@claude-flow/codex 3.0.0-alpha.2 → 3.0.0-alpha.3

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.
Files changed (2) hide show
  1. package/README.md +444 -73
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -13,19 +13,10 @@ OpenAI Codex CLI adapter for Claude Flow V3. Enables multi-agent orchestration w
13
13
 
14
14
  **Codex does the work. Claude-flow coordinates and learns.**
15
15
 
16
- ## Features
17
-
18
- - **AGENTS.md Generation** - Creates project instructions for Codex
19
- - **MCP Integration** - Self-learning via memory and vector search
20
- - **137+ Skills** - Invoke with `$skill-name` syntax
21
- - **Vector Memory** - Semantic pattern search (384-dim embeddings)
22
- - **Dual Platform** - Supports both Claude Code and Codex
23
- - **Auto-Registration** - MCP server registered during init
24
-
25
- ## Installation
16
+ ## Quick Start
26
17
 
27
18
  ```bash
28
- # Via claude-flow CLI (recommended)
19
+ # Initialize for Codex (recommended)
29
20
  npx claude-flow@alpha init --codex
30
21
 
31
22
  # Full setup with all 137+ skills
@@ -35,7 +26,30 @@ npx claude-flow@alpha init --codex --full
35
26
  npx claude-flow@alpha init --dual
36
27
  ```
37
28
 
38
- ## MCP Integration (Self-Learning)
29
+ ---
30
+
31
+ <details>
32
+ <summary><b>Features</b></summary>
33
+
34
+ | Feature | Description |
35
+ |---------|-------------|
36
+ | **AGENTS.md Generation** | Creates project instructions for Codex |
37
+ | **MCP Integration** | Self-learning via memory and vector search |
38
+ | **137+ Skills** | Invoke with `$skill-name` syntax |
39
+ | **Vector Memory** | Semantic pattern search (384-dim embeddings) |
40
+ | **Dual Platform** | Supports both Claude Code and Codex |
41
+ | **Auto-Registration** | MCP server registered during init |
42
+ | **HNSW Search** | 150x-12,500x faster pattern matching |
43
+ | **Self-Learning** | Learn from successes, remember patterns |
44
+
45
+ </details>
46
+
47
+ ---
48
+
49
+ <details>
50
+ <summary><b>MCP Integration (Self-Learning)</b></summary>
51
+
52
+ ### Automatic Registration
39
53
 
40
54
  When you run `init --codex`, the MCP server is **automatically registered** with Codex:
41
55
 
@@ -43,34 +57,76 @@ When you run `init --codex`, the MCP server is **automatically registered** with
43
57
  # Verify MCP is registered
44
58
  codex mcp list
45
59
 
46
- # Expected:
60
+ # Expected output:
47
61
  # Name Command Args Status
48
62
  # claude-flow npx claude-flow mcp start enabled
63
+ ```
64
+
65
+ ### Manual Registration
49
66
 
50
- # If not present, add manually:
67
+ If MCP is not present, add manually:
68
+
69
+ ```bash
51
70
  codex mcp add claude-flow -- npx claude-flow mcp start
52
71
  ```
53
72
 
54
- ### MCP Tools for Learning
73
+ ### MCP Tools Reference
55
74
 
56
75
  | Tool | Purpose | When to Use |
57
76
  |------|---------|-------------|
58
- | `memory_search` | Semantic vector search | BEFORE starting any task |
59
- | `memory_store` | Save patterns with embeddings | AFTER completing successfully |
77
+ | `memory_search` | Semantic vector search | **BEFORE** starting any task |
78
+ | `memory_store` | Save patterns with embeddings | **AFTER** completing successfully |
60
79
  | `swarm_init` | Initialize coordination | Start of complex tasks |
61
80
  | `agent_spawn` | Register agent roles | Multi-agent workflows |
62
81
  | `neural_train` | Train on patterns | Periodic improvement |
63
82
 
64
- ## Self-Learning Workflow
83
+ ### Tool Parameters
65
84
 
85
+ **memory_search**
86
+ ```json
87
+ {
88
+ "query": "search terms",
89
+ "namespace": "patterns",
90
+ "limit": 5
91
+ }
66
92
  ```
67
- 1. LEARN: memory_search(query="task keywords") → Find similar patterns
68
- 2. COORD: swarm_init(topology="hierarchical") → Set up coordination
69
- 3. EXECUTE: YOU write code, run commands → Codex does real work
70
- 4. REMEMBER: memory_store(key, value, namespace="patterns") → Save for future
93
+
94
+ **memory_store**
95
+ ```json
96
+ {
97
+ "key": "pattern-name",
98
+ "value": "what worked",
99
+ "namespace": "patterns",
100
+ "upsert": true
101
+ }
71
102
  ```
72
103
 
73
- ### Example Prompt for Codex
104
+ **swarm_init**
105
+ ```json
106
+ {
107
+ "topology": "hierarchical",
108
+ "maxAgents": 5,
109
+ "strategy": "specialized"
110
+ }
111
+ ```
112
+
113
+ </details>
114
+
115
+ ---
116
+
117
+ <details>
118
+ <summary><b>Self-Learning Workflow</b></summary>
119
+
120
+ ### The 4-Step Pattern
121
+
122
+ ```
123
+ 1. LEARN: memory_search(query="task keywords") → Find similar patterns
124
+ 2. COORD: swarm_init(topology="hierarchical") → Set up coordination
125
+ 3. EXECUTE: YOU write code, run commands → Codex does real work
126
+ 4. REMEMBER: memory_store(key, value, upsert=true) → Save for future
127
+ ```
128
+
129
+ ### Complete Example Prompt
74
130
 
75
131
  ```
76
132
  Build an email validator using a learning-enabled swarm.
@@ -85,7 +141,7 @@ STEP 2 - COORDINATE (use MCP tools):
85
141
  Use tool: swarm_init with topology="hierarchical", maxAgents=3
86
142
  Use tool: agent_spawn with type="coder", name="validator"
87
143
 
