brain-memory 0.1.0-beta.14 → 0.1.0-beta.16

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 CHANGED
@@ -44,6 +44,8 @@ Existing AI memory solutions use flat databases with tag-based retrieval. Brain
44
44
  - **Context-dependent recall** — Memories encoded in a similar context to the current session are scored higher
45
45
  - **Spaced reinforcement** — Memories recalled after longer intervals get bigger boosts, cramming produces diminishing returns
46
46
  - **Cognitive types** — Episodic, semantic, and procedural memories each decay differently, just like in the brain
47
+ - **Always-present knowledge** — Pin critical conventions and preferences so they load every session, bypassing recall and never decaying — the facts your agent must never miss
48
+ - **Procedural skills** — Reusable how-to workflows with progressive disclosure, learned automatically from repeated experience and exportable to your agent's native skills
47
49
  - **On-demand depth** — Subcategories are created as needed, not pre-defined
48
50
  - **Consolidation** — Weak related memories merge into stronger combined knowledge
49
51
  - **Zero dependencies** — Pure file I/O, no databases, no servers, no embeddings required
@@ -52,38 +54,40 @@ Existing AI memory solutions use flat databases with tag-based retrieval. Brain
52
54
 
53
55
  ```bash
54
56
  npm install -g brain-memory@beta
55
- brain-memory
57
+ brain
56
58
  ```
57
59
 
58
- The first command installs the package globally — this gives you both the interactive setup wizard and the CLI tools (`brain-memorize`, `brain-recall`, `brain-reinforce`) that agents rely on for deterministic scoring.
60
+ The first command installs the package globally — this gives you both the interactive setup wizard and the `brain` CLI (`brain recall`, `brain memorize`, `brain reinforce`, …) that agents rely on for deterministic scoring.
59
61
 
60
62
  The second command runs the setup wizard, which asks which runtime(s) to configure (Claude Code, Gemini CLI, OpenAI Codex CLI, or all) and whether to install globally or for the current project.
61
63
 
62
64
  ### Non-interactive
63
65
 
64
66
  ```bash
65
- brain-memory --claude --global # Claude Code, global
66
- brain-memory --gemini --local # Gemini CLI, local project
67
- brain-memory --codex --global # OpenAI Codex CLI, global
68
- brain-memory --opencode --global # OpenCode, global
69
- brain-memory --all --global # All runtimes, global
67
+ brain --claude --global # Claude Code, global
68
+ brain --gemini --local # Gemini CLI, local project
69
+ brain --codex --global # OpenAI Codex CLI, global
70
+ brain --opencode --global # OpenCode, global
71
+ brain --all --global # All runtimes, global
70
72
  ```
71
73
 
72
74
  ### Update
73
75
 
74
76
  ```bash
75
77
  npm install -g brain-memory@beta
76
- brain-memory update
78
+ brain update
77
79
  ```
78
80
 
79
- The first command updates the package and CLI tools. The second command refreshes the slash command prompts for your installed runtimes. Target specific runtimes with `--claude`, `--gemini`, `--openai`, or `--all`.
81
+ The first command updates the package and the `brain` CLI. The second command refreshes the slash command prompts for your installed runtimes. Target specific runtimes with `--claude`, `--gemini`, `--openai`, or `--all`.
80
82
 
81
- > **Why not `npx`?** `npx` runs the setup wizard in a temporary directory that is discarded after execution. The CLI tools (`brain-memorize`, `brain-recall`, `brain-reinforce`) won't be available in your PATH, which means agents will fall back to less reliable manual file operations. Always use `npm install -g` to ensure everything works correctly.
83
+ > **Upgrading from an older version?** The separate binaries (`brain-recall`, `brain-memorize`, `brain-reinforce`, `brain-cloud`, `brain-memory`) were unified into a single `brain` dispatcher — use `brain recall`, `brain memorize`, `brain reinforce`, `brain cloud <…>` instead. Run `brain update` to refresh your runtime prompts to the new command surface.
84
+
85
+ > **Why not `npx`?** `npx` runs the setup wizard in a temporary directory that is discarded after execution. The `brain` CLI (`brain recall`, `brain memorize`, `brain reinforce`) won't be available in your PATH, which means agents will fall back to less reliable manual file operations. Always use `npm install -g` to ensure everything works correctly.
82
86
 
