@claude-flow/codex 3.0.0-alpha.4 → 3.0.0-alpha.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 +52 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,6 +1,29 @@
|
|
|
1
1
|
# @claude-flow/codex
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
<p align="center">
|
|
4
|
+
<strong>OpenAI Codex CLI Adapter for Claude Flow V3</strong><br/>
|
|
5
|
+
<em>Self-learning multi-agent orchestration following the <a href="https://agentics.org">Agentics Foundation</a> standard</em>
|
|
6
|
+
</p>
|
|
7
|
+
|
|
8
|
+
<p align="center">
|
|
9
|
+
<a href="https://www.npmjs.com/package/@claude-flow/codex"><img src="https://img.shields.io/npm/v/@claude-flow/codex?label=npm&color=blue" alt="npm version"></a>
|
|
10
|
+
<a href="https://github.com/ruvnet/claude-flow"><img src="https://img.shields.io/badge/license-MIT-green" alt="license"></a>
|
|
11
|
+
<a href="https://agentics.org"><img src="https://img.shields.io/badge/standard-Agentics-purple" alt="Agentics Standard"></a>
|
|
12
|
+
</p>
|
|
13
|
+
|
|
14
|
+
---
|
|
15
|
+
|
|
16
|
+
## Why @claude-flow/codex?
|
|
17
|
+
|
|
18
|
+
Transform OpenAI Codex CLI into a **self-improving AI development system**. While Codex executes code, claude-flow orchestrates, coordinates, and **learns from every interaction**.
|
|
19
|
+
|
|
20
|
+
| Traditional Codex | With Claude-Flow |
|
|
21
|
+
|-------------------|------------------|
|
|
22
|
+
| Stateless execution | Persistent vector memory |
|
|
23
|
+
| Single-agent | Multi-agent swarms (up to 15) |
|
|
24
|
+
| Manual coordination | Automatic orchestration |
|
|
25
|
+
| No learning | Self-learning patterns (HNSW) |
|
|
26
|
+
| One platform | Dual-mode (Claude Code + Codex) |
|
|
4
27
|
|
|
5
28
|
## Key Concept: Execution Model
|
|
6
29
|
|
|
@@ -13,6 +36,30 @@ OpenAI Codex CLI adapter for Claude Flow V3. Enables multi-agent orchestration w
|
|
|
13
36
|
|
|
14
37
|
**Codex does the work. Claude-flow coordinates and learns.**
|
|
15
38
|
|
|
39
|
+
### The Self-Learning Loop
|
|
40
|
+
|
|
41
|
+
```
|
|
42
|
+
┌──────────────┐
|
|
43
|
+
│ SEARCH │ ──→ Find relevant patterns from past successes
|
|
44
|
+
│ memory │
|
|
45
|
+
└──────┬───────┘
|
|
46
|
+
│
|
|
47
|
+
┌──────▼───────┐
|
|
48
|
+
│ COORDINATE │ ──→ Initialize swarm, spawn specialized agents
|
|
49
|
+
│ swarm │
|
|
50
|
+
└──────┬───────┘
|
|
51
|
+
│
|
|
52
|
+
┌──────▼───────┐
|
|
53
|
+
│ EXECUTE │ ──→ Codex writes code, runs commands
|
|
54
|
+
│ codex │
|
|
55
|
+
└──────┬───────┘
|
|
56
|
+
│
|
|
57
|
+
┌──────▼───────┐
|
|
58
|
+
│ STORE │ ──→ Save successful patterns for future use
|
|
59
|
+
│ memory │
|
|
60
|
+
└──────────────┘
|
|
61
|
+
```
|
|
62
|
+
|
|
16
63
|
## Quick Start
|
|
17
64
|
|
|
18
65
|
```bash
|
|
@@ -26,6 +73,8 @@ npx claude-flow@alpha init --codex --full
|
|
|
26
73
|
npx claude-flow@alpha init --dual
|
|
27
74
|
```
|
|
28
75
|
|
|
76
|
+
**That's it!** The MCP server is auto-registered, skills are installed, and your project is ready for self-learning development.
|
|
77
|
+
|
|
29
78
|
---
|
|
30
79
|
|
|
31
80
|
<details>
|
|
@@ -41,6 +90,8 @@ npx claude-flow@alpha init --dual
|
|
|
41
90
|
| **Auto-Registration** | MCP server registered during init |
|
|
42
91
|
| **HNSW Search** | 150x-12,500x faster pattern matching |
|
|
43
92
|
| **Self-Learning** | Learn from successes, remember patterns |
|
|
93
|
+
| **GPT-5.3 Support** | Optimized for latest OpenAI models |
|
|
94
|
+
| **Neural Training** | Train patterns with SONA architecture |
|
|
44
95
|
|
|
45
96
|
</details>
|
|
46
97
|
|