88
- STEP 3 - EXECUTE (YOU do this):
144
+ STEP 3 - EXECUTE (YOU do this - DON'T STOP HERE):
89
145
  Create /tmp/validator/email.js with validateEmail() function
90
146
  Create /tmp/validator/test.js with test cases
91
147
  Run the tests
@@ -95,53 +151,146 @@ Use tool: memory_store
95
151
  key: "pattern-email-validator"
96
152
  value: "Email validation: regex, returns boolean, test cases"
97
153
  namespace: "patterns"
154
+ upsert: true
98
155
 
99
- YOU execute all code. Use MCP tools for learning.
156
+ YOU execute all code. MCP tools are for learning only.
100
157
  ```
101
158
 
102
- ## Directory Structure
159
+ ### Similarity Score Guide
160
+
161
+ | Score | Meaning | Action |
162
+ |-------|---------|--------|
163
+ | > 0.7 | Strong match | Use the pattern directly |
164
+ | 0.5 - 0.7 | Partial match | Adapt and modify |
165
+ | < 0.5 | Weak match | Create new approach |
166
+
167
+ </details>
168
+
169
+ ---
170
+
171
+ <details>
172
+ <summary><b>Directory Structure</b></summary>
103
173
 
104
174
  ```
105
175
  project/
106
- ├── AGENTS.md # Main project instructions (Codex format)
176
+ ├── AGENTS.md # Main project instructions (Codex format)
107
177
  ├── .agents/
108
- │ ├── config.toml # Project configuration
109
- │ ├── skills/ # 137+ skills
178
+ │ ├── config.toml # Project configuration
179
+ │ ├── skills/ # 137+ skills
110
180
  │ │ ├── swarm-orchestration/
111
181
  │ │ │ └── SKILL.md
112
182
  │ │ ├── memory-management/
113
183
  │ │ │ └── SKILL.md
184
+ │ │ ├── sparc-methodology/
185
+ │ │ │ └── SKILL.md
114
186
  │ │ └── ...
115
- │ └── README.md # Directory documentation
116
- ├── .codex/
117
- │ ├── config.toml # Local overrides (gitignored)
118
- │ └── AGENTS.override.md # Local instruction overrides
119
- └── .claude-flow/
120
- ├── config.yaml # Runtime configuration
121
- ├── data/ # Memory and cache
122
- └── logs/ # Log files
187
+ │ └── README.md # Directory documentation
188
+ ├── .codex/ # Local overrides (gitignored)
189
+ │ ├── config.toml # Local development settings
190
+ │ └── AGENTS.override.md # Local instruction overrides
191
+ └── .claude-flow/ # Runtime data
192
+ ├── config.yaml # Runtime configuration
193
+ ├── data/ # Memory and cache
194
+ └── memory.db # SQLite with vector embeddings
195
+ └── logs/ # Log files
123
196
  ```
124
197
 
125
- ## Templates
198
+ ### Key Files
199
+
200
+ | File | Purpose |
201
+ |------|---------|
202
+ | `AGENTS.md` | Main instructions for Codex (required) |
203
+ | `.agents/config.toml` | Project-wide configuration |
204
+ | `.codex/config.toml` | Local overrides (gitignored) |
205
+ | `.claude-flow/data/memory.db` | Vector memory database |
206
+
207
+ </details>
208
+
209
+ ---
126
210
 
127
- | Template | Skills | Learning | Description |
128
- |----------|--------|----------|-------------|
129
- | `minimal` | 2 | Basic | Core skills only |
130
- | `default` | 4 | Yes | Standard setup |
131
- | `full` | 137+ | Yes | All available skills |
132
- | `enterprise` | 137+ | Advanced | Full + governance |
211
+ <details>
212
+ <summary><b>Templates</b></summary>
133
213
 
134
- ## Platform Comparison
214
+ ### Available Templates
215
+
216
+ | Template | Skills | Learning | Best For |
