brain-memory 0.1.0-beta.8 → 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +555 -0
- package/README.md +411 -61
- package/SECURITY.md +100 -0
- package/assets/brand/README.md +28 -0
- package/assets/brand/icon-dark.svg +19 -0
- package/assets/brand/icon-light.svg +20 -0
- package/assets/brand/linkedin_cover.png +0 -0
- package/assets/brand/linkedin_cover_light.png +0 -0
- package/assets/brand/mark-dark.svg +19 -0
- package/assets/brand/mark-light.svg +20 -0
- package/assets/brand/png/icon-dark-1024.png +0 -0
- package/assets/brand/png/icon-dark-128.png +0 -0
- package/assets/brand/png/icon-dark-256.png +0 -0
- package/assets/brand/png/icon-dark-512.png +0 -0
- package/assets/brand/png/icon-dark-64.png +0 -0
- package/assets/brand/png/icon-light-1024.png +0 -0
- package/assets/brand/png/icon-light-128.png +0 -0
- package/assets/brand/png/icon-light-256.png +0 -0
- package/assets/brand/png/icon-light-512.png +0 -0
- package/assets/brand/png/icon-light-64.png +0 -0
- package/assets/brand/png/mark-dark-1024.png +0 -0
- package/assets/brand/png/mark-light-1024.png +0 -0
- package/assets/icon.png +0 -0
- package/assets/icon.svg +19 -0
- package/bin/audit.js +93 -0
- package/bin/brain.js +132 -0
- package/bin/cloud-sync.js +150 -0
- package/bin/forget.js +163 -0
- package/bin/import.js +132 -0
- package/bin/install.js +63 -31
- package/bin/memorize.js +637 -0
- package/bin/pin.js +44 -0
- package/bin/recall.js +287 -0
- package/bin/reinforce.js +191 -0
- package/bin/restore.js +122 -0
- package/bin/session-start.js +337 -0
- package/bin/skill.js +67 -0
- package/bin/unpin.js +38 -0
- package/bin/verify.js +154 -0
- package/commands/brain/forget.md +243 -13
- package/commands/brain/import.md +125 -0
- package/commands/brain/memorize.md +95 -137
- package/commands/brain/pin.md +79 -0
- package/commands/brain/remember.md +53 -103
- package/commands/brain/skills.md +60 -0
- package/commands/brain/sleep.md +93 -6
- package/commands/brain/status.md +15 -6
- package/commands/brain/sync.md +181 -17
- package/commands/brain/verify.md +57 -0
- package/integrations/README.md +29 -0
- package/integrations/agentskills/brain-memory/SKILL.md +115 -0
- package/integrations/agentskills/brain-memory/scripts/session-start.mjs +34 -0
- package/package.json +20 -7
- package/prompts/antigravity.md +201 -0
- package/prompts/claude.md +107 -40
- package/prompts/copilot.md +203 -0
- package/prompts/kilo.md +202 -0
- package/prompts/openai.md +112 -45
- package/prompts/opencode.md +200 -0
- package/src/anomaly.js +260 -0
- package/src/audit.js +71 -0
- package/src/cloud-sync.js +672 -0
- package/src/content-lint.js +118 -0
- package/src/export-import.js +45 -7
- package/src/git-sync.js +170 -11
- package/src/harvest.js +562 -0
- package/src/index-manager.js +250 -11
- package/src/installer.js +250 -29
- package/src/pinning.js +146 -0
- package/src/provenance.js +79 -0
- package/src/quarantine.js +111 -0
- package/src/receipt.js +81 -0
- package/src/scorer.js +69 -12
- package/src/skills.js +208 -0
- package/src/tfidf.js +520 -0
- package/commands/brain/consolidate.md +0 -153
- package/commands/brain/explore.md +0 -79
- package/commands/brain/init.md +0 -149
- package/commands/brain/review.md +0 -130
- package/commands/brain/sunshine.md +0 -337
- package/prompts/gemini.md +0 -134
package/CHANGELOG.md
ADDED
|
@@ -0,0 +1,555 @@
|
|
|
1
|
+
# Changelog
|
|
2
|
+
|
|
3
|
+
All notable changes to brain-memory will be documented in this file.
|
|
4
|
+
|
|
5
|
+
The format is based on [Keep a Changelog](https://keepachangelog.com/), and this project adheres to [Semantic Versioning](https://semver.org/).
|
|
6
|
+
|
|
7
|
+
## [Unreleased]
|
|
8
|
+
|
|
9
|
+
## [0.1.0] - 2026-08-08
|
|
10
|
+
|
|
11
|
+
First stable release. Completes the memory-poisoning defense (OWASP ASI06),
|
|
12
|
+
adds a portable cross-agent distribution rail, and introduces truth-based
|
|
13
|
+
invalidation.
|
|
14
|
+
|
|
15
|
+
### Added
|
|
16
|
+
|
|
17
|
+
- **Quarantine for untrusted writes.** Low-trust origins (`tool-output`,
|
|
18
|
+
`external`) and instruction-shaped content (a write-time lint catches
|
|
19
|
+
"ignore previous instructions", pipe-to-shell, secret-exfiltration, and
|
|
20
|
+
similar) now land in a pending-verification state. The `quarantine_mode`
|
|
21
|
+
config knob controls behavior: `flag` (default — recallable but marked
|
|
22
|
+
`⊘ unverified`, never pinnable), `enforce` (excluded from recall until
|
|
23
|
+
approved), or `off`. Resolve with `brain verify list | approve | reject` —
|
|
24
|
+
approval clears the flag but keeps origin and trust weighting; it never
|
|
25
|
+
promotes a memory to user trust.
|
|
26
|
+
- **Anomaly detection.** `brain audit [--window 7d] [--apply]` scans the audit
|
|
27
|
+
log, index, and association graph for the patterns poisoning leaves — write
|
|
28
|
+
bursts per origin, co-tagged low-trust cliques, and quietly-reinforced
|
|
29
|
+
unverified memories — and can quarantine what it finds (capped per run). Runs
|
|
30
|
+
automatically as Phase 0 of `brain sleep`.
|
|
31
|
+
- **Unified, readable audit trail.** A single append-only `~/.brain/audit.log`
|
|
32
|
+
records every write, archival, verification, and restore. `brain forget` now
|
|
33
|
+
audits archivals, and the log is carried forward through restores.
|
|
34
|
+
- **Portable Agent Skill.** Brain now ships as a self-contained
|
|
35
|
+
`SKILL.md` folder (`integrations/agentskills/brain-memory/`) that runs
|
|
36
|
+
unmodified on any agentskills.io-compatible client — reaching agents without
|
|
37
|
+
a dedicated installer. Included in the npm package.
