brain-memory 0.1.0-beta.3 → 0.1.0-beta.5
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/README.md +59 -47
- package/bin/install.js +18 -235
- package/commands/brain/init.md +0 -8
- package/commands/brain/remember.md +2 -2
- package/commands/brain/sleep.md +0 -19
- package/commands/brain/status.md +12 -1
- package/commands/brain/sync.md +220 -0
- package/package.json +12 -4
- package/prompts/claude.md +55 -2
- package/prompts/gemini.md +55 -2
- package/prompts/openai.md +55 -2
- package/src/installer.js +231 -0
- package/src/sync/crypto-utils.js +217 -0
- package/src/sync/oauth.js +430 -0
- package/src/sync/provider.js +144 -0
- package/src/sync/providers/dropbox.js +288 -0
- package/src/sync/providers/google-drive.js +496 -0
- package/src/sync/providers/onedrive.js +308 -0
- package/src/sync/sync-engine.js +774 -0
- package/hooks/session-end.md +0 -48
- package/hooks/session-start.md +0 -48
package/README.md
CHANGED
|
@@ -95,6 +95,38 @@ Then append the contents of the corresponding prompt file to your agent's instru
|
|
|
95
95
|
| `/brain:sunshine [target]` | Deep forensic erasure — trace and remove all references |
|
|
96
96
|
| `/brain:sleep [scope]` | Full maintenance cycle — 9 neuroscience-inspired phases |
|
|
97
97
|
| `/brain:status` | Dashboard with brain health metrics and recommendations |
|
|
98
|
+
| `/brain:sync [subcommand]` | Cloud sync — push/pull memories to Dropbox, Google Drive, or OneDrive |
|
|
99
|
+
|
|
100
|
+
## Session Lifecycle
|
|
101
|
+
|
|
102
|
+
Brain Memory works automatically in the background — no commands needed for basic context awareness.
|
|
103
|
+
|
|
104
|
+
### Session Start
|
|
105
|
+
|
|
106
|
+
When a session begins and `.brain/` exists, the agent automatically:
|
|
107
|
+
|
|
108
|
+
1. Reads the brain index and loads the top 3-5 memories relevant to the current project
|
|
109
|
+
2. Checks the review queue for memories due for spaced repetition
|
|
110
|
+
3. Outputs a brief status line:
|
|
111
|
+
|
|
112
|
+
```
|
|
113
|
+
🧠 Brain active — 42 memories loaded (8 in current project context)
|
|
114
|
+
📋 3 memories due for review — run /brain:review
|
|
115
|
+
```
|
|
116
|
+
|
|
117
|
+
The agent silently internalizes relevant memories and references them naturally during the session — no information dump.
|
|
118
|
+
|
|
119
|
+
### Session End
|
|
120
|
+
|
|
121
|
+
When a session ends, the agent evaluates whether significant decisions, learnings, insights, or experiences occurred. If so, it suggests:
|
|
122
|
+
|
|
123
|
+
```
|
|
124
|
+
💡 This session contained notable decisions and learnings.
|
|
125
|
+
Would you like to store them as brain memories?
|
|
126
|
+
Run /brain:memorize to capture them before this context is lost.
|
|
127
|
+
```
|
|
128
|
+
|
|
129
|
+
The agent never auto-memorizes without user consent. Session context is always saved to `.brain/contexts.json` for context-dependent recall.
|
|
98
130
|
|
|
99
131
|
## How It Works
|
|
100
132
|
|
|
@@ -117,7 +149,7 @@ Create → Store → Decay → Recall → Reinforce → Review → Sleep → Arc
|
|
|
117
149
|
|
|
118
150
|
### Neuroscience Foundations
|
|
119
151
|
|
|
120
|
-
Brain Memory
|
|
152
|
+
Brain Memory is grounded in peer-reviewed neuroscience research. Here's how each mechanism maps to the brain:
|
|
121
153
|
|
|
122
154
|
| Brain Mechanism | Implementation |
|
|
123
155
|
|-----------------|---------------|
|
|
@@ -226,8 +258,6 @@ score = 0.38 * relevance
|
|
|
226
258
|
- **context_match** (0.14) — How similar the encoding context is to the current session
|
|
227
259
|
- **salience** (0.08) — Emotional/motivational significance
|
|
228
260
|
|
|
229
|
-
The formula gracefully degrades for v1 memories missing newer fields — weights are renormalized across available terms.