83
87
  ### Uninstall
84
88
 
85
89
  ```bash
86
- brain-memory uninstall
90
+ brain uninstall
87
91
  npm uninstall -g brain-memory
88
92
  ```
89
93
 
@@ -120,6 +124,8 @@ Then append the contents of the corresponding prompt file to your agent's instru
120
124
  | `/brain:init` | Initialize `~/.brain/` directory structure with default categories |
121
125
  | `/brain:memorize [topic] [--sync]` | Store memories from current session context (add `--sync` to auto-push) |
122
126
  | `/brain:remember [query]` | Recall relevant memories with spreading activation and context matching |
127
+ | `/brain:pin [id\|query]` | Pin a memory to the always-present tier — loads every session, never decays |
128
+ | `/brain:unpin [id\|query]` | Remove a memory from the always-present tier |
123
129
  | `/brain:review [scope]` | Spaced repetition review session for due memories |
124
130
  | `/brain:explore [category]` | Browse the brain hierarchy with visual tree view |
125
131
  | `/brain:consolidate [scope]` | Merge related weak memories into stronger combined ones |
@@ -127,6 +133,7 @@ Then append the contents of the corresponding prompt file to your agent's instru
127
133
  | `/brain:sunshine [target]` | Deep forensic erasure — trace and remove all references |
128
134
  | `/brain:sleep [scope]` | Full maintenance cycle — 9 neuroscience-inspired phases |
129
135
  | `/brain:status` | Dashboard with brain health metrics and recommendations |
136
+ | `/brain:skill [list\|show\|add\|use\|remove\|export]` | Manage procedural skills — reusable how-to workflows with progressive disclosure |
130
137
  | `/brain:sync [subcommand]` | Sync memories via Git remote or export/import for portability |
131
138
 
132
139
  ## Session Lifecycle
@@ -135,18 +142,19 @@ Brain Memory works automatically in the background — no commands needed for ba
135
142
 
136
143
  ### Session Start
137
144
 
138
- When a session begins and `~/.brain/` exists, the agent automatically:
145
+ When a session begins and `~/.brain/` exists, the agent makes a single `brain session-start` call. This aggregator returns one deterministic, **token-budget-bounded** payload so the brain can never bloat the context window (the budget lives in `~/.brain/config.json`):
139
146
 
140
- 1. Reads the brain index and loads the top 3-5 memories relevant to the current project
141
- 2. Checks the review queue for memories due for spaced repetition
142
- 3. Outputs a brief status line:
147
+ 1. **Pinned memories** — always-present conventions and preferences, injected verbatim regardless of recall score
148
+ 2. **Skills index** — the name + description of each available procedural skill (~100 tokens each; full instructions are loaded only when a task matches)
149
+ 3. **Context recall** — the top memories relevant to the current project
150
+ 4. **Review queue + low-confidence alerts**, then a brief status line:
143
151
 
144
152
  ```
145
153
  🧠 Brain active — 42 memories loaded (8 in current project context)
146
154
  📋 3 memories due for review — run /brain:review
147
155
  ```
148
156
 
149
- The agent silently internalizes relevant memories and references them naturally during the session — no information dump.
157
+ The agent treats pinned facts as active constraints, notes which skills exist, silently internalizes relevant memories, and references them naturally during the session — no information dump.
150
158
 
151
159
  ### Ambient Session Tracking
152
160
 
@@ -240,6 +248,38 @@ Each memory is also classified by how the brain processes it:
240
248
 
241
249
  During sleep, frequently-recalled episodic memories are **crystallized** into semantic memories — the specific event fades but the lesson persists. This mirrors how humans extract general principles from repeated experiences.
242
250
 