217
+ |----------|--------|----------|----------|
218
+ | `minimal` | 2 | Basic | Quick prototypes |
219
+ | `default` | 4 | Yes | Standard projects |
220
+ | `full` | 137+ | Yes | Full-featured development |
221
+ | `enterprise` | 137+ | Advanced | Team environments |
222
+
223
+ ### Usage
224
+
225
+ ```bash
226
+ # Minimal (fastest init)
227
+ npx claude-flow@alpha init --codex --minimal
228
+
229
+ # Default
230
+ npx claude-flow@alpha init --codex
231
+
232
+ # Full (all skills)
233
+ npx claude-flow@alpha init --codex --full
234
+ ```
235
+
236
+ ### Template Contents
237
+
238
+ **Minimal:**
239
+ - Core swarm orchestration
240
+ - Basic memory management
241
+
242
+ **Default:**
243
+ - Swarm orchestration
244
+ - Memory management
245
+ - SPARC methodology
246
+ - Basic coding patterns
247
+
248
+ **Full:**
249
+ - All 137+ skills
250
+ - GitHub integration
251
+ - Security scanning
252
+ - Performance optimization
253
+ - AgentDB vector search
254
+ - Neural pattern training
255
+
256
+ </details>
257
+
258
+ ---
259
+
260
+ <details>
261
+ <summary><b>Platform Comparison (Claude Code vs Codex)</b></summary>
135
262
 
136
263
  | Feature | Claude Code | OpenAI Codex |
137
264
  |---------|-------------|--------------|
138
- | Config File | CLAUDE.md | AGENTS.md |
139
- | Skills Dir | .claude/skills/ | .agents/skills/ |
265
+ | Config File | `CLAUDE.md` | `AGENTS.md` |
266
+ | Skills Dir | `.claude/skills/` | `.agents/skills/` |
140
267
  | Skill Syntax | `/skill-name` | `$skill-name` |
141
- | Settings | settings.json | config.toml |
268
+ | Settings | `settings.json` | `config.toml` |
142
269
  | MCP | Native | Via `codex mcp add` |
270
+ | Overrides | `.claude.local.md` | `.codex/config.toml` |
271
+
272
+ ### Dual Mode
273
+
274
+ Run `init --dual` to set up both platforms:
275
+
276
+ ```bash
277
+ npx claude-flow@alpha init --dual
278
+ ```
143
279
 
144
- ## Skill Invocation
280
+ This creates:
281
+ - `CLAUDE.md` for Claude Code users
282
+ - `AGENTS.md` for Codex users
283
+ - Shared `.claude-flow/` runtime
284
+ - Cross-compatible skills
285
+
286
+ </details>
287
+
288
+ ---
289
+
290
+ <details>
291
+ <summary><b>Skill Invocation</b></summary>
292
+
293
+ ### Syntax
145
294
 
146
295
  In OpenAI Codex CLI, invoke skills with `$` prefix:
147
296
 
@@ -152,9 +301,46 @@ $sparc-methodology
152
301
  $security-audit
153
302
  $agent-coder
154
303
  $agent-tester
304
+ $github-workflow
305
+ $performance-optimization
306
+ ```
307
+
308
+ ### Skill Categories
309
+
310
+ | Category | Examples |
311
+ |----------|----------|
312
+ | **Swarm** | `$swarm-orchestration`, `$swarm-advanced` |
313
+ | **Memory** | `$memory-management`, `$agentdb-vector-search` |
314
+ | **SPARC** | `$sparc-methodology`, `$specification`, `$architecture` |
315
+ | **GitHub** | `$github-code-review`, `$github-workflow-automation` |
316
+ | **Security** | `$security-audit`, `$security-overhaul` |
317
+ | **Testing** | `$tdd-london-swarm`, `$production-validator` |
318
+
319
+ ### Custom Skills
320
+
321
+ Create custom skills in `.agents/skills/`:
322
+
323
+ ```
324
+ .agents/skills/my-skill/
325
+ └── SKILL.md
155
326
  ```
156
327
 