|
|
38
|
+
- **Temporal invalidation.** `brain memorize` accepts `supersedes: [ids]`,
|
|
39
|
+
stamping `superseded_by` on the replaced memory. Superseded memories are
|
|
40
|
+
strongly demoted at recall (not deleted), so the successor always wins while
|
|
41
|
+
"this was true until X" stays answerable. `brain sleep` consolidation now
|
|
42
|
+
proposes superseding for contradictory memories.
|
|
43
|
+
- **Memory inspector (Brain Cloud).** New `/api/brains/{id}/audit` endpoint and
|
|
44
|
+
memory-trust fields (origin, quarantined, vetted, superseded_by) on the tree
|
|
45
|
+
endpoint, a server-side version-restore route, and a read-only Inspector page
|
|
46
|
+
in the subscriber panel. Experimental `ui://brain/inspector` MCP App in the
|
|
47
|
+
connector (off by default).
|
|
48
|
+
|
|
49
|
+
### Changed
|
|
50
|
+
|
|
51
|
+
- **Connector conformance.** Every memory-bearing MCP result declares
|
|
52
|
+
`cacheScope: private` (a memory response is per-user and must never be cached
|
|
53
|
+
across users); the `brain.write` scope is now enforced (read-only tokens are
|
|
54
|
+
refused writes); `brain_verify` tool added; `WWW-Authenticate` emits
|
|
55
|
+
`error="invalid_token"`; non-POST `/mcp` returns 405.
|
|
56
|
+
|
|
57
|
+
### Fixed
|
|
58
|
+
|
|
59
|
+
- **Path & symlink hardening.** `validateBrainPath` now resolves symlinks and
|
|
60
|
+
refuses writes that escape `~/.brain` even through a symlinked directory, and
|
|
61
|
+
the guard is applied in every index-trusting writer (reinforce, pin, forget).
|
|
62
|
+
Export/import reject `..` traversal and skip symlinks; Git sync skips symlinks
|
|
63
|
+
and excludes `.cloud` (so cloud OAuth tokens are never committed to a remote);
|
|
64
|
+
cloud tar extraction drops symlink members via a staging directory. The
|
|
65
|
+
Git-sync push child process takes paths as argv rather than an interpolated
|
|
66
|
+
shell string.
|
|
67
|
+
|
|
68
|
+
## [0.1.0-beta.36] - 2026-08-07
|
|
69
|
+
|
|
70
|
+
### Added
|
|
71
|
+
|
|
72
|
+
- **Trust-weighted recall — origin now decides how far a memory's score can
|
|
73
|
+
reach.** beta.34 labelled every write with an origin and capped what
|
|
74
|
+
untrusted origins may claim; this release closes the read side. Recall
|
|
75
|
+
multiplies each memory's composite score by an origin trust factor (`user`
|
|
76
|
+
1.0, `agent-inferred` 0.95, `tool-output` 0.85, `external` 0.75), and
|
|
77
|
+
spreading-activation *sources* are damped by the same factor — so a clique
|
|
78
|
+
of co-tagged planted memories (which auto-link through tag overlap) cannot
|
|
79
|
+
amplify itself past something the user said directly. Trust bounds volume,
|
|
80
|
+
not relevance: a genuinely more relevant external memory can still win; it
|
|
81
|
+
just can't win on bulk. Missing origin weighs as the memorize default, so
|
|
82
|
+
pre-provenance brains rank exactly as before.
|
|
83
|
+
- **Low-trust results are visibly marked.** `brain recall` and
|
|
84
|
+
`brain session-start` return `origin` and a `low_trust` flag on every
|
|
85
|
+
result, and receipts for `tool-output`/`external` memories carry a trailing
|
|
86
|
+
warning — `◉ memory: "…" (learning, 3d ago, ⚠ external)` — so a fact
|
|
87
|
+
absorbed from a web page can never quietly pass as something you said.
|
|
88
|
+
Trusted receipts are byte-identical to the existing format.
|
|
89
|
+
- **Connector: `brain_memorize` accepts `origin`.** The remote MCP tool passes
|
|
90
|
+
a validated origin through to the engine, with tool-description guidance
|
|
91
|
+
that `user` is reserved for facts the human explicitly stated or asked to
|
|
92
|
+
remember.
|
|
93
|
+
- **`brain restore` — an undo button for the whole brain.**
|
|
94
|
+
`brain restore --list` shows restore points; `--to <point>` rolls
|
|
95
|
+
`~/.brain/` back to one. Two sources: the Git sync history
|
|
96
|
+
(`--from git`, default — one point per push) and Brain Cloud's server-side
|
|
97
|
+
pre-push snapshots (`--from cloud`, listed via the new
|
|
98
|
+
`GET /api/brains/{id}/versions` endpoint). Every restore is undoable:
|
|
99
|
+
the git path first commits the current state as a safety snapshot (unsynced
|
|
100
|
+
work included), the cloud path writes a local backup under
|
|
101
|
+
`~/.brain/.cloud/`. `audit.log` is deliberately carried *forward* through
|
|
102
|
+
restores — the append-only trail records history through a rollback, never
|
|
103
|
+
gets rolled back by one — and each restore is itself logged there.
|
|
104
|
+
|
|
105
|
+
## [0.1.0-beta.35] - 2026-08-01
|
|
106
|
+
|
|
107
|
+
### Added
|
|
108
|
+
|
|
109
|
+
- **`/brain:import` — cold-start a brain from transcripts your agents already
|
|
110
|
+
wrote.** A new brain is empty, and an empty brain is worth nothing until
|
|
111
|
+
something fills it; meanwhile every coding agent has been keeping months of
|
|
112
|
+
local history. `brain import` harvests it: session titles, user prompts,
|
|
113
|
+
projects, branches and edited files, with harness wrappers
|
|
114
|
+
(`<system-reminder>`, slash-command tags, command output), subagent sidechain
|
|
115
|
+
traffic, and bare acknowledgements filtered out. The digest is bounded on
|
|
116
|
+
three axes (sessions, prompts per session, total characters) and
|
|
117
|
+
round-robins across projects, so one busy repo cannot consume the whole
|
|
118
|
+
budget — on a real 261-session history that lifted project coverage from 5
|
|
119
|
+
to 13 within the same ~15k tokens.
|
|
120
|
+
|
|
121
|
+
The CLI harvests; the **agent distills**. Extracting meaning is a semantic
|
|
122
|
+
judgement, and making it in the CLI would mean shipping an embedding model
|
|
123
|
+
or calling an LLM — the two things Brain exists to avoid. So the harvester
|
|
124
|
+
reports facts and never infers, and distilled memories go through the
|
|
125
|
+
ordinary `brain memorize` path as `agent-inferred`: an import inherits the
|
|
126
|
+
existing provenance ceilings for free and can never pin, entrench, or
|
|
127
|
+
outrank something the user said directly.