251
+ ### Always-Present Memories (Pinning)
252
+
253
+ Recall is probabilistic — a stored preference only applies if scoring happens to surface it. For the facts an agent must **never** miss (coding conventions, standing decisions, hard constraints), that's not good enough. Pinning fixes it:
254
+
255
+ - **`pinned`** — the memory is injected at **every** session start regardless of recall score, and is **decay-exempt** (it never fades). Scope it `global` (loads everywhere) or `project:<name>` (loads only in that project).
256
+ - **`stable`** — an independent flag that exempts a memory from decay and pruning **without** forcing it to always load — for timeless facts you recall on demand but don't want to fade.
257
+
258
+ ```bash
259
+ brain pin <id> --scope global --priority 1 # or: /brain:pin always use tabs
260
+ ```
261
+
262
+ Pinned and stable memories are skipped by sleep-cycle homeostasis and pruning, and `/brain:memorize` proactively proposes pinning durable conventions. The always-present set is budget-capped (`pin_budget_tokens`) so it can't crowd out the context window. This maps cleanly to the **semantic memory** type in the [CoALA](https://arxiv.org/abs/2309.02427) agent-memory model — knowledge that is always in context — decomposed into two orthogonal properties (always-loaded vs. non-decaying).
263
+
264
+ ### Procedural Skills
265
+
266
+ Procedural memory is *how* to do things — reusable, step-by-step workflows stored as `~/.brain/_skills/<name>/SKILL.md`. To keep them from flooding the context window, skills use **three-level progressive disclosure**:
267
+
268
+ | Level | When | What loads |
269
+ |-------|------|------------|
270
+ | **L0** | Every session start | Only each skill's name + description (~100 tokens) |
271
+ | **L1** | A task matches a skill | The full `SKILL.md` step-by-step instructions |
272
+ | **L2** | A step needs them | Referenced `resources/` (templates, scripts) |
273
+
274
+ ```bash
275
+ brain skill list # advertised skills (L0)
276
+ brain skill show structured-code-review # full instructions (L1)
277
+ brain skill use structured-code-review # record outcome (--failed weakens it)
278
+ brain skill export structured-code-review --target claude # → native .claude/skills/
279
+ ```
280
+
281
+ Skills strengthen on successful `use` and weaken on `--failed` — one that fails too often demotes itself out of the advertised L0 index. And they aren't only hand-authored: during sleep, Brain **crystallizes** recurring task-solving patterns from repeated experience into new skills (user-confirmed). Finally, `brain skill export` emits a skill in your agent's **native** format so it becomes directly executable.
282
+
243
283
  ### Memory File Format
244
284
 