157
- ## Configuration
328
+ **SKILL.md format:**
329
+ ```markdown
330
+ # My Custom Skill
331
+
332
+ Instructions for what this skill does...
333
+
334
+ ## Usage
335
+ Invoke with `$my-skill`
336
+ ```
337
+
338
+ </details>
339
+
340
+ ---
341
+
342
+ <details>
343
+ <summary><b>Configuration</b></summary>
158
344
 
159
345
  ### .agents/config.toml
160
346
 
@@ -162,12 +348,15 @@ $agent-tester
162
348
  # Model configuration
163
349
  model = "gpt-4"
164
350
 
165
- # Approval policy
351
+ # Approval policy: "always" | "on-request" | "never"
166
352
  approval_policy = "on-request"
167
353
 
168
- # Sandbox mode
354
+ # Sandbox mode: "read-only" | "workspace-write" | "danger-full-access"
169
355
  sandbox_mode = "workspace-write"
170
356
 
357
+ # Web search: "off" | "cached" | "live"
358
+ web_search = "cached"
359
+
171
360
  # MCP Servers
172
361
  [mcp_servers.claude-flow]
173
362
  command = "npx"
@@ -182,31 +371,117 @@ enabled = true
182
371
  [[skills]]
183
372
  path = ".agents/skills/memory-management"
184
373
  enabled = true
374
+
375
+ [[skills]]
376
+ path = ".agents/skills/sparc-methodology"
377
+ enabled = true
185
378
  ```
186
379
 
187
- ### .codex/config.toml (Local)
380
+ ### .codex/config.toml (Local Overrides)
188
381
 
189
382
  ```toml
190
383
  # Local development overrides (gitignored)
384
+ # These settings override .agents/config.toml
385
+
191
386
  approval_policy = "never"
192
387
  sandbox_mode = "danger-full-access"
193
388
  web_search = "live"
389
+
390
+ # Disable MCP in local if needed
391
+ [mcp_servers.claude-flow]
392
+ enabled = false
194
393
  ```
195
394
 
196
- ## API Reference
395
+ ### Environment Variables
396
+
397
+ ```bash
398
+ # Configuration paths
399
+ CLAUDE_FLOW_CONFIG=./claude-flow.config.json
400
+ CLAUDE_FLOW_MEMORY_PATH=./.claude-flow/data
401
+
402
+ # Provider keys
403
+ ANTHROPIC_API_KEY=sk-ant-...
404
+ OPENAI_API_KEY=sk-...
405
+
406
+ # MCP settings
407
+ CLAUDE_FLOW_MCP_PORT=3000
408
+ ```
409
+
410
+ </details>
411
+
412
+ ---
413
+
414
+ <details>
415
+ <summary><b>Vector Search Details</b></summary>
416
+
417
+ ### Specifications
418
+
419
+ | Property | Value |
420
+ |----------|-------|
421
+ | Embedding Dimensions | 384 |
422
+ | Search Algorithm | HNSW |
423
+ | Speed Improvement | 150x-12,500x faster |
424
+ | Similarity Range | 0.0 - 1.0 |
425
+ | Storage | SQLite with vector extension |
426
+ | Model | all-MiniLM-L6-v2 |
427
+
428
+ ### Namespaces
429
+
430
+ | Namespace | Purpose |
431
+ |-----------|---------|
432
+ | `patterns` | Successful code patterns |
433
+ | `solutions` | Bug fixes and solutions |
434
+ | `tasks` | Task completion records |
435
+ | `coordination` | Swarm state |
436
+ | `results` | Worker results |
437
+ | `default` | General storage |
438
+
439
+ ### Example Searches
197
440
 
198
- ### CodexInitializer
441
+ ```javascript
442
+ // Find auth patterns
443
+ memory_search({ query: "authentication JWT patterns", namespace: "patterns" })
444
+
445
+ // Find bug solutions
446
+ memory_search({ query: "null pointer fix", namespace: "solutions" })
447
+
448
+ // Find past tasks
449
+ memory_search({ query: "user profile API", namespace: "tasks" })
450
+ ```
451
+
452
+ </details>
453
+
454
+ ---
455
+
456
+ <details>
457
+ <summary><b>API Reference</b></summary>
458
+
459
+ ### CodexInitializer Class
199
460
 
200
461
  ```typescript
462
+ import { CodexInitializer } from '@claude-flow/codex';
463
+
201
464
  class CodexInitializer {
465
+ /**
466
+ * Initialize a Codex project
467
+ */
202
468
  async initialize(options: CodexInitOptions): Promise<CodexInitResult>;
469
+
470
+ /**
471
+ * Preview what would be created without writing files
472
+ */
203
473
  async dryRun(options: CodexInitOptions): Promise<string[]>;
204
474
  }
205
475
  ```
206
476
 
207
- ### initializeCodexProject
477
+ ### initializeCodexProject Function
208
478
 
209
479
  ```typescript
480
+ import { initializeCodexProject } from '@claude-flow/codex';
481
+
482
+ /**
483
+ * Quick initialization helper
484
+ */
210
485
  async function initializeCodexProject(
211
486
  projectPath: string,
212
487
  options?: Partial<CodexInitOptions>
@@ -217,24 +492,35 @@ async function initializeCodexProject(
217
492
 