|
|
128
|
+
|
|
129
|
+
Import is incremental — a cursor at `~/.brain/.import/state.json` records
|
|
130
|
+
which sessions have been read so re-runs offer only new ones (`--all`
|
|
131
|
+
overrides). `--mark` validates ids against the source's real sessions and
|
|
132
|
+
exits non-zero on any that match nothing: silently accepting a truncated or
|
|
133
|
+
mistyped id would report a session as retired while the cursor never matches
|
|
134
|
+
it, re-offering that session forever. Scope with `--project`,
|
|
135
|
+
`--since 30d|6m|2026-01-01`, `--limit`.
|
|
136
|
+
`brain import --sources` lists detected history stores. `brain import` only
|
|
137
|
+
ever reads and prints; no memory is written without the agent.
|
|
138
|
+
|
|
139
|
+
Claude Code is the first source adapter; the registry in `src/harvest.js`
|
|
140
|
+
takes additional agents without changes downstream.
|
|
141
|
+
|
|
142
|
+
## [0.1.0-beta.34] - 2026-07-26
|
|
143
|
+
|
|
144
|
+
### Added
|
|
145
|
+
|
|
146
|
+
- **Memory provenance — every write is now labelled by origin.** Each memory
|
|
147
|
+
carries an `origin` (`user`, `agent-inferred`, `tool-output`, `external`)
|
|
148
|
+
recording *where the content came from*, which is a different question from
|
|
149
|
+
how much the agent believes it. Origin decides what a memory may claim:
|
|
150
|
+
non-user origins are capped below the 0.7 prune-exempt salience threshold,
|
|
151
|
+
capped on confidence so they stay flagged as uncertain at recall, may not
|
|
152
|
+
raise their own base strength, and decay faster — so a fact absorbed from
|
|
153
|
+
untrusted content fades and loses to a genuine one over time. Defaults to
|
|
154
|
+
`agent-inferred` when absent (the safe direction). Downgrades are never
|
|
155
|
+
silent: `brain memorize` reports every value it lowered under
|
|
156
|
+
`provenance_clamps`. Mitigates OWASP ASI06 (memory poisoning); see
|
|
157
|
+
MemGhost, [arXiv:2607.05189](https://arxiv.org/abs/2607.05189).
|
|
158
|
+
- **Append-only provenance log** at `~/.brain/audit.log` — one JSON object per
|
|
159
|
+
write, recorded before the caller sees success, so a fact that later proves
|
|
160
|
+
to be planted can be traced to the write that introduced it even if the
|
|
161
|
+
memory was since edited, consolidated, or deleted.
|
|
162
|
+
|
|
163
|
+
### Changed
|
|
164
|
+
|
|
165
|
+
- **Breaking (CLI):** born-pinning through `brain memorize` now requires
|
|
166
|
+
`origin: "user"`. Entrenchment — `pinned` (loaded into every session) and
|
|
167
|
+
`stable` (exempt from decay) — is a capability rather than a magnitude, so a
|
|
168
|
+
request from any other origin is refused with a non-zero exit rather than
|
|
169
|
+
quietly capped. Pin deliberately afterwards with `brain pin <id>` instead.
|
|
170
|
+
Only affects callers that drive the CLI directly; `/brain:memorize` already
|
|
171
|
+
proposed rather than assumed pinning.
|
|
172
|
+
|
|
173
|
+
### Fixed
|
|
174
|
+
|
|
175
|
+
- **Cache-honest token accounting in the benchmark harness.** `normalizeUsage`
|
|
176
|
+
now folds `cache_read`/`cache_creation` input tokens back into the input
|
|
177
|
+
count — the cached prefix was being undercounted, which deflated
|
|
178
|
+
tokens-per-successful-task on the DeepSeek endpoint. Cached tokens are
|
|
179
|
+
accumulated, logged, and persisted separately so the two can be compared.
|
|
180
|
+
Also: model-aware judge dispatch, `runs_per_scenario` raised to 10, tighter
|
|
181
|
+
needle-fact rubrics on scenarios A/B/C, and three amendment rows recording
|
|
182
|
+
all of it in `PREREGISTRATION.md`.
|
|
183
|
+
|
|
184
|
+
## [0.1.0-beta.33] - 2026-07-04
|
|
185
|
+
|
|
186
|
+
_Covers everything since v0.1.0-beta.31, including the changes first shipped in the changelog-less 0.1.0-beta.32._
|
|
187
|
+
|
|
188
|
+
### Added
|
|
189
|
+
|
|
190
|
+
- **Recall receipts — memory that visibly fires.** Every memory returned by
|
|
191
|
+
`brain recall` and `brain session-start` now carries an engine-minted
|
|
192
|
+
`receipt` line (`◉ memory: "<title>" (<type>, <age>)`). Hosts end a response
|
|
193
|
+
with the receipts of the memories that actually shaped it — max 3, copied
|
|
194
|
+
verbatim, pinned facts only when decisive, none when none were used. A
|
|
195
|
+
receipt can only exist if the engine returned that memory, so receipts
|
|
196
|
+
cannot be hallucinated.
|
|
197
|
+
- **Four new agent hosts.** Native integrations under `integrations/` for
|
|
198
|
+
**OpenClaw / NVIDIA NemoClaw** (memory-slot plugin `openclaw-brain-memory`
|
|
199
|
+
replacing `memory-core`, slot-neutral hook pack, ClawHub skill, NemoClaw
|
|
200
|
+
egress-policy preset — all live-verified), **Hermes Agent** (full
|
|
201
|
+
`MemoryProvider` plugin, shipped standalone as the `hermes-brain-memory`
|
|
202
|
+
pip package per upstream policy), **GitHub Copilot CLI** (plugin with
|
|
203
|
+
`sessionStart` context injection + skills; the repo is now a Copilot plugin
|
|
204
|
+
marketplace via `.github/plugin/marketplace.json` — install with
|
|
205
|
+
`copilot plugin install brain-memory@brain`), and **Kilo** (runtime plugin
|
|
206
|
+
with chat-message injection, session tracking, and `BRAIN_AGENT` labeling).
|
|
207
|
+
- **Two new installer runtimes.** `brain --copilot` (global prompt at
|
|
208
|
+
`~/.copilot/copilot-instructions.md`, skills in the cross-tool
|
|
209
|
+
`~/.agents/skills/`) and `brain --kilo` (prompt registered in the
|
|
210
|
+
`kilo.jsonc` `instructions` array via a safe strict-JSON editor; repo-local
|
|
211
|
+
`AGENTS.md` shared with Codex/OpenCode).