245
285
  Each memory is a Markdown file with YAML frontmatter:
@@ -442,9 +482,16 @@ Sync state is stored locally in `~/.brain/.sync/` and is never pushed to the rem
442
482
  ```
443
483
  ~/.brain/
444
484
  ├── index.json # Memory inventory — fast lookup for all memories
485
+ ├── config.json # Working-memory token budgets (session-start injection)
445
486
  ├── associations.json # Weighted associative network between memories
446
487
  ├── contexts.json # Session context snapshots for context-dependent recall
447
488
  ├── review-queue.json # Spaced repetition scheduling
489
+ ├── pinned.json # Always-present tier manifest (pinned memory IDs + scope)
490
+ ├── skills-index.json # Advertised procedural skills (L0 — name + description)
491
+ ├── _skills/ # Procedural skills
492
+ │ └── <skill-name>/
493
+ │ ├── SKILL.md # Advertised description + step-by-step instructions
494
+ │ └── resources/ # Optional templates/scripts (loaded only at execution)
448
495
  ├── professional/ # Work, career, technical skills
449
496
  │ ├── _meta.json # Category metadata and stats
450
497
  │ ├── _expertise.md # Generated expertise profile
@@ -515,6 +562,28 @@ Brain configuration lives in `~/.brain/index.json` under the `config` key:
515
562
  | `association_config.spreading_activation_depth` | 2 | Maximum hops for spreading activation traversal |
516
563
  | `association_config.spreading_activation_decay` | 0.5 | Decay factor per hop during spreading activation |
517
564
 
565
+ ### Working-Memory Budget
566
+
567
+ A separate `~/.brain/config.json` (created lazily with safe defaults) caps how much the brain injects into the context window at session start, so the always-present tier can never crowd out your actual work:
568
+
569
+ ```json
570
+ {
571
+ "working_memory_budget_tokens": 3000,
572
+ "pin_budget_tokens": 1500,
573
+ "skills_index_budget_tokens": 800,
574
+ "recall_budget_tokens": 700
575
+ }
576
+ ```
577
+
578
+ | Setting | Default | Description |
579
+ |---------|---------|-------------|
580
+ | `working_memory_budget_tokens` | 3000 | Total token ceiling for the whole `brain session-start` payload |
581
+ | `pin_budget_tokens` | 1500 | Sub-budget for pinned, always-present memories |
582
+ | `skills_index_budget_tokens` | 800 | Sub-budget for the advertised skills index (L0) |
583
+ | `recall_budget_tokens` | 700 | Sub-budget for context-relevant recalled memories |
584
+
585
+ Token counts use a dependency-free heuristic stored on each memory at write time. When pins exceed their budget they're selected by `--priority` then strength, and the overflow is reported rather than silently dropped.
586
+
518
587
  ## Benchmark
519
588
 
520
589
  Empirical benchmarks show that agents with Brain Memory produce **more consistent** and **more successful** outputs across sessions.
package/assets/icon.png CHANGED
Binary file
@@ -0,0 +1,21 @@
1
+ <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1024 1024" width="1024" height="1024">
2
+ <rect x="0" y="0" width="1024" height="1024" rx="224" ry="224" fill="#F0EFE8"/>
3
+ <g stroke="#1A1A1A" stroke-width="20" stroke-linecap="round">
4
+ <line x1="512" y1="512" x2="512" y2="232"/>
5
+ <line x1="512" y1="512" x2="754.49" y2="372"/>
6
+ <line x1="512" y1="512" x2="754.49" y2="652"/>
7
+ <line x1="512" y1="512" x2="512" y2="792"/>
8
+ <line x1="512" y1="512" x2="269.51" y2="652"/>
9
+ <line x1="512" y1="512" x2="269.51" y2="372"/>
10
+ </g>
11
+ <g fill="#1A1A1A">
12
+ <circle cx="512" cy="232" r="44"/>
13
+ <circle cx="754.49" cy="372" r="44"/>
14
+ <circle cx="754.49" cy="652" r="44"/>
15
+ <circle cx="512" cy="792" r="44"/>
16
+ <circle cx="269.51" cy="652" r="44"/>
17
+ <circle cx="269.51" cy="372" r="44"/>
18
+ </g>
19
+ <circle cx="512" cy="512" r="98" fill="#1A1A1A"/>
20
+ <circle cx="512" cy="512" r="58" fill="#E7B300"/>
21