|
|
230
|
-
|
|
231
261
|
The agent then decides the response strategy:
|
|
232
262
|
- **Single strong match** (top score > 0.7) → Return the full memory
|
|
233
263
|
- **Multiple related** (2-5 candidates > 0.4) → Synthesize a consolidated response
|
|
@@ -261,7 +291,7 @@ Memories are connected via weighted edges in `.brain/associations.json`:
|
|
|
261
291
|
|
|
262
292
|
### Spaced Reinforcement
|
|
263
293
|
|
|
264
|
-
|
|
294
|
+
Spaced reinforcement rewards optimal recall timing:
|
|
265
295
|
|
|
266
296
|
```
|
|
267
297
|
spacingMultiplier = min(3.0, 1.0 + log2(1 + daysSinceLastAccess))
|
|
@@ -328,15 +358,24 @@ Each expertise area gets an `_expertise.md` profile documenting what you know we
|
|
|
328
358
|
|
|
329
359
|
Failed recalls reset the interval to 1 day. Successful recalls extend the interval by the ease factor. This ensures you spend time on memories that need reinforcement, not ones you already know well.
|
|
330
360
|
|
|
331
|
-
###
|
|
361
|
+
### Cloud Sync
|
|
332
362
|
|
|
333
|
-
|
|
334
|
-
- Creates `associations.json` from existing `related` fields
|
|
335
|
-
- Backfills `recall_history` from `access_count`
|
|
336
|
-
- Sets sensible defaults for new fields (`cognitive_type: semantic`, `salience: 0.5`, `confidence: 0.8`)
|
|
337
|
-
- Bumps `index.json` version to 2
|
|
363
|
+
`/brain:sync` lets you push and pull your `.brain/` memories to a cloud provider for cross-device access. Supports **Dropbox**, **Google Drive**, and **OneDrive** with zero npm dependencies (uses Node.js 18+ built-in `fetch`).
|
|
338
364
|
|
|
339
|
-
|
|
365
|
+
**Key features:**
|
|
366
|
+
- **Manual push/pull** — No background watchers, no auto-sync. You control when data moves.
|
|
367
|
+
- **Three-way diff** — Compares local state, remote state, and last-known sync state to detect changes and conflicts.
|
|
368
|
+
- **Conflict resolution** — When the same file is modified locally and remotely, sync detects the conflict and lets you choose: keep local, keep remote, or keep both.
|
|
369
|
+
- **Optional encryption** — AES-256-GCM encryption with a user-provided passphrase. When enabled, all files are encrypted before upload and decrypted after download. The cloud provider only ever sees opaque bytes.
|
|
370
|
+
- **OAuth2 authentication** — PKCE authorization code flow with a Device Code Flow fallback for headless/SSH environments. Users register their own OAuth app with the provider and supply their client ID.
|
|
371
|
+
|
|
372
|
+
**Setup:**
|
|
373
|
+
1. Register an OAuth app with your chosen provider (Dropbox / Google Drive / OneDrive)
|
|
374
|
+
2. Run `/brain:sync login <provider>` and provide your client ID
|
|
375
|
+
3. Authorize in the browser (or enter the device code for headless environments)
|
|
376
|
+
4. Use `/brain:sync push` and `/brain:sync pull` to keep memories in sync
|
|
377
|
+
|
|
378
|
+
Sync state is stored locally in `.brain/.sync/` and is never uploaded to the cloud.
|
|
340
379
|
|
|
341
380
|
## File Structure
|
|
342
381
|
|
|
@@ -368,9 +407,13 @@ No data is lost. All new scoring gracefully falls back when newer fields are abs
|
|
|
368
407
|
│ └── events/
|
|
369
408
|
├── _consolidated/ # Merged memories from consolidation
|
|
370
409
|
│ └── _meta.json
|
|
371
|
-
|
|
372
|
-
|
|
373
|
-
|
|
410
|
+
├── _archived/ # Decayed memories (recoverable + searchable)
|
|
411
|
+
│ ├── _meta.json
|
|
412
|
+
│ └── index.json # Searchable archive index
|
|
413
|
+
└── .sync/ # Cloud sync state (never synced, local only)
|
|
414
|
+
├── config.json # Provider, client ID, encryption flag
|
|
415
|
+
├── credentials.enc # AES-256-GCM encrypted OAuth tokens
|
|
416
|
+
└── sync-state.json # Per-file revisions, cursor, conflicts
|
|
374
417
|
```
|
|
375
418
|
|
|
376
419
|
Subdirectories are created **on demand** — the agent decides placement depth based on how specific the memory is. A generic career thought lands in `professional/`, but a specific deployment incident goes to `professional/companies/acme/projects/alpha/`.