|
|
212
|
+
|
|
213
|
+
### Fixed
|
|
214
|
+
|
|
215
|
+
- Kilo plugin derives the project label from `input.project` as well, so a
|
|
216
|
+
plugin host running with cwd `/` no longer records sessions as project
|
|
217
|
+
`"unknown"`.
|
|
218
|
+
- Hermes `cli.py` is a standalone diagnostics tool (`python3 cli.py
|
|
219
|
+
status|recall`) — Hermes exposes no CLI hook to user-installed memory
|
|
220
|
+
providers, so the previously documented `hermes memory recall` never
|
|
221
|
+
existed.
|
|
222
|
+
- Every `npm publish` now runs the full test suite via `prepublishOnly` —
|
|
223
|
+
the old `prerelease` script was a no-op vestige no release path invoked.
|
|
224
|
+
|
|
225
|
+
## [0.1.0-beta.31] - 2026-07-01
|
|
226
|
+
|
|
227
|
+
### Fixed
|
|
228
|
+
|
|
229
|
+
- **Recall relevance is now calibrated in absolute terms.** BM25 relevance was
|
|
230
|
+
normalized per-query by the top score, so the best match for *any* query scored
|
|
231
|
+
relevance 1.0 — a nonsense query's one weak term-match produced ten confident-looking
|
|
232
|
+
results (top composite 0.679). Three coordinated changes fix the calibration:
|
|
233
|
+
relevance is scaled by **IDF-weighted query coverage** (a memory matching one term
|
|
234
|
+
of a four-term query can no longer score 1.0); explicit-query recall applies a
|
|
235
|
+
**relevance floor** so zero-relevance memories can't pad the top-N on strength
|
|
236
|
+
alone; and spreading-activation **sources are relevance-gated** in query mode, so a
|
|
237
|
+
strong-but-irrelevant clique can't rescue itself past the floor (associates of
|
|
238
|
+
genuinely relevant memories still surface — that's the feature). Context mode
|
|
239
|
+
(`--context`, session-start) is exempt: topical padding is intended there. On a
|
|
240
|
+
real 177-memory brain the same nonsense query now returns one result with honest
|
|
241
|
+
relevance (0.213), and a 20-query retrieval probe improved from hit@1 90% /
|
|
242
|
+
MRR 0.950 to **hit@1 100% / MRR 1.000** — coverage scaling also demotes
|
|
243
|
+
partial-match distractors below full-coverage targets.
|
|
244
|
+
|
|
245
|
+
## [0.1.0-beta.30] - 2026-07-01
|
|
246
|
+
|
|
247
|
+
### Security
|
|
248
|
+
|
|
249
|
+
- **Connector purges plaintext working copies.** The hosted MCP connector already
|
|
250
|
+
kept per-user working copies in RAM only (tmpfs, never on disk); it now also
|
|
251
|
+
**wipes them proactively** — on an idle TTL, at session end, and via a dedicated
|
|
252
|
+
ephemeral working path — so a decrypted brain never lingers in memory longer than
|
|
253
|
+
an active session needs it. Local-only and Git/export use are unaffected. See
|
|
254
|
+
[SECURITY.md](SECURITY.md).
|
|
255
|
+
|
|
256
|
+
### Added
|
|
257
|
+
|
|
258
|
+
- **`memorize` tags each memory with its origin agent.** New memories record
|
|
259
|
+
`encoding_context.agent` — the detected host (`claude-code`, `gemini-cli`,
|
|
260
|
+
`codex`, `opencode`), a `BRAIN_AGENT` override, or `unknown` — in both frontmatter
|
|
261
|
+
and the index. This powers the Brain Cloud dashboard's "where your brain is used"
|
|
262
|
+
attribution. Existing memories are unaffected; the field is additive.
|
|
263
|
+
|
|
264
|
+
### Fixed
|
|
265
|
+
|
|
266
|
+
- **`forget` now actually clears a memory from recall.** `forget` sourced its
|
|
267
|
+
search index differently from `recall`, so a forgotten memory could keep surfacing
|
|
268
|
+
until the index was rebuilt out-of-band; it now sources the index via the same
|
|
269
|
+
TF-IDF path as `recall`, so forgetting takes effect immediately. Added CLI test
|
|
270
|
+
coverage for `recall` and `forget`, and de-flaked the stress-test performance gate.
|
|
271
|
+
|
|
272
|
+
### Changed
|
|
273
|
+
|
|
274
|
+
- **Website NL/EU compliance pass.** Privacy and Terms were revised for NL/EU law —
|
|
275
|
+
sub-processor list and EU data location, a cookies/browser-storage section,
|
|
276
|
+
retention periods, KMS-accurate at-rest-encryption language, the Omelas controller
|
|
277
|
+
identity, a VAT (EU OSS) clause, and the 14-day consumer right of withdrawal — plus
|
|
278
|
+
a site-wide transparency notice (not a consent CMP; the site sets no tracking
|
|
279
|
+
cookies).
|
|
280
|
+
- **Brand asset set.** Added `assets/brand/` — light + dark firing-neuron tiles and
|
|
281
|
+
marks (SVG + PNG 64–1024), transparent marks, icon-centered LinkedIn covers
|
|
282
|
+
(6336×1584, no text), and a usage README — with a dependency-free regeneration
|
|
283
|
+
script. No behavior change.
|
|
284
|
+
|
|
285
|
+
## [0.1.0-beta.29] - 2026-06-26
|
|
286
|
+
|
|
287
|
+
Version marker only — no functional changes since beta.28.
|
|
288
|
+
|
|
289
|
+
## [0.1.0-beta.28] - 2026-06-26
|
|
290
|
+
|
|
291
|
+
### Fixed
|
|
292
|
+
|
|
293
|
+
- **Recall relevance after out-of-band memory changes.** `session-start` now
|
|
294
|
+
rebuilds its search index when it has drifted out of sync with `index.json`
|
|
295
|
+
(after a `sync pull`, `sleep`/consolidate, `forget`, or a manual edit), not
|
|
296
|
+
only when the index is missing — matching `recall`'s behavior. A stale index
|
|
297
|
+
silently scored every memory's relevance as 0, so newly-synced or changed
|
|
298
|
+
memories were surfaced by strength/context only, never by relevance.