+ </svg>
package/bin/brain.js ADDED
@@ -0,0 +1,111 @@
1
+ #!/usr/bin/env node
2
+
3
+ /**
4
+ * brain — unified CLI dispatcher for the Brain Memory system.
5
+ *
6
+ * Routes subcommands to their implementations, replacing the former per-binary
7
+ * surface (brain-recall, brain-reinforce, brain-memorize, brain-cloud). Each
8
+ * delegate module still runs on load and remains invokable as `node bin/<file>`,
9
+ * so direct invocation and the existing test suite are unaffected.
10
+ *
11
+ * Usage:
12
+ * brain Interactive installer (also: brain install)
13
+ * brain install|update|uninstall [flags]
14
+ * brain recall "<query>" [--project P] [--task T] [--top N] [--context] [--reindex]
15
+ * brain memorize [--sync] Store memories from a JSON payload on stdin
16
+ * brain reinforce <id> [<id>...] Spaced reinforcement + Hebbian co-retrieval
17
+ * brain cloud <login|logout|push|pull|status>
18
+ * brain --help | brain --version
19
+ */
20
+
21
+ const path = require('path');
22
+
23
+ const VERSION = require('../package.json').version;
24
+
25
+ // Subcommands whose modules read process.argv.slice(2) directly. We strip the
26
+ // leading subcommand token, then require the module (which executes on load).
27
+ const DELEGATED = {
28
+ recall: 'recall.js',
29
+ reinforce: 'reinforce.js',
30
+ memorize: 'memorize.js',
31
+ cloud: 'cloud-sync.js',
32
+ 'session-start': 'session-start.js',
33
+ pin: 'pin.js',
34
+ unpin: 'unpin.js',
35
+ skill: 'skill.js',
36
+ };
37
+
38
+ // install.js finds its positional subcommand from process.argv itself, so it is
39
+ // required without stripping anything. Bare `brain` also routes here, preserving
40
+ // `npx brain-memory` via npm's single-bin fallback.
41
+ const INSTALLER = new Set(['install', 'update', 'uninstall']);
42
+
43
+ const HELP = `🧠 brain — Brain Memory CLI
44
+
45
+ Usage: brain <command> [options]
46
+
47
+ Memory
48
+ recall "<query>" [--project P] [--task T] [--top N]
49
+ Deterministic recall (TF-IDF + decay + spreading)
50
+ recall --context Session-start recall from project context
51
+ recall --reindex Rebuild the search index
52
+ memorize [--sync] Store memories from a JSON payload on stdin
53
+ reinforce <id> [<id>...] Spaced reinforcement + Hebbian co-retrieval
54
+ pin <id> [--scope global|project:<name>] [--priority N]
55
+ Pin a memory into the always-present tier
56
+ unpin <id> Remove a memory from the always-present tier
57
+ skill <list|show|use|add|remove|export>
58
+ Manage procedural skills (progressive disclosure)
59
+ session-start [--project P] [--task T] [--top N]
60
+ Budget-bounded startup payload (agent-invoked)
61
+
62
+ Sync
63
+ cloud <login|logout|push|pull|status>
64
+
65
+ Setup
66
+ install Interactive installer (default when no command)
67
+ update Update an existing installation
68
+ uninstall [--delete-data] Remove the installation
69
+
70
+ Other
71
+ --help, -h Show this help
72
+ --version, -v Show version
73
+ `;
74
+
75
+ function main() {
76
+ const sub = process.argv[2];
77
+
78
+ if (sub === '--version' || sub === '-v') {
79
+ console.log(VERSION);
80
+ return;
81
+ }
82
+
83
+ if (sub === '--help' || sub === '-h' || sub === 'help') {
84
+ console.log(HELP);
85
+ return;
86
+ }
87
+
88
+ // Bare `brain` or an installer subcommand → run the installer.
89
+ if (sub === undefined || INSTALLER.has(sub)) {
90
+ require(path.join(__dirname, 'install.js'));
91
+ return;
92
+ }
93
+
94
+ const file = DELEGATED[sub];
95
+ if (file) {
96
+ process.argv.splice(2, 1); // drop the subcommand token
97
+ const mod = require(path.join(__dirname, file));
98
+ // Modules guarded with `require.main === module` (e.g. session-start) export
99
+ // a main() that we must invoke; legacy modules already ran on require.
100
+ if (mod && typeof mod.main === 'function') {
101
+ mod.main(process.argv.slice(2));
