f81271cb7b34893a28d7c9e3d14d07eb80fadcf44d58  ai-memory-macos-aarch64.tar.gz
13259e2d60705d09b8b7dd8bbcea0d361b994498333095c91d0128f382a6a1da  ai-memory-macos-x86_64.tar.gz
72c477e5c02b54c202e1c7515aacf00a1702f9916c51a26d875fcfeff65b1451  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
2d35c2f1fba28a1aee3ffeb58e3deaec772803f3dc6fd159de6ae0a47ba797ac  ai-memory-wrapper.ps1
127282baf003aec6a5e3a8c73c5186ff785c2a412c93e5538141ceb9b04909d9  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:2.1.0

# 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 --locked --git https://github.com/akitaonrails/ai-memory --tag v2.1.0

ai-memory 2.0.3 — a patch release hardening the 2.0 line: data-safety, provider correctness, and reliability. No breaking changes; drop-in over 2.0.x.

Highlights

• 1.x rollback restored (#633). The pre-migration safety archive is now taken before the SQLite schema is migrated, so it is a genuine pre-2.0 recovery point a 1.x binary can reopen — the documented "reversible upgrade" works again. (Earlier 2.0.x archives captured the already-migrated DB and were 2.x-only.)
• Typed edges work on OpenAI-family providers (#630). relations was an open map that OpenAI strict mode silently emptied; it is now a fixed-shape object, so causes/fixes/contradicts edges emit again on openai, openai-oauth, copilot, opencode, and openai-compat.
• bootstrap reliability. Tolerates a chunk that returns no pages (#614); retries a chunk on transient LLM errors — 5xx/429/timeout — instead of discarding the whole run (#617).
• finalize-session --agent accepts every captured agent (#623) — hermes, claude-desktop, crush, other.
• Generated TypeScript integrations authenticate again under --apply (#625).
• Watcher no longer spams on orphan project dirs (#613, #616); dangling-project error clarified (#612); antigravity Windows hook quoting fixed (#611).
• Operability: ai-memory status and the pre-migration log now surface filesystem free space (#629); release/Docker/cargo install builds are --locked (#628); the auto-improve pending sidecar drops its always-pending status line (#624).

⚠️ Upgrading from 1.x

The OKF v0.2 wiki-format migration is automatic and backup-gated. As of 2.0.3 the automatic safety archive is a true pre-migration recovery point (restore it and start the old 1.x binary — #633). Full steps, including the surgical git-checkpoint rollback: docs/MIGRATION-2.0.md.

Full change list: CHANGELOG.md.

Checksums (SHA256)

0f547a0057c2a15a3f57ede4087215f905765c4ebaadbc60e00852b97ef0aa34  ai-memory-hooks.tar.gz
448f6cfad616e13692598dd49709ce9dec10eed0f702818ccca4a0c54a79f8c7  ai-memory-install-hooks
c053935c88c0b3f22a28a9a138fdbdbc9eb3ca5aa8626a3128fb56611460d32e  ai-memory-linux-aarch64.tar.gz
bdc2ae7623eb3bf39eb446f4c2b51aa65e60ce4496ac2c4c9618d14f59e464c9  ai-memory-linux-x86_64.tar.gz
466498c3dfb59b495d5ec232622357215a571dccbe4494cc3a03afa98251143f  ai-memory-macos-aarch64.tar.gz
6a47c4078215b62fd0f190892fb07cce08b6ae88dbaed324a4310b9dffd56bd6  ai-memory-macos-x86_64.tar.gz
f5614fe3da119696ef31182032dc09cb145f71efcc8a401c50a339542a52e9e8  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
2d35c2f1fba28a1aee3ffeb58e3deaec772803f3dc6fd159de6ae0a47ba797ac  ai-memory-wrapper.ps1
4b2e5736195f0ac4cd38adf62f25b294922ebf81f5f4802a07803e1abbf9f72d  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:2.0.3

# 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 --locked --git https://github.com/akitaonrails/ai-memory --tag v2.0.3

ai-memory 2.0.2

A patch release that hardens the 2.0 line — most importantly, it fixes two startup crash-loops that could block a 1.x→2.0 upgrade, and meets OpenCode Go's Sept 6 header requirement.