|
|
299
|
+
|
|
300
|
+
## [0.1.0-beta.27] - 2026-06-10
|
|
301
|
+
|
|
302
|
+
### Security
|
|
303
|
+
|
|
304
|
+
- **Hosted-service hardening (Brain Cloud + connector).** Memories synced to Brain
|
|
305
|
+
Cloud are now **encrypted at rest** (AES-256-GCM, per-user key, with keys managed
|
|
306
|
+
in a cloud KMS — the key never sits on the server); the connector keeps per-user
|
|
307
|
+
working copies in **RAM only** (tmpfs), never on disk. CLI sessions use
|
|
308
|
+
**rotating refresh tokens with automatic reuse detection** and real **logout**
|
|
309
|
+
(one device or all). The connector now fails closed without an identity provider,
|
|
310
|
+
runs as an unprivileged sandboxed service, safely handles untrusted brain
|
|
311
|
+
bundles, and rate-limits its endpoints; OAuth account-linking requires a
|
|
312
|
+
**verified** email. None of this changes local-only or Git/export use, which stay
|
|
313
|
+
passphrase-encrypted and never touch the cloud. See [SECURITY.md](SECURITY.md).
|
|
314
|
+
- The published package now also ships `SECURITY.md` and `CHANGELOG.md`.
|
|
315
|
+
|
|
316
|
+
## [0.1.0-beta.25] - 2026-06-07
|
|
317
|
+
|
|
318
|
+
### Changed
|
|
319
|
+
|
|
320
|
+
- **Brand refresh.** Adopted the firing-neuron "activation" glyph in place of the brain emoji across the prompts, command output, CLI help text, and the README, and refreshed the icon set (`assets/`). No behavior change.
|
|
321
|
+
|
|
322
|
+
## [0.1.0-beta.24] - 2026-06-05
|
|
323
|
+
|
|
324
|
+
### Added
|
|
325
|
+
|
|
326
|
+
- **`BRAIN_DIR` environment variable** — point your brain at any folder instead of the default `~/.brain`. Set it to a folder your existing tools already sync (Google Drive, Dropbox, iCloud Drive, OneDrive, Syncthing, or a git working copy) to get cross-device sync with no account and no extra setup. A leading `~/` is expanded. Honored everywhere the brain is resolved — recall, memorize, init, and Cloud sync.
|
|
327
|
+
|
|
328
|
+
## [0.1.0-beta.23] - 2026-06-05
|
|
329
|
+
|
|
330
|
+
### Changed
|
|
331
|
+
|
|
332
|
+
- **Command surface collapsed to a six-verb core.** The everyday loop is ambient (recall + memorize), with a small manual surface and maintenance demoted to the background. Removed/merged six commands: `consolidate` and `review` are now handled by `/brain:sleep`; `unpin` is folded into `/brain:pin` (a toggle — `--off` unpins); `sunshine` (forensic erasure) is now `/brain:forget --deep`; `explore` is dropped (browse `~/.brain/` directly or use the web dashboard); and `init` is folded into install + first `/brain:sync` (which auto-creates the structure if missing). The surviving commands are `remember`, `memorize`, `status`, `pin`, `forget`, `sync`, `skills`, and `sleep`. This aligns the plugin with the forthcoming Claude connector, which exposes the same minimal tool set.
|
|
333
|
+
|
|
334
|
+
### Fixed
|
|
335
|
+
|
|
336
|
+
- **Install detection no longer depends on a specific command.** The Codex/OpenAI skills-style detector keyed off `brain-init/SKILL.md`; it now matches any `brain-*` skill directory, so detection survives command-set changes.
|
|
337
|
+
|
|
338
|
+
## [0.1.0-beta.21] - 2026-06-03
|
|
339
|
+
|
|
340
|
+
### Changed
|
|
341
|
+
|
|
342
|
+
- **Primary domain moved to `brainmemory.ai`.** The website, dashboard, and Brain Cloud API now live at `brainmemory.ai`, `app.brainmemory.ai`, and `api.brainmemory.ai`. The plugin's default sync endpoint (`DEFAULT_API_URL`) is now `https://api.brainmemory.ai`. The old `brainmemory.work` hosts remain as redirects — `api.brainmemory.work` issues a `308` to the new API, so existing installs keep syncing without changes.
|
|
343
|
+
|
|
344
|
+
## [0.1.0-beta.20] - 2026-05-31
|
|
345
|
+
|
|
346
|
+
### Fixed
|
|
347
|
+
|
|
348
|
+
- **`memorize` and `skill add` now read piped stdin portably (fixes CI on Linux & Windows).** Both CLIs read input by opening the `/dev/stdin` *path*, which works on macOS but throws `ENXIO` on Linux CI runners and doesn't exist on Windows — so the contradiction-surfacing tests failed on every non-macOS job. Switched to reading file descriptor `0` (`fs.readFileSync(0, …)`), which reads piped stdin correctly across Linux, macOS, and Windows.
|
|
349
|
+
|
|
350
|
+
### Changed
|
|
351
|
+
|
|
352
|
+
- **Project moved to the Omelas organization.** Repository transferred to `github.com/omelas-tech/brain` (old `onurkarali/brain` URLs redirect). Updated `repository`, `bugs`, and all in-repo/website GitHub references accordingly, and set `homepage` to `https://brainmemory.work/`. No code or behavior changes — metadata only. The npm package name stays `brain-memory` (unscoped); install is unchanged.
|
|
353
|
+
|
|
354
|
+
## [0.1.0-beta.19] - 2026-05-30
|
|
355
|
+
|
|
356
|
+
### Fixed
|
|
357
|
+
|
|
358
|
+
- **Installer now removes stale command files on update**, so the beta.18 `/brain:skill` → `/brain:skills` rename actually takes effect for existing users. Previously the installer only *copied* the current command set and never deleted renamed/removed files — so an upgrader's old `skill.md` lingered next to the new `skills.md`, and on case-insensitive filesystems that leftover `skill.md` (== `SKILL.md`) kept the whole `commands/brain/` directory shadowed as a single skill, hiding every `/brain:*` command. `installForRuntime` now wipes the `brain` command dir (and stale `brain-*` skill dirs for the Codex skills layout) before writing the fresh set.
|
|
359
|
+
|
|
360
|
+
## [0.1.0-beta.18] - 2026-05-30
|
|
361
|
+
|
|
362
|
+
### Fixed
|
|
363
|
+
|
|
364
|
+
- **`/brain:*` slash commands now actually register in Claude Code** (completes the beta.17 fix). On case-insensitive filesystems (default on macOS), the `skill` command file `skill.md` collides with `SKILL.md` — Claude Code's skill loader treated the entire `commands/brain/` directory as a single skill named `brain`, shadowing all 14 commands so none appeared in autocomplete. Renamed the command `skill` → `skills` (`commands/brain/skills.md`, invoked as `/brain:skills`) to remove the collision. The CLI subcommand remains `brain skill`. Updated slash-command references in `prompts/{claude,gemini,opencode}.md`, `CLAUDE.md`, and `README.md`.