|
|
@@ -413,40 +456,9 @@ Brain configuration lives in `.brain/index.json` under the `config` key:
|
|
|
413
456
|
| `association_config.spreading_activation_depth` | 2 | Maximum hops for spreading activation traversal |
|
|
414
457
|
| `association_config.spreading_activation_decay` | 0.5 | Decay factor per hop during spreading activation |
|
|
415
458
|
|
|
416
|
-
##
|
|
459
|
+
## Contributing
|
|
417
460
|
|
|
418
|
-
|
|
419
|
-
brain/
|
|
420
|
-
├── bin/
|
|
421
|
-
│ └── install.js # Interactive installer (npx brain-memory)
|
|
422
|
-
├── commands/
|
|
423
|
-
│ └── brain/ # Slash command definitions
|
|
424
|
-
│ ├── init.md
|
|
425
|
-
│ ├── memorize.md
|
|
426
|
-
│ ├── remember.md
|
|
427
|
-
│ ├── review.md
|
|
428
|
-
│ ├── explore.md
|
|
429
|
-
│ ├── consolidate.md
|
|
430
|
-
│ ├── forget.md
|
|
431
|
-
│ ├── sunshine.md
|
|
432
|
-
│ ├── sleep.md
|
|
433
|
-
│ └── status.md
|
|
434
|
-
├── prompts/
|
|
435
|
-
│ ├── claude.md # CLAUDE.md content (injected by installer)
|
|
436
|
-
│ ├── gemini.md # GEMINI.md content (injected by installer)
|
|
437
|
-
│ └── openai.md # AGENTS.md content (injected by installer)
|
|
438
|
-
├── hooks/
|
|
439
|
-
│ ├── session-start.md # Ambient memory loading + review notifications
|
|
440
|
-
│ └── session-end.md # Auto-memorize suggestion + context capture
|
|
441
|
-
├── templates/
|
|
442
|
-
│ └── default-categories.json # Default brain category definitions
|
|
443
|
-
├── src/
|
|
444
|
-
│ ├── scorer.js # Decay, spreading activation, context matching, spaced reinforcement
|
|
445
|
-
│ └── index-manager.js # Index, associations, contexts, review queue, archive CRUD
|
|
446
|
-
├── CLAUDE.md # Development guide for this repo
|
|
447
|
-
├── package.json
|
|
448
|
-
└── README.md
|
|
449
|
-
```
|
|
461
|
+
Contributions are welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup, project structure, and how to submit changes.
|
|
450
462
|
|
|
451
463
|
## Inspired By
|
|
452
464
|
|
package/bin/install.js
CHANGED
|
@@ -1,46 +1,11 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
|
|
3
|
-
const fs = require('fs');
|
|
4
|
-
const path = require('path');
|
|
5
3
|
const readline = require('readline');
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
name: 'Claude Code',
|
|
12
|
-
globalDir: path.join(require('os').homedir(), '.claude'),
|
|
13
|
-
localDir: '.claude',
|
|
14
|
-
commandsSubdir: 'commands',
|
|
15
|
-
promptFile: 'CLAUDE.md',
|
|
16
|
-
promptSource: 'claude.md',
|
|
17
|
-
settingsFile: 'settings.json',
|
|
18
|
-
commandStyle: 'flat',
|
|
19
|
-
},
|
|
20
|
-
gemini: {
|
|
21
|
-
name: 'Gemini CLI',
|
|
22
|
-
globalDir: path.join(require('os').homedir(), '.gemini'),
|
|
23
|
-
localDir: '.gemini',
|
|
24
|
-
commandsSubdir: 'commands',
|
|
25
|
-
promptFile: 'GEMINI.md',
|
|
26
|
-
promptSource: 'gemini.md',
|
|
27
|
-
settingsFile: null,
|
|
28
|
-
commandStyle: 'flat',
|
|
29
|
-
},
|
|
30
|
-
openai: {
|
|
31
|
-
name: 'OpenAI Codex CLI',