Upgrade-blocking fixes (upgrade to this before migrating)

• Windows: the OKF migration no longer aborts on the .serve.lock file the same server holds under an exclusive lock (os error 33). The backup walk now skips it. (#593, thanks @Gaalbu / @rafaelkenedy)
• libgit2 crash-loop fixed: the OKF migration could fail with invalid object specified … class=Tree and never start; the wiki commit now clears its index before staging so a stale cached blob OID can't abort it. (#594)

Fixes

• OpenCode Go: requests now send x-opencode-session + User-Agent: ai-memory/<version> — required before OpenCode Go starts rejecting header-less requests on 2026-09-06. (#608, thanks @lucazz)
• ZCode: install-hooks --agent zcode --apply no longer reports a config ZCode has rejected as "already up to date"; it now reports the offending keys. (#600, thanks @costajohnt)
• Empty page titles: pages with a blank frontmatter title (but a real # H1) read back correctly and no longer trip a bogus duplicate-title lint. (#599)
• Web UI: OKF bundle-index and relative in-wiki links no longer 404; directory paths list their pages. (#603)
• as_of / entity retrieval now work on real stores (entity index is populated from tags + a startup backfill). (#592)
• Local embeddings: the model download can no longer hang startup forever (connect + overall timeout). (#602)
• Windows PowerShell wrapper no longer crashes running status outside a git repo. (#591)

Security / hardening

• Auth-bearing HTTP headers with opaque values are redacted before capture. (#598, thanks @gb)
• Untrusted frontmatter values are length-bounded before logging; handoff and workstream content is size-bounded at the store boundary (defense in depth). (#607)

Docs

• macOS quickstart now states the server must be running before bootstrap/install-*/status. (#595)

Upgrading from 2.0.x needs nothing special — docker compose pull && docker compose up -d (or your platform's equivalent). Full list in CHANGELOG.md.

Checksums (SHA256)

f415e9f278060fd62ecdfc26d140427e9c631dddc003cc050da6d2f49a3feaa1  ai-memory-hooks.tar.gz
448f6cfad616e13692598dd49709ce9dec10eed0f702818ccca4a0c54a79f8c7  ai-memory-install-hooks
14c4ef51cb45ce7095abbabee2fe72a9d394fc72ceac51e29119747317af3baa  ai-memory-linux-aarch64.tar.gz
3c39d8d9afad57a34747e6c52a13036b7411de95e4a2b1bbcd11976f4da31a23  ai-memory-linux-x86_64.tar.gz
1b7113614c76f6d38d80e39d9657806e6621a3cd20eeddd0c1927eadacc1d0c6  ai-memory-macos-aarch64.tar.gz
2823c93a6e323718a1138501b926a1e46a73aab1d60cb3a8cd3ac45b98498a2e  ai-memory-macos-x86_64.tar.gz
33812222b35ff871a27b781855089825f1ad161b099c409e7c5c14180a07aa85  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
2d35c2f1fba28a1aee3ffeb58e3deaec772803f3dc6fd159de6ae0a47ba797ac  ai-memory-wrapper.ps1
4b2e5736195f0ac4cd38adf62f25b294922ebf81f5f4802a07803e1abbf9f72d  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:2.0.2

# 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 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 v2.0.2

ai-memory 2.0.1

Patch release: the human-readable wiki no longer drowns knowledge in machinery.