102
+ }
103
+ return;
104
+ }
105
+
106
+ console.error(`Unknown command: ${sub}\n`);
107
+ console.error(HELP);
108
+ process.exit(1);
109
+ }
110
+
111
+ main();
package/bin/cloud-sync.js CHANGED
@@ -1,14 +1,14 @@
1
1
  #!/usr/bin/env node
2
2
 
3
3
  /**
4
- * brain-cloud — CLI for Brain Cloud sync
4
+ * brain cloud — CLI for Brain Cloud sync
5
5
  *
6
6
  * Usage:
7
- * brain-cloud login [--api-url URL] Authenticate via device code flow
8
- * brain-cloud logout Clear stored credentials
9
- * brain-cloud push Upload ~/.brain/ to the cloud
10
- * brain-cloud pull Download from the cloud to ~/.brain/
11
- * brain-cloud status Show connection and sync status
7
+ * brain cloud login [--api-url URL] Authenticate via device code flow
8
+ * brain cloud logout Clear stored credentials
9
+ * brain cloud push Upload ~/.brain/ to the cloud
10
+ * brain cloud pull Download from the cloud to ~/.brain/
11
+ * brain cloud status Show connection and sync status
12
12
  */
13
13
 
14
14
  const path = require('path');
@@ -23,7 +23,7 @@ async function main() {
23
23
 
24
24
  if (!command || command === '--help' || command === '-h') {
25
25
  console.log(`
26
- brain-cloud — Brain Cloud sync CLI
26
+ brain cloud — Brain Cloud sync CLI
27
27
 
28
28
  Commands:
29
29
  login [--api-url URL] Authenticate via device code flow
@@ -118,7 +118,7 @@ async function cmdStatus() {
118
118
 
119
119
  if (!s.connected) {
120
120
  console.log('☁️ Not connected to Brain Cloud');
121
- console.log(' Run: brain-cloud login');
121
+ console.log(' Run: brain cloud login');
122
122
  return;
123
123
  }
124
124
 
package/bin/memorize.js CHANGED
@@ -1,14 +1,14 @@
1
1
  #!/usr/bin/env node
2
2
 
3
3
  /**
4
- * brain-memorize — Store memories from AI agent input
4
+ * brain memorize — Store memories from AI agent input
5
5
  *
6
6
  * Accepts a JSON payload via stdin with memory definitions.
7
7
  * Handles all plumbing: ID generation, directory creation, file writing,
8
8
  * index updates, association edges, search index, and optional sync.
9
9
  *
10
10
  * Usage:
11
- * brain-memorize [--sync] <<'EOF'
11
+ * brain memorize [--sync] <<'EOF'
12
12
  * { "memories": [{ "title": "...", "type": "learning", ... }] }
13
13
  * EOF
14
14
  *
@@ -29,6 +29,8 @@ const {
29
29
  readAssociations,
30
30
  writeAssociations,
31
31
  reinforceEdge,
32
+ readPinned,
33
+ writePinned,
32
34
  atomicWriteSync,
33
35
  validateBrainPath,
34
36
  } = require('../src/index-manager');
@@ -82,7 +84,7 @@ function buildMemoryFileContent(mem, id, now) {
82
84
  mem.type, mem.cognitive_type, mem.strength_adjustment
83
85
  );
84
86
 
85
- const frontmatter = [
87
+ const fmLines = [
86
88
  '---',
87
89
  `id: ${id}`,
88
90
  `type: ${mem.type}`,
@@ -95,6 +97,16 @@ function buildMemoryFileContent(mem, id, now) {
95
97
  `decay_rate: ${decay_rate}`,
96
98
  `salience: ${mem.salience ?? 0.5}`,
97
99
  `confidence: ${mem.confidence ?? 0.7}`,
100
+ ];
101
+ // CoALA Phase 1: pinned (always-loaded) and stable (decay-exempt) are emitted
102
+ // only when set, so ordinary memories keep their existing frontmatter shape.
103
+ if (mem.pinned) {
104
+ fmLines.push('pinned: true');
105
+ fmLines.push(`pin_scope: "${mem.pin_scope || 'global'}"`);
106
+ fmLines.push(`pin_priority: ${mem.pin_priority || 0}`);
107
+ }
108
+ if (mem.stable) fmLines.push('stable: true');
109
+ fmLines.push(
98
110
  `tags: [${(mem.tags || []).map(t => `"${t}"`).join(', ')}]`,
99
111
  `related: [${(mem.related || []).map(r => `"${r}"`).join(', ')}]`,
100
112
  `source: "${mem.source || ''}"`,
@@ -104,13 +116,14 @@ function buildMemoryFileContent(mem, id, now) {
104
116
  ` task_type: "${(mem.encoding_context && mem.encoding_context.task_type) || ''}"`,
105
117
  '---',
106
118
  '',
107
- ].join('\n');
119
+ );
120
+ const frontmatter = fmLines.join('\n');