|
|
32
|
-
globalDir: path.join(require('os').homedir(), '.codex'),
|
|
33
|
-
localDir: '.codex',
|
|
34
|
-
commandsSubdir: 'skills',
|
|
35
|
-
promptFile: 'AGENTS.md',
|
|
36
|
-
promptSource: 'openai.md',
|
|
37
|
-
settingsFile: null,
|
|
38
|
-
commandStyle: 'skills',
|
|
39
|
-
},
|
|
40
|
-
};
|
|
41
|
-
|
|
42
|
-
const BRAIN_MARKER_START = '<!-- BRAIN-MEMORY-START -->';
|
|
43
|
-
const BRAIN_MARKER_END = '<!-- BRAIN-MEMORY-END -->';
|
|
4
|
+
const {
|
|
5
|
+
RUNTIMES,
|
|
6
|
+
installForRuntime,
|
|
7
|
+
initializeBrain,
|
|
8
|
+
} = require('../src/installer');
|
|
44
9
|
|
|
45
10
|
function createRL() {
|
|
46
11
|
return readline.createInterface({
|
|
@@ -53,85 +18,6 @@ function ask(rl, question) {
|
|
|
53
18
|
return new Promise((resolve) => rl.question(question, resolve));
|
|
54
19
|
}
|
|
55
20
|
|
|
56
|
-
function copyDir(src, dest) {
|
|
57
|
-
fs.mkdirSync(dest, { recursive: true });
|
|
58
|
-
const entries = fs.readdirSync(src, { withFileTypes: true });
|
|
59
|
-
for (const entry of entries) {
|
|
60
|
-
const srcPath = path.join(src, entry.name);
|
|
61
|
-
const destPath = path.join(dest, entry.name);
|
|
62
|
-
if (entry.isDirectory()) {
|
|
63
|
-
copyDir(srcPath, destPath);
|
|
64
|
-
} else {
|
|
65
|
-
fs.copyFileSync(srcPath, destPath);
|
|
66
|
-
}
|
|
67
|
-
}
|
|
68
|
-
}
|
|
69
|
-
|
|
70
|
-
function installSkills(commandsSrc, skillsDest) {
|
|
71
|
-
const entries = fs.readdirSync(commandsSrc).filter((f) => f.endsWith('.md'));
|
|
72
|
-
for (const file of entries) {
|
|
73
|
-
const name = file.replace('.md', '');
|
|
74
|
-
const skillDir = path.join(skillsDest, `brain-${name}`);
|
|
75
|
-
fs.mkdirSync(skillDir, { recursive: true });
|
|
76
|
-
fs.copyFileSync(
|
|
77
|
-
path.join(commandsSrc, file),
|
|
78
|
-
path.join(skillDir, 'SKILL.md')
|
|
79
|
-
);
|
|
80
|
-
}
|
|
81
|
-
}
|
|
82
|
-
|
|
83
|
-
function injectPrompt(targetDir, promptFile, promptSource) {
|
|
84
|
-
const promptContent = fs.readFileSync(
|
|
85
|
-
path.join(PACKAGE_ROOT, 'prompts', promptSource),
|
|
86
|
-
'utf-8'
|
|
87
|
-
);
|
|
88
|
-
const targetPath = path.join(targetDir, promptFile);
|
|
89
|
-
|
|
90
|
-
const wrappedContent = `\n${BRAIN_MARKER_START}\n${promptContent}\n${BRAIN_MARKER_END}\n`;
|
|
91
|
-
|
|
92
|
-
if (fs.existsSync(targetPath)) {
|
|
93
|
-
let existing = fs.readFileSync(targetPath, 'utf-8');
|
|
94
|
-
// Remove old brain section if present
|
|
95
|
-
const startIdx = existing.indexOf(BRAIN_MARKER_START);
|
|
96
|
-
const endIdx = existing.indexOf(BRAIN_MARKER_END);
|
|
97
|
-
if (startIdx !== -1 && endIdx !== -1) {
|
|
98
|
-
existing =
|
|
99
|
-
existing.substring(0, startIdx) +
|
|
100
|
-
existing.substring(endIdx + BRAIN_MARKER_END.length);
|
|
101
|
-
}
|
|
102
|
-
fs.writeFileSync(targetPath, existing.trimEnd() + '\n' + wrappedContent);
|
|
103
|
-
} else {
|
|
104
|
-
fs.writeFileSync(targetPath, wrappedContent.trim() + '\n');
|
|
105
|
-
}
|
|
106
|
-
}
|
|
107
|
-