• One lint report per project. The lint pass supersedes a single _lint/report.md (history stays in the version chain) instead of writing a dated page every day — a long-lived store had accumulated 2,000+ of them, all indexed, searched, and embedded. Each pass also prunes the legacy dated pile, so existing stores clean themselves up with no migration; a pass with no findings removes the report entirely.
• Knowledge first in the web UI. The project view moves machinery (lint reports, session captures, monthly logs, bundle indexes) into a collapsed System sidebar section, and Recent Activity lists knowledge pages only — concepts, decisions, gotchas, notes, procedures, and _rules.
• Calmer homepage. The "LLM-optimised memory" explainer is dismissible (remembered per browser), and the redundant always-on backup banner is gone — the one-time migration dialog and ai-memory status carry that information.

Upgrading from 2.0.0 needs nothing special: docker compose pull && docker compose up -d (or your platform's equivalent). Details in CHANGELOG.md.

Checksums (SHA256)

8cb167a01d263473e72eea391720e9b81de03f56539eb28e0db3e96cb791d4a7  ai-memory-hooks.tar.gz
448f6cfad616e13692598dd49709ce9dec10eed0f702818ccca4a0c54a79f8c7  ai-memory-install-hooks
042bc86a97b78d1c6d5c195655410385b667af016b1f4db689340d1336a796cb  ai-memory-linux-aarch64.tar.gz
3fe40014a43f635f487d453c31ab1d1d2827451f7d1c2c2b685def617f48275c  ai-memory-linux-x86_64.tar.gz
99001e818ec0f1c3e609ac20868754509205f55116111cc1ecb2b729d2d2eaf4  ai-memory-macos-aarch64.tar.gz
9531ca7c250972f9d1e9d138f0ba836c289bce9260f5f22689505c0aca79aea0  ai-memory-macos-x86_64.tar.gz
0f641b87a0b77b86ded87ce340f6cc2677612a65dae4c7e89ab643564a888e0a  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
f4912fadae3f7aa0fa2f1612b40c8a915462330c217a6e7780cdd7be5ce5b068  ai-memory-wrapper.ps1
4b2e5736195f0ac4cd38adf62f25b294922ebf81f5f4802a07803e1abbf9f72d  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:2.0.1

# 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 v2.0.1

ai-memory 2.0

The wiki is now a portable open format, retrieval is hybrid by default, and memory quality is measured — LongMemEval-S hit@5 went from 0.617 → 0.823 in this release.

Highlights

• Local embeddings, on by default — in-process sentence embeddings (pure Rust, no API key, no external server). The model (~87 MB) downloads in the background on first start and existing pages are backfilled automatically; hosts that can't fetch it keep working FTS-only. Opt out with embedding_provider = "none". → docs/local-embeddings.md
• Open Knowledge Format v0.2 on disk — every page is a conformant OKF document; ai-memory export-okf streams a validated bundle you can import anywhere. → docs/okf.md
• Time-travel queries — memory_query accepts as_of to answer "what did we know about X then", including knowledge superseded since. → docs/temporal.md
• Typed relation edges — causes / fixes / contradicts in page frontmatter; declared contradictions surface as lint findings with zero LLM cost. → docs/typed-edges.md
• Cross-session experience pass (opt-in) — every N sessions, recent trajectories are reviewed side by side for knowledge visible only across sessions, staged through the same gated auto-improve path. → docs/experience.md
• Retrieval benchmark harness — ai-memory-eval retrieval runs LongMemEval-S against a real server end to end; baselines published. → docs/benchmarks/
• Search quality fixes — natural-language queries no longer crash FTS5 or surface stopword-only matches; status now reports embedding coverage, wiki format, typed edges, and write-queue backpressure truthfully.
• Offline durability for TypeScript integrations — OpenCode, OMP, Pi, and OpenClaw now spool failed hook deliveries and drain them when the server is reachable again, exactly like the shell hooks (#580).
• Also: single-instance serve lock (#563), refusal of misfiled unscoped writes (#564), macOS launchd agent (#569), llm_reasoning_effort across providers (#557), atomic capture-mode writes, and a laptop-offline day's worth of hardening. Full list in CHANGELOG.md.