|
|
365
|
+
|
|
366
|
+
## [0.1.0-beta.17] - 2026-05-29
|
|
367
|
+
|
|
368
|
+
### Fixed
|
|
369
|
+
|
|
370
|
+
- **Claude Code now registers all `/brain:*` slash commands.** The command files (`commands/brain/*.md`) shipped without YAML frontmatter; current Claude Code requires a `description` field to register a `.md` as a slash command, so all 14 commands were silently skipped (only `/brain:skill` surfaced, via the separate skills path). Added `description` + `argument-hint` frontmatter to every command file — the field Claude Code needs, and tolerated by the Gemini / Codex / OpenCode install targets too.
|
|
371
|
+
|
|
372
|
+
## [0.1.0-beta.16] - 2026-05-28
|
|
373
|
+
|
|
374
|
+
### Changed
|
|
375
|
+
|
|
376
|
+
- **Benchmark redesigned around 2025-2026 long-term-memory SOTA.** No runtime changes to the brain CLI; this release is a milestone marker for the new evaluation methodology shipped in `benchmark/` and documented at `/docs/benchmarks/`.
|
|
377
|
+
- New N-arm matrix harness with cross-family LLM judge (Claude judges Gemini and vice-versa) — mitigates preference leakage (arxiv 2502.01534) and position bias (arxiv 2509.20293).
|
|
378
|
+
- Six pitchable scenarios (A-F) replacing the legacy 5-scenario suite: Noisy Project Folder (LongMemEval-S retrieval-under-distractors), Three Sessions / One Decision (Pinned Tier ablation), The Contradiction Test (decay + recency), Skill Progressive Disclosure (CoALA Phase-2 L0/L1/L2 ablation), Continual Coding (SWE-Bench-CL style with real `brain memorize` between tasks), Abstention (confabulation resistance).
|
|
379
|
+
- Deterministic 200-memory distractor haystack; real `brain session-start` / `brain recall` integration with Recall@k / NDCG@k scoring against oracle ID sets.
|
|
380
|
+
- Tokens-per-successful-task adopted as the headline efficiency metric (Mem0/BEAM standard); write-side cost co-reported.
|
|
381
|
+
- New OpenCode CLI agent adapter (default model `deepseek/deepseek-v4-pro`), with `--opencode-model` override for cheaper DeepSeek variants.
|
|
382
|
+
- Codex CLI dropped from the default benchmark suite (no token reporting); remains a fully supported brain install target.
|
|
383
|
+
- Legacy scenarios 1-5 stay on disk for reproducing historical reports; invoke explicitly via `--scenario scenario-N-…`.
|
|
384
|
+
|
|
385
|
+
## [0.1.0-beta.15] - 2026-05-27
|
|
386
|
+
|
|
387
|
+
### Changed
|
|
388
|
+
|
|
389
|
+
- **BREAKING: unified CLI surface** — the five separate binaries (`brain-memory`, `brain-recall`, `brain-reinforce`, `brain-cloud`, `brain-memorize`) are replaced by a single `brain` dispatcher with subcommands: `brain recall`, `brain memorize`, `brain reinforce`, `brain cloud <…>`, and `brain install|update|uninstall` (bare `brain` runs the installer). New features ship as subcommands rather than new top-level binaries. Re-run the installer/update to refresh prompts; agents now invoke `brain <command>`. (`bin/brain.js`)
|
|
390
|
+
|
|
391
|
+
### Added
|
|
392
|
+
|
|
393
|
+
- `brain --help` / `brain --version` on the unified dispatcher
|
|
394
|
+
- **CoALA Phase 0 — budget-aware working memory.** New `brain session-start` aggregator returns a single deterministic, token-budget-bounded startup payload (`memory_count`, `pinned`, `skills_index`, `context_recall`, `due_for_review`, `low_confidence_alerts`, `budget`); `~/.brain/config.json` holds the working-memory budget (created lazily with safe defaults); each new memory records a `token_estimate`. Session-start prompts/hook now make one `brain session-start` call instead of hand-rolled recall + review + low-confidence checks.
|
|
395
|
+
- **CoALA Phase 3 — procedural crystallization.** New `/brain:sleep` phase (4b) clusters repeated procedural/experience memories and proposes distilling a recurring task-solving procedure into a `SKILL.md` (user-confirmed, never silent) — learned skills, not just hand-authored ones.
|
|
396
|
+
- **CoALA Phase 4 — host skill export.** `brain skill export <name> [--target claude|gemini]` emits a native `.claude/skills/<name>/SKILL.md` (or `.gemini/...`) so distilled skills become directly executable by the host. The new state files (`config.json`, `pinned.json`, `skills-index.json`, `_skills/`) sync automatically via the existing whole-directory git/export-import engines.
|
|
397
|
+
- **Tier B §10.1 — obsolescence / context-shift detection.** `/brain:sleep` Prune phase flags memory clusters whose project/role has been absent from recent sessions (`contexts.json`) as reversible archive candidates — catching abrupt relevance loss that decay misses. Never flags pinned memories.
|
|
398
|
+
- **Tier B §10.2 — contradiction surfacing.** `brain memorize` now reports `potential_conflicts` when a new memory heavily overlaps a pinned/stable memory; `/brain:memorize` guidance has the agent adjudicate (supersede / keep-both-scoped / reject) instead of silently keeping both.
|
|
399
|
+
- **Tier B §10.4 — primacy/recency ordering.** `brain session-start` orders recalled memories so the highest-ranked land at the edges of the payload, mitigating "lost in the middle."
|
|
400
|
+
- **CoALA Phase 2 — procedural skills layer.** Skills are stored as `~/.brain/_skills/<name>/SKILL.md` and served via three-level progressive disclosure (L0 session-start advertises name + description only; L1 reads the full skill on a matching task; L2 loads resources at execution). `brain skill list|show <name>|use <name> [--failed]|add|remove <name>` and `/brain:skill`. Procedural strength rises on successful `use` and falls on `--failed`; a skill that fails too often demotes itself out of the advertised L0 index (Tier B §10.3). `~/.brain/skills-index.json` holds the L0 list; session-start injects skill summaries budget-capped by `skills_index_budget_tokens`.
|
|
401
|
+
- **CoALA Phase 1 — pinned semantic tier + stable flag.** `brain pin <id> [--scope global|project:<name>] [--priority N]` / `brain unpin <id>` and the `/brain:pin` `/brain:unpin` commands. Pinned memories are injected at every session start regardless of recall score and are decay-exempt; `stable: true` exempts a memory from decay without forcing it to always load. `pinned`/`stable` memories are skipped by sleep-cycle homeostasis and pruning. `~/.brain/pinned.json` manifest; `/brain:memorize` now proposes pinning durable conventions. Fixes the long-standing hole where a stored preference (e.g. "always use tabs") only applied if recall happened to surface it.