|
|
108
|
-
function installForRuntime(runtime, scope) {
|
|
109
|
-
const config = RUNTIMES[runtime];
|
|
110
|
-
const targetDir = scope === 'global' ? config.globalDir : config.localDir;
|
|
111
|
-
const commandsSrc = path.join(PACKAGE_ROOT, 'commands', 'brain');
|
|
112
|
-
|
|
113
|
-
console.log(`\n Installing for ${config.name} (${scope})...`);
|
|
114
|
-
|
|
115
|
-
if (config.commandStyle === 'skills') {
|
|
116
|
-
// Codex: each command becomes a skill directory with SKILL.md
|
|
117
|
-
const skillsDest = path.join(targetDir, config.commandsSubdir);
|
|
118
|
-
console.log(` Installing skills to ${skillsDest}`);
|
|
119
|
-
installSkills(commandsSrc, skillsDest);
|
|
120
|
-
} else {
|
|
121
|
-
// Claude / Gemini: flat copy into commands/brain/
|
|
122
|
-
const commandsDest = path.join(targetDir, config.commandsSubdir, 'brain');
|
|
123
|
-
console.log(` Copying commands to ${commandsDest}`);
|
|
124
|
-
copyDir(commandsSrc, commandsDest);
|
|
125
|
-
}
|
|
126
|
-
|
|
127
|
-
// Inject prompt into CLAUDE.md / GEMINI.md / AGENTS.md
|
|
128
|
-
const promptTarget = scope === 'global' ? config.globalDir : '.';
|
|
129
|
-
console.log(` Injecting brain context into ${path.join(promptTarget, config.promptFile)}`);
|
|
130
|
-
injectPrompt(promptTarget, config.promptFile, config.promptSource);
|
|
131
|
-
|
|
132
|
-
console.log(` Done!`);
|
|
133
|
-
}
|
|
134
|
-
|
|
135
21
|
async function main() {
|
|
136
22
|
console.log(`
|
|
137
23
|
╔══════════════════════════════════════════════════════╗
|
|
@@ -210,12 +96,23 @@ async function main() {
|
|
|
210
96
|
// Perform installation
|
|
211
97
|
console.log('\n Installing...');
|
|
212
98
|
for (const runtime of runtimes) {
|
|
99
|
+
const config = RUNTIMES[runtime];
|
|
100
|
+
console.log(`\n Installing for ${config.name} (${scope})...`);
|
|
213
101
|
installForRuntime(runtime, scope);
|
|
102
|
+
console.log(` Done!`);
|
|
214
103
|
}
|
|
215
104
|
|
|
216
105
|
// Initialize .brain if requested
|
|
217
106
|
if (initBrain.trim().toLowerCase() !== 'n') {
|
|
218
|
-
initializeBrain();
|
|
107
|
+
const result = initializeBrain();
|
|
108
|
+
if (result.alreadyExists) {
|
|
109
|
+
console.log('\n .brain/ already exists, skipping initialization.');
|
|
110
|
+
} else {
|
|
111
|
+
console.log('\n .brain/ initialized successfully.');
|
|
112
|
+
console.log('');
|
|
113
|
+
console.log(' ☁️ Cloud sync is available! Use /brain:sync login to connect');
|
|
114
|
+
console.log(' Dropbox, Google Drive, or OneDrive for cross-device access.');
|
|
115
|
+
}
|
|
219
116
|
}
|
|
220
117
|
|
|
221
118
|
console.log(`
|
|
@@ -232,6 +129,7 @@ async function main() {
|
|
|
232
129
|
/brain:sunshine Deep forensic memory erasure
|
|
233
130
|
/brain:sleep Full maintenance cycle
|
|
234
131
|
/brain:status Brain overview dashboard
|
|
132
|
+
/brain:sync Cloud sync (Dropbox/Google Drive/OneDrive)
|
|
235
133
|
|
|
236
134
|
Get started by running /brain:init in your agent session.