108
121
 
109
122
  return { fileContent: frontmatter + mem.content + '\n', strength, decay_rate };
110
123
  }
111
124
 
112
125
  function buildIndexEntry(mem, id, strength, decayRate, now) {
113
- return {
126
+ const entry = {
114
127
  title: mem.title,
115
128
  path: mem.path,
116
129
  type: mem.type,
@@ -125,7 +138,17 @@ function buildIndexEntry(mem, id, strength, decayRate, now) {
125
138
  tags: mem.tags || [],
126
139
  related: mem.related || [],
127
140
  encoding_context: mem.encoding_context || {},
141
+ // CoALA Phase 0: cheap chars/4 token estimate for working-memory budgeting.
142
+ token_estimate: Math.ceil((mem.content || '').length / 4),
128
143
  };
144
+ // CoALA Phase 1: only set when present — keeps existing index entries lean.
145
+ if (mem.pinned) {
146
+ entry.pinned = true;
147
+ entry.pin_scope = mem.pin_scope || 'global';
148
+ entry.pin_priority = mem.pin_priority || 0;
149
+ }
150
+ if (mem.stable) entry.stable = true;
151
+ return entry;
129
152
  }
130
153
 
131
154
  function updateMetaFiles(brainDir, memPath) {
@@ -184,7 +207,7 @@ function trySync() {
184
207
  const cloudConfig = path.join(brainDir, '.cloud', 'config.json');
185
208
  if (fs.existsSync(cloudConfig)) {
186
209
  try {
187
- execSync('brain-cloud push', { stdio: 'pipe', timeout: 30000 });
210
+ execSync('brain cloud push', { stdio: 'pipe', timeout: 30000 });
188
211
  return { method: 'cloud', success: true };
189
212
  } catch (err) {
190
213
  return { method: 'cloud', success: false, error: err.message };
@@ -242,7 +265,7 @@ async function main() {
242
265
 
243
266
  // Validate brain exists
244
267
  if (!fs.existsSync(path.join(brainDir, 'index.json'))) {
245
- console.error(JSON.stringify({ error: `Brain not initialized. Run brain-memory install first.` }));
268
+ console.error(JSON.stringify({ error: `Brain not initialized. Run brain install first.` }));
246
269
  process.exit(1);
247
270
  }
248
271
 
@@ -278,6 +301,7 @@ async function main() {
278
301
  const now = new Date().toISOString();
279
302
  const results = [];
280
303
  const newIds = [];
304
+ const pinnedToAdd = [];
281
305
 
282
306
  for (const mem of input.memories) {
283
307
  // Validate required fields
@@ -312,6 +336,16 @@ async function main() {
312
336
  const indexEntry = buildIndexEntry(mem, id, strength, decay_rate, now);
313
337
  addMemory(index, id, indexEntry);
314
338
 
339
+ // CoALA Phase 1: register a born-pinned memory in the pinned manifest
340
+ if (mem.pinned) {
341
+ pinnedToAdd.push({
342
+ id,
343
+ scope: mem.pin_scope || 'global',
344
+ priority: mem.pin_priority || 0,
345
+ token_estimate: indexEntry.token_estimate,
346
+ });
347
+ }
348
+
315
349
  // Update associations — explicit related links
316
350
  for (const relatedId of (mem.related || [])) {
317
351
  if (index.memories[relatedId]) {
@@ -325,6 +359,15 @@ async function main() {
325
359
  reinforceEdge(associations, id, overlapId, 'tag_overlap', 0.10);
326
360
  }
327
361
 
362
+ // Tier B §10.2: surface potential contradictions with pinned/stable memories
363
+ // (high tag overlap) so the agent can adjudicate — never auto-resolved here.
364
+ const potentialConflicts = tagOverlaps
365
+ .filter((oid) => {
366
+ const e = index.memories[oid];
367
+ return e && (e.pinned || e.stable);
368
+ })
369
+ .map((oid) => ({ id: oid, title: index.memories[oid].title }));
370
+
328
371
  // Update search index
329
372
  addDocument(searchIndex, id, {
330
373
  title: mem.title,
@@ -349,6 +392,7 @@ async function main() {
349
392
  confidence: mem.confidence ?? 0.7,
350
393
  tags: mem.tags || [],
351
394
  edges_created: edgesCreated,
395
+ ...(potentialConflicts.length ? { potential_conflicts: potentialConflicts } : {}),
352
396
  });
353
397
  }
354
398
 
@@ -357,6 +401,16 @@ async function main() {
357
401