218
493
  ```typescript
219
494
  interface CodexInitOptions {
495
+ /** Project directory path */
220
496
  projectPath: string;
497
+ /** Template to use */
221
498
  template?: 'minimal' | 'default' | 'full' | 'enterprise';
499
+ /** Specific skills to include */
222
500
  skills?: string[];
501
+ /** Overwrite existing files */
223
502
  force?: boolean;
503
+ /** Enable dual mode (Claude Code + Codex) */
224
504
  dual?: boolean;
225
505
  }
226
506
 
227
507
  interface CodexInitResult {
508
+ /** Whether initialization succeeded */
228
509
  success: boolean;
510
+ /** List of files created */
229
511
  filesCreated: string[];
512
+ /** List of skills generated */
230
513
  skillsGenerated: string[];
514
+ /** Whether MCP was registered */
231
515
  mcpRegistered?: boolean;
516
+ /** Non-fatal warnings */
232
517
  warnings?: string[];
518
+ /** Fatal errors */
233
519
  errors?: string[];
234
520
  }
235
521
  ```
236
522
 
237
- ## Programmatic Usage
523
+ ### Programmatic Usage
238
524
 
239
525
  ```typescript
240
526
  import { CodexInitializer, initializeCodexProject } from '@claude-flow/codex';
@@ -246,32 +532,33 @@ const result = await initializeCodexProject('/path/to/project', {
246
532
  dual: false,
247
533
  });
248
534
 
535
+ console.log(`Files created: ${result.filesCreated.length}`);
536
+ console.log(`Skills: ${result.skillsGenerated.length}`);
537
+ console.log(`MCP registered: ${result.mcpRegistered}`);
538
+
249
539
  // Or use the class directly
250
540
  const initializer = new CodexInitializer();
251
541
  const result = await initializer.initialize({
252
542
  projectPath: '/path/to/project',
253
543
  template: 'enterprise',
254
- skills: ['swarm-orchestration', 'memory-management'],
544
+ skills: ['swarm-orchestration', 'memory-management', 'security-audit'],
255
545
  force: false,
256
546
  dual: true,
257
547
  });
258
548
 
259
- console.log(`MCP registered: ${result.mcpRegistered}`);
260
- console.log(`Skills created: ${result.skillsGenerated.length}`);
549
+ if (result.warnings?.length) {
550
+ console.warn('Warnings:', result.warnings);
551
+ }
261
552
  ```
262
553
 
263
- ## Vector Search Details
554
+ </details>
264
555
 
265
- - **Embedding Dimensions**: 384
266
- - **Search Algorithm**: HNSW (150x-12,500x faster)
267
- - **Similarity Scoring**: 0-1 (higher = better match)
268
- - Score > 0.7: Strong match, use pattern
269
- - Score 0.5-0.7: Partial match, adapt
270
- - Score < 0.5: Weak match, create new
556
+ ---
271
557
 
272
- ## Migration
558
+ <details>
559
+ <summary><b>Migration from Claude Code</b></summary>
273
560
 