|
|
237
135
|
`);
|
|
@@ -240,121 +138,6 @@ async function main() {
|
|
|
240
138
|
}
|
|
241
139
|
}
|
|
242
140
|
|
|
243
|
-
function initializeBrain() {
|
|
244
|
-
const brainDir = path.join(process.cwd(), '.brain');
|
|
245
|
-
|
|
246
|
-
if (fs.existsSync(brainDir)) {
|
|
247
|
-
console.log('\n .brain/ already exists, skipping initialization.');
|
|
248
|
-
return;
|
|
249
|
-
}
|
|
250
|
-
|
|
251
|
-
console.log('\n Creating .brain/ directory structure...');
|
|
252
|
-
|
|
253
|
-
const now = new Date().toISOString();
|
|
254
|
-
|
|
255
|
-
// Create directories
|
|
256
|
-
const categories = ['professional', 'personal', 'social', 'family', '_consolidated', '_archived'];
|
|
257
|
-
for (const cat of categories) {
|
|
258
|
-
fs.mkdirSync(path.join(brainDir, cat), { recursive: true });
|
|
259
|
-
}
|
|
260
|
-
|
|
261
|
-
// Create index.json
|
|
262
|
-
const index = {
|
|
263
|
-
version: 2,
|
|
264
|
-
created: now,
|
|
265
|
-
last_updated: now,
|
|
266
|
-
memory_count: 0,
|
|
267
|
-
memories: {},
|
|
268
|
-
config: {
|
|
269
|
-
max_depth: 6,
|
|
270
|
-
consolidation_threshold: 0.3,
|
|
271
|
-
decay_check_interval_days: 7,
|
|
272
|
-
strength_boost_on_recall: 0.05,
|
|
273
|
-
auto_consolidate: true,
|
|
274
|
-
propagation_window_days: 7,
|
|
275
|
-
association_config: {
|
|
276
|
-
co_retrieval_boost: 0.10,
|
|
277
|
-
link_decay_rate: 0.998,
|
|
278
|
-
link_prune_threshold: 0.05,
|
|
279
|
-
spreading_activation_depth: 2,
|
|
280
|
-
spreading_activation_decay: 0.5,
|
|
281
|
-
},
|
|
282
|
-
},
|
|
283
|
-
};
|
|
284
|
-
fs.writeFileSync(
|
|
285
|
-
path.join(brainDir, 'index.json'),
|
|
286
|
-
JSON.stringify(index, null, 2) + '\n'
|
|
287
|
-
);
|
|
288
|
-
|
|
289
|
-
// Create associations.json
|
|
290
|
-
fs.writeFileSync(
|
|
291
|
-
path.join(brainDir, 'associations.json'),
|
|
292
|
-
JSON.stringify({ version: 1, edges: {} }, null, 2) + '\n'
|
|
293
|
-
);
|
|
294
|
-
|
|
295
|
-
// Create contexts.json
|
|
296
|
-
fs.writeFileSync(
|
|
297
|
-
path.join(brainDir, 'contexts.json'),
|
|
298
|
-
JSON.stringify({ version: 1, sessions: [] }, null, 2) + '\n'
|
|
299
|
-
);
|
|
300
|
-
|
|
301
|
-
// Create review-queue.json
|
|
302
|
-
fs.writeFileSync(
|
|
303
|
-
path.join(brainDir, 'review-queue.json'),
|
|
304
|
-
JSON.stringify({ version: 1, items: [] }, null, 2) + '\n'
|
|
305
|
-
);
|
|
306
|
-
|
|
307
|
-
// Create _archived/index.json
|
|
308
|
-
fs.writeFileSync(
|
|
309
|
-
path.join(brainDir, '_archived', 'index.json'),
|
|
310
|
-
JSON.stringify({ version: 1, archived_count: 0, memories: {} }, null, 2) + '\n'
|
|
311
|
-
);
|
|
312
|
-
|
|
313
|
-
// Load category descriptions from template
|
|
314
|
-
const templatePath = path.join(PACKAGE_ROOT, 'templates', 'default-categories.json');
|
|
315
|
-
let template = { top_categories: [] };
|
|
316
|
-
if (fs.existsSync(templatePath)) {
|
|
317
|
-
template = JSON.parse(fs.readFileSync(templatePath, 'utf-8'));
|
|
318
|
-
}
|
|
319
|
-
|
|
320
|
-
// Create _meta.json for each category
|
|
321
|
-