⚠️ Migration — read before upgrading

• First 2.0 start migrates the wiki to OKF in place. It is gated on a verified full backup of the data dir, archived to your home directory (or AI_MEMORY_BACKUP_DIR); if the backup cannot be written and verified, the server refuses to start. Allow disk space and a moment proportional to your store.
• One-way door for shared stores. Once migrated, pre-2.0 binaries refuse the data dir. If several machines share one store, upgrade all of them; don't downgrade.
• Default embeddings change behavior. First start downloads the model in the background and backfills existing pages; hybrid search enables on the next restart. Air-gapped installs stay FTS-only (or drop the pinned model files in manually).
• Container/wrapper installs have specific path notes — see docs/MIGRATION-2.0.md for the full checklist.

Full changelog: v1.39.0...v2.0.0

Checksums (SHA256)

59c604813b74d7256ccc2e09007d5cb025106f360ff35a2112349b6df7e03e4c  ai-memory-hooks.tar.gz
448f6cfad616e13692598dd49709ce9dec10eed0f702818ccca4a0c54a79f8c7  ai-memory-install-hooks
d889eb21d242d7409ce06729c3f8aa506380d19e0ad02284ef9aef50a2cc5b4d  ai-memory-linux-aarch64.tar.gz
b872b162104dadbe12e7b1498c0e6e439709d7fac25859e183a9c19e7bf6ced9  ai-memory-linux-x86_64.tar.gz
3433db418fd1a3573dfda0ccedf1f7f8a40820d5af3b96912d5944bfd153d194  ai-memory-macos-aarch64.tar.gz
9d0d018fce6d53a744f64cc4ba27fd240c5f0c5a3ec1727eeb72fbe729091031  ai-memory-macos-x86_64.tar.gz
abfccc8cbb53108201614921196e069fc16f0b07bb55aa6c22bcafedb13295b3  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
f4912fadae3f7aa0fa2f1612b40c8a915462330c217a6e7780cdd7be5ce5b068  ai-memory-wrapper.ps1
4b2e5736195f0ac4cd38adf62f25b294922ebf81f5f4802a07803e1abbf9f72d  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:2.0.0

# 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 v2.0.0

Checksums (SHA256)

55d302283dccb2904c69981346bb54d29d33a04ea3b7fb27612ff8741a0cfef8  ai-memory-hooks.tar.gz
448f6cfad616e13692598dd49709ce9dec10eed0f702818ccca4a0c54a79f8c7  ai-memory-install-hooks
eca8b3b2dc72a4a44e828a0a1934ff8e0728eb6322bccb7f833d58185124fee4  ai-memory-linux-aarch64.tar.gz
621034bc3f83b425be843704b301c1533f8abaa1ae528b0da5d09e6052559f40  ai-memory-linux-x86_64.tar.gz
1ed9cd091dacfe063300ede09ce0808d5bb8c058996ecdda4e1da674b6ae145f  ai-memory-macos-aarch64.tar.gz
34cd27bb78c2c70476f7f0ec097f3171c22800ef219d9acfd220998fc2cbf872  ai-memory-macos-x86_64.tar.gz
dad7f2c835842a8b50837621ea9760c7b63e6d017a8ced32a66c360046454b05  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
f4912fadae3f7aa0fa2f1612b40c8a915462330c217a6e7780cdd7be5ce5b068  ai-memory-wrapper.ps1
4b2e5736195f0ac4cd38adf62f25b294922ebf81f5f4802a07803e1abbf9f72d  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:1.39.0