|
|
402
|
+
|
|
403
|
+
## [0.1.0-beta.14] - 2026-04-25
|
|
404
|
+
|
|
405
|
+
### Added
|
|
406
|
+
|
|
407
|
+
- **OpenCode support** — `brain --opencode` installs Brain Memory for the OpenCode agent (`prompts/opencode.md`), bringing the supported runtimes to Claude Code, Gemini CLI, OpenAI Codex CLI, and OpenCode.
|
|
408
|
+
|
|
409
|
+
### Fixed
|
|
410
|
+
|
|
411
|
+
- **Graceful handling of corrupt brain state files** — CLI tools now emit a clear, actionable error (naming the offending JSON and suggesting a sync/backup restore) instead of crashing when `index.json`, `associations.json`, or the search index is malformed.
|
|
412
|
+
|
|
413
|
+
### Changed
|
|
414
|
+
|
|
415
|
+
- **Install docs recommend `npm install -g` over `npx`** — `npx` discards the temporary install, so the `brain` CLI never lands in `PATH` and agents fall back to less reliable manual file operations.
|
|
416
|
+
|
|
417
|
+
## [0.1.0-beta.13] - 2026-04-05
|
|
418
|
+
|
|
419
|
+
### Added
|
|
420
|
+
|
|
421
|
+
- **`brain-memorize` CLI** — single-command memory storage that handles all plumbing (ID generation, strength/decay computation, directory creation, file writing, index updates, association edges, search index) in one call
|
|
422
|
+
- `--sync` flag for `/brain:memorize` — auto-pushes to cloud/git after storing, eliminating the separate `/brain:sync push` step
|
|
423
|
+
- `--confirm` flag for `/brain:memorize` — opt-in confirmation (was previously the default)
|
|
424
|
+
- Install check for `brain-cloud` CLI in `/brain:sync cloud push` — shows install instructions if missing
|
|
425
|
+
|
|
426
|
+
### Changed
|
|
427
|
+
|
|
428
|
+
- **`/brain:memorize` is now non-interactive by default** — stores immediately and shows results after, instead of asking "Store these memories?" before writing. The user said "memorize" — they want it stored.
|
|
429
|
+
- **`/brain:sync push` and `cloud push` are now non-interactive** — execute immediately without confirmation, matching `git push` behavior. Pull/import still confirm before overwriting.
|
|
430
|
+
- **Memorize prompt reduced ~60%** — AI classifies memories and pipes JSON to `brain-memorize` CLI instead of manually writing files. One bash call instead of 6-8 tool calls.
|
|
431
|
+
- **Session start behavior made lightweight** — recall engine skips if project has no matching memories, output condensed to single status line, removed heavy mandatory phrasing
|
|
432
|
+
|
|
433
|
+
## [0.1.0-beta.12] - 2026-04-02
|
|
434
|
+
|
|
435
|
+
### Added
|
|
436
|
+
|
|
437
|
+
- **Brain Cloud sync** — push/pull `~/.brain/` to Brain Cloud (`api.brainmemory.work`) via new cloud subcommands
|
|
438
|
+
- `brain-cloud` CLI (`bin/cloud-sync.js`) — device code auth, push, pull, status, logout
|
|
439
|
+
- `src/cloud-sync.js` — zero-dependency cloud sync engine using Node.js built-in `https` module
|
|
440
|
+
- Device code OAuth flow for CLI authentication (`/brain:sync cloud login`)
|
|
441
|
+
- Tar.gz archive-based sync protocol for efficient uploads/downloads
|
|
442
|
+
- Token management with automatic refresh
|
|
443
|
+
- Cloud subcommands in `/brain:sync`: `cloud login`, `cloud push`, `cloud pull`, `cloud status`, `cloud logout`
|
|
444
|
+
|
|
445
|
+
## [0.1.0-beta.11] - 2026-03-22
|
|
446
|
+
|
|
447
|
+
### Added
|
|
448
|
+
|
|
449
|
+
- **Ambient Session Tracking** — agent maintains a running mental log of decisions, learnings, insights, experiences, and goals as they happen throughout the session, so nothing is lost by session end
|
|
450
|
+
- **Periodic Memory Checkpoint** — every ~10 substantive interactions, the agent appends a one-liner nudge to its next response, never interrupting flow
|
|
451
|
+
- `notable_unsaved` field in session context — preserves what happened even when the user doesn't memorize, so future sessions can reference it
|
|
452
|
+
- `update` subcommand — auto-detects existing installations and refreshes commands + prompt sections (`brain-memory update`)
|
|
453
|
+
- `uninstall` subcommand — removes commands and prompt sections, preserves `.brain/` by default (`brain-memory uninstall`)
|
|
454
|
+
- `detectInstallations()`, `removePromptSection()`, `removeCommands()`, `uninstallForRuntime()` in `src/installer.js`
|
|
455
|
+
- Subcommand routing in `bin/install.js` with `parseArgs()`, `runUpdate()`, `runUninstall()`
|
|
456
|
+
- 20 new tests covering detection, removal, and round-trip install/uninstall
|
|
457
|
+
- Git-based sync — push/pull `.brain/` to any private Git remote (GitHub, GitLab, Codeberg, self-hosted) via `/brain:sync setup/push/pull`
|
|
458
|
+
- Export/Import — single-file encrypted backup for portable transfers via `/brain:sync export` and `/brain:sync import`
|
|
459
|
+
- `src/crypto.js` — standalone AES-256-GCM crypto module extracted from the old sync code
|
|
460
|
+
- `src/git-sync.js` — Git sync engine using `child_process.execFileSync`
|
|
461
|
+
- `src/export-import.js` — single-file export/import with encryption and merge mode
|
|
462
|
+
- 74 new tests: installer unit tests (`test/install.test.js`) and prompt content validation + integration tests (`test/prompts.test.js`)
|
|
463
|
+
- Deterministic recall engine with TF-IDF scoring (`bin/recall.js`, `bin/reinforce.js`)
|
|
464
|
+
- Benchmark suite with automated multi-agent evaluation
|
|
465
|
+
- Website with full documentation site at brainmemory.work
|
|
466
|
+
|
|
467
|
+
### Changed
|
|
468
|
+
|
|
469
|
+
- **Session End Behavior** — context save to `contexts.json` is now the first action (was an afterthought), saves unconditionally even for trivial sessions, and proactively detects session endings without waiting for explicit signals
|
|
470
|
+
- **`/brain:memorize` command** — restructured prompt for efficiency: batches all file writes into a single parallel call, skips reads when state is already in context, presents proposed memories for user confirmation before writing, targets 3-4 tool call rounds total (was 6+)
|
|
471
|
+
- `/brain:sync` now uses Git remotes instead of OAuth cloud providers — no more registering OAuth apps
|
|
472
|
+
- Replaced cloud sync dashboard in `/brain:status` with git sync status (remote URL, ahead/behind counts)
|
|
473
|
+
- Extracted installer logic from `bin/install.js` into `src/installer.js` for testability — `bin/install.js` is now a thin CLI wrapper
|
|
474
|
+
- Hook files (`hooks/session-start.md`, `hooks/session-end.md`) now have reference notes clarifying that behavior is delivered through prompt injection, not native hook events
|
|
475
|
+
- Removed dead `settingsFile` config from runtime definitions — it was never used
|
|
476
|
+
- Removed `hooks/` from npm package since they are internal reference docs, not user-facing files
|
|
477
|
+
- Website redesigned with clean light theme and updated icon
|
|
478
|
+
|
|
479
|
+
### Removed
|
|
480
|
+
|
|
481
|
+
- Cloud sync module (`src/sync/`) — OAuth2, Dropbox, Google Drive, and OneDrive providers
|
|
482
|
+
- OAuth token storage (`credentials.enc`) and three-way diff sync state (`sync-state.json`)
|
|
483
|
+
|
|
484
|
+
### Fixed
|
|
485
|
+
|
|
486
|
+
- Git sync repo isolation — the `git()` helper in `src/git-sync.js` only used `cwd` to scope commands; if `.brain/.sync/repo/.git` didn't exist yet (first push or failed init), git would walk up the directory tree and commit brain files to the parent project repo. Now uses `GIT_DIR` + `GIT_WORK_TREE` env vars to fully isolate the sync repo.