const mainCategories = ['professional', 'personal', 'social', 'family'];
|
|
322
|
-
for (const cat of mainCategories) {
|
|
323
|
-
const templateCat = template.top_categories.find((c) => c.name === cat) || {};
|
|
324
|
-
const meta = {
|
|
325
|
-
category: cat,
|
|
326
|
-
description: templateCat.description || cat,
|
|
327
|
-
created: now,
|
|
328
|
-
memory_count: 0,
|
|
329
|
-
subcategories: [],
|
|
330
|
-
};
|
|
331
|
-
fs.writeFileSync(
|
|
332
|
-
path.join(brainDir, cat, '_meta.json'),
|
|
333
|
-
JSON.stringify(meta, null, 2) + '\n'
|
|
334
|
-
);
|
|
335
|
-
}
|
|
336
|
-
|
|
337
|
-
// Create _meta.json for special directories
|
|
338
|
-
for (const special of ['_consolidated', '_archived']) {
|
|
339
|
-
const meta = {
|
|
340
|
-
category: special,
|
|
341
|
-
description:
|
|
342
|
-
special === '_consolidated'
|
|
343
|
-
? 'Merged memories from consolidation operations'
|
|
344
|
-
: 'Archived memories preserved for recovery',
|
|
345
|
-
created: now,
|
|
346
|
-
memory_count: 0,
|
|
347
|
-
subcategories: [],
|
|
348
|
-
};
|
|
349
|
-
fs.writeFileSync(
|
|
350
|
-
path.join(brainDir, special, '_meta.json'),
|
|
351
|
-
JSON.stringify(meta, null, 2) + '\n'
|
|
352
|
-
);
|
|
353
|
-
}
|
|
354
|
-
|
|
355
|
-
console.log(' .brain/ initialized successfully.');
|
|
356
|
-
}
|
|
357
|
-
|
|
358
141
|
main().catch((err) => {
|
|
359
142
|
console.error('Installation failed:', err.message);
|
|
360
143
|
process.exit(1);
|
package/commands/brain/init.md
CHANGED
|
@@ -147,11 +147,3 @@ Print a summary of what was created, including the full tree structure. Inform t
|
|
|
147
147
|
- `/brain:status` — View brain overview
|
|
148
148
|
- `/brain:review` — Spaced repetition review of memories due for reinforcement
|
|
149
149
|
|
|
150
|
-
### Migration Note
|
|
151
|
-
|
|
152
|
-
If upgrading an existing v1 brain, the first `/brain:sleep` after upgrade will run a **Migration phase** (Phase 0) that:
|
|
153
|
-
- Creates `associations.json` from existing `related` fields
|
|
154
|
-
- Creates `contexts.json`, `review-queue.json`, and `_archived/index.json`
|
|
155
|
-
- Backfills `recall_history` from `access_count` (using `last_accessed` as sole entry)
|
|
156
|
-
- Sets default values for new frontmatter fields (`cognitive_type: semantic`, `salience: 0.5`, `confidence: 0.8`)
|
|
157
|
-
- Bumps `index.json` version to 2
|
|
@@ -67,7 +67,7 @@ effective_score = 0.38 * relevance
|
|
|
67
67
|
+ 0.08 * salience_bonus
|
|
68
68
|
```
|
|
69
69
|
|
|
70
|
-
**Note:** If a memory lacks
|
|
70
|
+
**Note:** If a memory lacks some fields (spreading_bonus, context_match, salience), the formula renormalizes weights across the available terms.
|
|
71
71
|
|
|
72
72
|
### 5. Decide Response Strategy
|
|
73
73
|
|
|
@@ -110,7 +110,7 @@ diminishingFactor = 1.0 / (1.0 + 0.1 * recallCount)
|
|
|
110
110
|
boost = 0.05 * spacingMultiplier * diminishingFactor
|
|
111
111
|
```
|
|
112
112
|
|
|
113
|
-
Examples: 1 day gap = +0.05
|
|
113
|
+
Examples: 1 day gap = +0.05, 7 days = +0.08, 30 days = +0.10, cramming same day 20th recall = +0.02.