# 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 v1.39.0

Checksums (SHA256)

eb01765b411499d1e6a1e62aa9420f5667f9e3b07480d5b77bf4983f58a1d557  ai-memory-hooks.tar.gz
448f6cfad616e13692598dd49709ce9dec10eed0f702818ccca4a0c54a79f8c7  ai-memory-install-hooks
0cf5082e849c83040d63f3820f2aec2799416a8623f8ff0b1d5d6c55c16c0399  ai-memory-linux-aarch64.tar.gz
ff869fe2c9780cd464ccef4b2544e3e608854ffbd559f01fd86e32d9a1bbf626  ai-memory-linux-x86_64.tar.gz
87bcf74aed222733963b9ef05c3d815988908b5dbffcdfdf54c207e2fa71dc38  ai-memory-macos-aarch64.tar.gz
42321aebad2dd7e06dfa7d9cf693c8c302e9c71d9546c798ecde611275d0a779  ai-memory-macos-x86_64.tar.gz
143a65bf5b60e5e6454788ea11017c0779ba8dd82c0053ee61c2ee00f8916856  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
f4912fadae3f7aa0fa2f1612b40c8a915462330c217a6e7780cdd7be5ce5b068  ai-memory-wrapper.ps1
a83bde7e2a372181805be5670fb35f121bcec6cd73c5be86d8917fead9fff1dd  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:1.38.0

# 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 v1.38.0

Checksums (SHA256)

04546f8c431011c321ab82907f395c58cfa3af9c8265887c6818b7be005708be  ai-memory-hooks.tar.gz
448f6cfad616e13692598dd49709ce9dec10eed0f702818ccca4a0c54a79f8c7  ai-memory-install-hooks
a074b0213549584c36cb86efb75a5d9c127648b2c60dad3b93a9303182a879ae  ai-memory-linux-aarch64.tar.gz
db8035b6e34253453d633aa73710a0dddf9fd3d50b10ebecbf0344958ca35c56  ai-memory-linux-x86_64.tar.gz
27609dcc85395da310f0ff623ef81169b28678c5d0b27ed71477753c88a54b70  ai-memory-macos-aarch64.tar.gz
c89a9259d7c69a82e32d756933ea21e36e519b231f9dc04e1a2d35b341198e37  ai-memory-macos-x86_64.tar.gz
14cb8104e44c2222028ca46c5550d2fc09635528f92814d6210fcac9b79609bc  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
f4912fadae3f7aa0fa2f1612b40c8a915462330c217a6e7780cdd7be5ce5b068  ai-memory-wrapper.ps1
a83bde7e2a372181805be5670fb35f121bcec6cd73c5be86d8917fead9fff1dd  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:1.37.0

# 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 v1.37.0

Checksums (SHA256)

2bacf3d93fe93b1c4a86eefb1c85e9084e08ab6687b9a0c660997a09c65b4ab6  ai-memory-hooks.tar.gz
448f6cfad616e13692598dd49709ce9dec10eed0f702818ccca4a0c54a79f8c7  ai-memory-install-hooks
4140a3d7236f30419ae5d2a420d8dea2d7a5f52706bc38e24d60523ad1fa7a09  ai-memory-linux-aarch64.tar.gz
10976121629bb005cdad0fd9d9de9b25b01c7349904d2fb011e612c41e2b7115  ai-memory-linux-x86_64.tar.gz
1064e559d601bb304cf18285ddd700cd5b6105cb49009cfbde3bd8a8f58bb17a  ai-memory-macos-aarch64.tar.gz
daa1fd78a27f11f8158de289e35a5864b7f45149a53cbdb1e7df811f5692473e  ai-memory-macos-x86_64.tar.gz
62bd81c8da126fa34d764940089fe6cc6b1ee58279eaaf5671ff3e14c7b82773  ai-memory-windows-x86_64.zip
6a91c44ffa2e85d3b5a6ce26a4ccff0286b91d08d276d2bb4d47c346b036ee8b  ai-memory-wrapper.cmd
f4912fadae3f7aa0fa2f1612b40c8a915462330c217a6e7780cdd7be5ce5b068  ai-memory-wrapper.ps1
a83bde7e2a372181805be5670fb35f121bcec6cd73c5be86d8917fead9fff1dd  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:1.36.0

# 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 v1.36.0