  writeAssociations(associations);
358
402
  writeSearchIndex(brainDir, searchIndex);
359
403
 
404
+ // CoALA Phase 1: persist any born-pinned memories to the pinned manifest
405
+ if (pinnedToAdd.length > 0) {
406
+ const pinned = readPinned();
407
+ for (const p of pinnedToAdd) {
408
+ pinned.pins = pinned.pins.filter((x) => x.id !== p.id);
409
+ pinned.pins.push(p);
410
+ }
411
+ writePinned(pinned);
412
+ }
413
+
360
414
  // Build output
361
415
  const output = {
362
416
  stored: results,
package/bin/pin.js ADDED
@@ -0,0 +1,44 @@
1
+ #!/usr/bin/env node
2
+
3
+ /**
4
+ * brain pin — pin a memory into the always-present semantic tier (CoALA Phase 1).
5
+ *
6
+ * Usage:
7
+ * brain pin <id> [--scope global|project:<name>] [--priority N]
8
+ */
9
+
10
+ const { pinMemory } = require('../src/pinning');
11
+
12
+ function parseArgs(argv) {
13
+ const args = { id: null, scope: 'global', priority: 0 };
14
+ for (let i = 0; i < argv.length; i++) {
15
+ switch (argv[i]) {
16
+ case '--scope': args.scope = argv[++i]; break;
17
+ case '--priority': args.priority = parseInt(argv[++i], 10) || 0; break;
18
+ default:
19
+ if (!argv[i].startsWith('--') && !args.id) args.id = argv[i];
20
+ break;
21
+ }
22
+ }
23
+ return args;
24
+ }
25
+
26
+ function main(argv) {
27
+ const args = parseArgs(argv || process.argv.slice(2));
28
+ if (!args.id) {
29
+ console.error(JSON.stringify({ error: 'Usage: brain pin <id> [--scope global|project:<name>] [--priority N]' }));
30
+ process.exit(1);
31
+ }
32
+ const result = pinMemory(undefined, args.id, { scope: args.scope, priority: args.priority });
33
+ if (result.error) {
34
+ console.error(JSON.stringify(result));
35
+ process.exit(1);
36
+ }
37
+ console.log(JSON.stringify(result, null, 2));
38
+ }
39
+
40
+ if (require.main === module) {
41
+ main(process.argv.slice(2));
42
+ }
43
+
44
+ module.exports = { main, parseArgs };
package/bin/recall.js CHANGED
@@ -7,10 +7,10 @@
7
7
  * The agent calls this instead of manually computing the v4 formula.
8
8
  *
9
9
  * Usage:
10
- * brain-recall "async race conditions"
11
- * brain-recall "database pooling" --project my-app --task implementing --top 5
12
- * brain-recall --context # Session-start mode: auto-detect context
13
- * brain-recall --reindex # Rebuild search index from all memories
10
+ * brain recall "async race conditions"
11
+ * brain recall "database pooling" --project my-app --task implementing --top 5
12
+ * brain recall --context # Session-start mode: auto-detect context
13
+ * brain recall --reindex # Rebuild search index from all memories
14
14
  *
15
15
  * Output: JSON array of scored results, sorted by score descending.
16
16
  */
@@ -54,7 +54,7 @@ function main() {
54
54
 
55
55
  // Need a query for search
56
56
  if (!args.query && !args.context) {
57
- console.error(JSON.stringify({ error: 'Usage: brain-recall "query" or brain-recall --context' }));
57
+ console.error(JSON.stringify({ error: 'Usage: brain recall "query" or brain recall --context' }));
58
58
  process.exit(1);
59
59
  }
60
60
 
package/bin/reinforce.js CHANGED
@@ -8,8 +8,8 @@
8
8
  * results instead of manually updating frontmatter.
9
9
  *
10
10
  * Usage:
11
- * brain-reinforce mem_123 mem_456 mem_789
12
- * brain-reinforce mem_123 --project my-app
11
+ * brain reinforce mem_123 mem_456 mem_789
12
+ * brain reinforce mem_123 --project my-app
13
13
  *
14
14
  * Effects:
15
15
  * - Spaced reinforcement boost to each memory's strength
@@ -41,7 +41,7 @@ function main() {
41
41
  const args = parseArgs(process.argv.slice(2));
42
42
 
43
43
  if (args.memoryIds.length === 0) {
44
- console.error(JSON.stringify({ error: 'Usage: brain-reinforce <mem_id1> [mem_id2] ...' }));
44
+ console.error(JSON.stringify({ error: 'Usage: brain reinforce <mem_id1> [mem_id2] ...' }));
45
45
  process.exit(1);
46
46
  }
47
47