|
|
114
114
|
|
|
115
115
|
**Update in both the memory file AND index.json:**
|
|
116
116
|
- `last_accessed` → current timestamp
|
package/commands/brain/sleep.md
CHANGED
|
@@ -18,24 +18,6 @@ Sleep performs nine phases, mimicking real neuroscience:
|
|
|
18
18
|
8. **REM Dreaming** — Discover creative cross-domain associations via analogical reasoning
|
|
19
19
|
9. **Expertise Detection** — Identify dense knowledge areas and generate expertise profiles
|
|
20
20
|
|
|
21
|
-
### Migration Phase (Phase 0)
|
|
22
|
-
|
|
23
|
-
If the brain's `index.json` has `version: 1` (pre-v2), run migration first:
|
|
24
|
-
|
|
25
|
-
1. Create `associations.json` from existing `related` fields — for each memory with `related` entries, create edges with weight 0.20 and origin `manual`
|
|
26
|
-
2. Auto-discover associations: for any two memories sharing 2+ tags, create edges with weight 0.10 and origin `tag_overlap`
|
|
27
|
-
3. Create `contexts.json` with `{"version": 1, "sessions": []}`
|
|
28
|
-
4. Create `review-queue.json` with `{"version": 1, "items": []}`
|
|
29
|
-
5. Create `_archived/index.json` if not present with `{"version": 1, "archived_count": 0, "memories": {}}`
|
|
30
|
-
6. For each memory: backfill `recall_history` from `access_count` (if `access_count > 0`, set `recall_history: [last_accessed]`; otherwise `recall_history: []`)
|
|
31
|
-
7. Set defaults for missing fields: `cognitive_type: "semantic"`, `salience: 0.5`, `confidence: 0.8`
|
|
32
|
-
8. Update both memory files (frontmatter) and `index.json` entries
|
|
33
|
-
9. Set `index.json` version to 2
|
|
34
|
-
|
|
35
|
-
Present migration summary, then proceed to Phase 1.
|
|
36
|
-
|
|
37
|
-
---
|
|
38
|
-
|
|
39
21
|
## Phase 1: Replay (Hippocampal Scan)
|
|
40
22
|
|
|
41
23
|
During sleep, the hippocampus replays the day's events. Here, we scan and assess the full brain state.
|
|
@@ -532,4 +514,3 @@ After all phases complete, present a comprehensive sleep report:
|
|
|
532
514
|
7. **Idempotent expertise** — if `_expertise.md` already exists, update it rather than creating a duplicate.
|
|
533
515
|
8. **Skip empty phases** — if there's nothing to do in a phase (e.g., no flat clusters to reorganize), briefly note it and move on.
|
|
534
516
|
9. **Salience protection** — never auto-prune memories with salience >= 0.7.
|
|
535
|
-
10. **Run migration** — if `index.json` version is 1, run Phase 0 migration before proceeding.
|
package/commands/brain/status.md
CHANGED
|
@@ -12,6 +12,8 @@ Also read (if they exist):
|
|
|
12
12
|
- `.brain/associations.json` — for association network stats
|
|
13
13
|
- `.brain/review-queue.json` — for review schedule info
|
|
14
14
|
- `.brain/_archived/index.json` — for archive stats
|
|
15
|
+
- `.brain/.sync/config.json` — for cloud sync configuration
|
|
16
|
+
- `.brain/.sync/sync-state.json` — for sync state and pending changes
|
|
15
17
|
|
|
16
18
|
### 2. Compute Statistics
|
|
17
19
|
|
|
@@ -104,6 +106,13 @@ Calculate aggregate stats:
|
|
|
104
106
|
+ <title> (<path>) — <date>
|
|
105
107
|
+ <title> (<path>) — <date>
|
|
106
108
|
...
|
|
109
|
+
|
|
110
|
+
## Cloud Sync
|
|
111
|
+
Provider: <provider or "not configured">
|
|
112
|
+
Encryption: <enabled/disabled>
|
|
113
|
+
Last Sync: <timestamp or "never">
|
|
114
|
+
Pending Changes: <count> files modified since last sync
|
|
115
|
+
Conflicts: <count>
|
|
107
116
|
```
|
|
108
117
|
|
|
109
118
|
### 4. Health Check
|
|
@@ -119,4 +128,6 @@ Analyze the brain's health and provide recommendations:
|
|
|
119
128
|
- **"Needs sleep"** — Multiple flat clusters detected, OR many memories in moderate/weak tiers, OR no `_expertise.md` profiles exist despite having 10+ memories. Suggest `/brain:sleep`
|
|
120
129
|
- **"Low confidence"** — More than 30% of memories have confidence < 0.5. Suggest reviewing and validating uncertain memories.
|
|
121
130
|
- **"Review overdue"** — More than 10 memories are past their review date. Suggest `/brain:review`
|
|
122
|
-
- **"
|
|
131
|
+
- **"Sync available"** — Cloud sync is not configured. Suggest `/brain:sync login` for cross-device access.
|
|
132
|
+
- **"Sync stale"** — Last sync was more than 7 days ago. Suggest `/brain:sync push` or `/brain:sync pull`.
|
|
133
|
+
- **"Sync conflicts"** — Unresolved sync conflicts exist. Suggest `/brain:sync resolve`.
|