274
- Convert an existing CLAUDE.md project to Codex format:
561
+ ### Convert CLAUDE.md to AGENTS.md
275
562
 
276
563
  ```typescript
277
564
  import { migrate } from '@claude-flow/codex';
@@ -282,14 +569,98 @@ const result = await migrate({
282
569
  preserveComments: true,
283
570
  generateSkills: true,
284
571
  });
572
+
573
+ console.log(`Migrated: ${result.success}`);
574
+ console.log(`Skills generated: ${result.skillsGenerated.length}`);
285
575
  ```
286
576
 
577
+ ### Manual Migration Checklist
578
+
579
+ 1. **Rename config file**: `CLAUDE.md` → `AGENTS.md`
580
+ 2. **Move skills**: `.claude/skills/` → `.agents/skills/`
581
+ 3. **Update syntax**: `/skill-name` → `$skill-name`
582
+ 4. **Convert settings**: `settings.json` → `config.toml`
583
+ 5. **Register MCP**: `codex mcp add claude-flow -- npx claude-flow mcp start`
584
+
585
+ ### Dual Mode Alternative
586
+
587
+ Instead of migrating, use dual mode to support both:
588
+
589
+ ```bash
590
+ npx claude-flow@alpha init --dual
591
+ ```
592
+
593
+ This keeps both `CLAUDE.md` and `AGENTS.md` in sync.
594
+
595
+ </details>
596
+
597
+ ---
598
+
599
+ <details>
600
+ <summary><b>Troubleshooting</b></summary>
601
+
602
+ ### MCP Not Working
603
+
604
+ ```bash
605
+ # Check if registered
606
+ codex mcp list
607
+
608
+ # Re-register
609
+ codex mcp remove claude-flow
610
+ codex mcp add claude-flow -- npx claude-flow mcp start
611
+
612
+ # Test connection
613
+ npx claude-flow mcp test
614
+ ```
615
+
616
+ ### Memory Search Returns Empty
617
+
618
+ ```bash
619
+ # Initialize memory database
620
+ npx claude-flow memory init --force
621
+
622
+ # Check if entries exist
623
+ npx claude-flow memory list
624
+
625
+ # Manually add a test pattern
626
+ npx claude-flow memory store --key "test" --value "test pattern" --namespace patterns
627
+ ```
628
+
629
+ ### Skills Not Loading
630
+
631
+ ```bash
632
+ # Verify skill directory
633
+ ls -la .agents/skills/
634
+
635
+ # Check config.toml for skill registration
636
+ cat .agents/config.toml | grep skills
637
+
638
+ # Rebuild skills
639
+ npx claude-flow@alpha init --codex --force
640
+ ```
641
+
642
+ ### Vector Search Slow
643
+
644
+ ```bash
645
+ # Check HNSW index
646
+ npx claude-flow memory stats
647
+
648
+ # Rebuild index
649
+ npx claude-flow memory optimize --rebuild-index
650
+ ```
651
+
652
+ </details>
653
+
654
+ ---
655
+
287
656
  ## Related Packages
288
657
 
289
- - [@claude-flow/cli](https://www.npmjs.com/package/@claude-flow/cli) - Main CLI
290
- - [claude-flow](https://www.npmjs.com/package/claude-flow) - Umbrella package
291
- - [@claude-flow/memory](https://www.npmjs.com/package/@claude-flow/memory) - AgentDB memory with vector search
292
- - [@claude-flow/security](https://www.npmjs.com/package/@claude-flow/security) - Security module
658
+ | Package | Description |
659
+ |---------|-------------|
660
+ | [@claude-flow/cli](https://www.npmjs.com/package/@claude-flow/cli) | Main CLI (26 commands, 140+ subcommands) |
661
+ | [claude-flow](https://www.npmjs.com/package/claude-flow) | Umbrella package |
662
+ | [@claude-flow/memory](https://www.npmjs.com/package/@claude-flow/memory) | AgentDB with HNSW vector search |
663
+ | [@claude-flow/security](https://www.npmjs.com/package/@claude-flow/security) | Security module |
293
664
 
294
665
  ## License
295
666
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@claude-flow/codex",
3
- "version": "3.0.0-alpha.2",
3
+ "version": "3.0.0-alpha.3",
4
4
  "description": "Codex CLI integration for Claude Flow - OpenAI Codex platform adapter",
5
5
  "type": "module",
6
6
  "main": "./dist/index.js",