|
|
487
|
+
- Session lifecycle was dead code — session-start/end hook instructions were defined in `hooks/` but never installed or referenced anywhere. The prompt injected into CLAUDE.md/GEMINI.md/AGENTS.md only had a weak one-liner about memorization. Now all three prompt files contain full "Session Start Behavior" and "Session End Behavior" sections with automatic brain context loading, review queue alerts, and end-of-session memorization suggestions.
|
|
488
|
+
- `release:beta` npm script now automatically updates the `latest` dist-tag after publishing
|
|
489
|
+
- Accurate model names in benchmark results
|
|
490
|
+
|
|
491
|
+
## [0.1.0-beta.4] - 2026-03-03
|
|
492
|
+
|
|
493
|
+
### Added
|
|
494
|
+
|
|
495
|
+
- `/brain:sync` command — cloud sync for pushing/pulling memories to Dropbox, Google Drive, or OneDrive
|
|
496
|
+
- Cloud sync module (`src/sync/`) with OAuth2 PKCE + Device Code Flow, AES-256-GCM encryption, three-way diff algorithm, and provider-specific implementations (Dropbox API v2, Google Drive API v3, Microsoft Graph API)
|
|
497
|
+
- Zero new dependencies — uses Node.js 18+ built-in `fetch`, `crypto`, `http`
|
|
498
|
+
|
|
499
|
+
### Changed
|
|
500
|
+
|
|
501
|
+
- Removed all v1 migration code and references — no v1 users exist
|
|
502
|
+
- Updated documentation to reflect 11 slash commands and cloud sync
|
|
503
|
+
|
|
504
|
+
## [0.1.0-beta.3] - 2026-02-28
|
|
505
|
+
|
|
506
|
+
### Added
|
|
507
|
+
|
|
508
|
+
- `/brain:sunshine` command — deep forensic memory erasure that traces and removes all references across the `.brain/` tree (related arrays, content mentions, association edges, context sessions, review queue, archive index, crystallization comments)
|
|
509
|
+
- `removeEdgesForMemory()` utility in index-manager for removing all association edges involving a memory
|
|
510
|
+
- `removeFromReviewQueue()` utility in index-manager for removing a memory from the review queue
|
|
511
|
+
- `_erased.json` audit log schema for tracking erasures without preserving erased content
|
|
512
|
+
- 16 new tests for erasure utilities
|
|
513
|
+
- npm release scripts (`release:beta`, `release:patch`, `release:minor`, `release:major`)
|
|
514
|
+
|
|
515
|
+
### Fixed
|
|
516
|
+
|
|
517
|
+
- Windows CI compatibility: explicit test file listing, bash shell for glob expansion, `path.join` in tests
|
|
518
|
+
- Relaxed stress test thresholds for CI runners (5x multiplier)
|
|
519
|
+
|
|
520
|
+
## [0.1.0-beta.1] - 2026-02-22
|
|
521
|
+
|
|
522
|
+
### Added
|
|
523
|
+
|
|
524
|
+
- 375x faster `rankMemories` via batch spreading activation
|
|
525
|
+
|
|
526
|
+
### Fixed
|
|
527
|
+
|
|
528
|
+
- Clamped recency bonus and optimized spreading activation loop
|
|
529
|
+
- Normalized `package.json` bin and repository fields for npm
|
|
530
|
+
|
|
531
|
+
## [0.1.0] - 2026-02-15
|
|
532
|
+
|
|
533
|
+
Initial beta release.
|
|
534
|
+
|
|
535
|
+
### Added
|
|
536
|
+
|
|
537
|
+
- 9 slash commands: `init`, `memorize`, `remember`, `review`, `explore`, `consolidate`, `forget`, `sleep`, `status`
|
|
538
|
+
- Neuroscience-inspired scoring with Ebbinghaus exponential decay
|
|
539
|
+
- Associative memory network with spreading activation (BFS, 2-hop, 50% decay per hop)
|
|
540
|
+
- Hebbian learning for co-retrieved memories
|
|
541
|
+
- Context-dependent recall scoring (project, topic Jaccard, task type matching)
|
|
542
|
+
- Spaced reinforcement with logarithmic spacing multiplier and diminishing returns
|
|
543
|
+
- 3 cognitive memory types: episodic, semantic, procedural (each with distinct decay behavior)
|
|
544
|
+
- Salience-based protection preventing auto-pruning of important memories
|
|
545
|
+
- Confidence tracking with contradiction detection
|
|
546
|
+
- 9-phase sleep cycle: replay, synaptic homeostasis, knowledge propagation, semantic crystallization, reorganize, consolidate, prune, REM dreaming, expertise detection
|
|
547
|
+
- SM-2 spaced repetition review scheduler
|
|
548
|
+
- Memory consolidation with salience anchoring
|
|
549
|
+
- Archive system with recoverable memories
|
|
550
|
+
- Multi-factor recall scoring formula (relevance, strength, recency, spreading, context, salience)
|
|
551
|
+
- Multi-runtime installer: Claude Code, Gemini CLI, OpenAI Codex CLI
|
|
552
|
+
- Interactive and non-interactive installation modes
|
|
553
|
+
- Session lifecycle hook definitions (session-start, session-end)
|
|
554
|
+
- 114 tests covering scorer, index-manager, and end-to-end lifecycle
|
|
555
|
+
- Zero external dependencies
|