@defai.digital/automatosx 5.6.1 → 5.6.3
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.
- package/CHANGELOG.md +4 -20
- package/README.md +154 -75
- package/dist/index.js +566 -487
- package/package.json +1 -3
package/CHANGELOG.md
CHANGED
|
@@ -2,26 +2,6 @@
|
|
|
2
2
|
|
|
3
3
|
All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
|
|
4
4
|
|
|
5
|
-
## [5.6.1](https://github.com/defai-digital/automatosx/compare/v5.6.0...v5.6.1) (2025-10-17)
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
### Features
|
|
9
|
-
|
|
10
|
-
* **claude-code:** enable Claude Agent SDK by default with CLI fallback
|
|
11
|
-
- Use `@anthropic-ai/claude-agent-sdk` for 77% lower latency
|
|
12
|
-
- Automatic fallback to CLI if SDK fails
|
|
13
|
-
- Native streaming support via AsyncGenerator
|
|
14
|
-
- Configuration: `useAgentSDK: true`, `fallbackToCLI: true` (defaults)
|
|
15
|
-
|
|
16
|
-
|
|
17
|
-
### Bug Fixes
|
|
18
|
-
|
|
19
|
-
* **claude-code:** remove recursion restriction for Claude Code provider
|
|
20
|
-
- Remove Claude Code environment detection that prevented claude-code provider usage
|
|
21
|
-
- Restore v3.0+ behavior: allow Claude calling Claude without restrictions
|
|
22
|
-
- Users confirmed no recursion issues in production since v3.0
|
|
23
|
-
|
|
24
|
-
|
|
25
5
|
## [5.6.0](https://github.com/defai-digital/automatosx/compare/v5.5.2...v5.6.0) (2025-10-17)
|
|
26
6
|
|
|
27
7
|
|
|
@@ -38,6 +18,10 @@ All notable changes to this project will be documented in this file. See [standa
|
|
|
38
18
|
- 161/163 parallel execution tests passing (99.0%)
|
|
39
19
|
- Phase 1-7 complete: Foundation, Engine, Integration, Observability, Testing, Beta, GA
|
|
40
20
|
|
|
21
|
+
* **claude-code:** fix claude-code provider recursion in Claude Code environment
|
|
22
|
+
- Prevent infinite recursion when running in Claude Code
|
|
23
|
+
- Add environment detection and fallback logic
|
|
24
|
+
|
|
41
25
|
|
|
42
26
|
### Bug Fixes
|
|
43
27
|
|
package/README.md
CHANGED
|
@@ -7,121 +7,200 @@ AutomatosX is a CLI-first orchestration tool that transforms stateless AI assist
|
|
|
7
7
|
[](https://www.npmjs.com/package/@defai.digital/automatosx)
|
|
8
8
|
[](LICENSE)
|
|
9
9
|
[](https://www.typescriptlang.org/)
|
|
10
|
-
[](#)
|
|
11
11
|
[](https://www.apple.com/macos)
|
|
12
12
|
[](https://www.microsoft.com/windows)
|
|
13
13
|
[](https://ubuntu.com)
|
|
14
14
|
|
|
15
|
-
**Status**: ✅ Production Ready · **v5.6.
|
|
15
|
+
**Status**: ✅ Production Ready · **v5.6.3** · October 2025
|
|
16
16
|
|
|
17
17
|
---
|
|
18
18
|
|
|
19
|
-
## 🚀
|
|
19
|
+
## 🚀 Get Started in 3 Steps
|
|
20
20
|
|
|
21
21
|
1. **Install AutomatosX:**
|
|
22
22
|
```bash
|
|
23
23
|
npm install -g @defai.digital/automatosx
|
|
24
24
|
```
|
|
25
25
|
|
|
26
|
-
2. **Initialize Your Project
|
|
26
|
+
2. **Initialize Your Project:**
|
|
27
27
|
```bash
|
|
28
28
|
cd your-project-folder
|
|
29
29
|
ax init
|
|
30
|
-
# Follow prompts to set up your default provider (e.g., Gemini, Claude, OpenAI)
|
|
31
30
|
```
|
|
32
31
|
|
|
33
32
|
3. **Run Your First Agent:**
|
|
34
33
|
```bash
|
|
35
|
-
# Use natural language in
|
|
36
|
-
"work with ax agent to design a REST API for user management"
|
|
34
|
+
# Use natural language in Claude Code
|
|
35
|
+
"please work with ax agent to design a REST API for user management"
|
|
37
36
|
|
|
38
37
|
# Or run directly in your terminal
|
|
39
38
|
ax run product "Design a REST API for user management"
|
|
40
39
|
```
|
|
41
40
|
|
|
42
|
-
[➡️ **Full
|
|
41
|
+
[➡️ **Full Quick Start Guide**](docs/guide/quick-start.md) | [**Installation Details**](docs/guide/installation.md)
|
|
43
42
|
|
|
44
43
|
---
|
|
45
44
|
|
|
46
|
-
##
|
|
45
|
+
## 💡 Why AutomatosX? The End of AI Amnesia
|
|
46
|
+
|
|
47
|
+
### The Problem: Stateless AI is Inefficient
|
|
48
|
+
|
|
49
|
+
Standard AI assistants suffer from digital amnesia. They have no memory of past conversations, forcing you to repeat context, re-explain requirements, and manually coordinate every single task. This is slow, repetitive, and inefficient.
|
|
50
|
+
|
|
51
|
+
- ❌ **No Long-Term Memory**: Every session starts from zero.
|
|
52
|
+
- ❌ **Constant Repetition**: You explain the same architecture and requirements over and over.
|
|
53
|
+
- ❌ **Manual Coordination**: You are the single point of failure for orchestrating tasks.
|
|
54
|
+
- ❌ **Knowledge is Lost**: Valuable insights and decisions disappear forever.
|
|
55
|
+
|
|
56
|
+
### The Solution: A Persistent, Collaborative AI Workforce
|
|
57
|
+
|
|
58
|
+
AutomatosX gives your AI a permanent brain and a team of specialists who learn and collaborate.
|
|
47
59
|
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
| **Persistent Memory** | A local SQLite FTS5 database gives agents long-term memory, enabling context-aware, sub-millisecond responses at zero cost. |
|
|
55
|
-
| **Multi-Agent Orchestration** | Delegate high-level goals to a coordinator agent, which then plans and orchestrates a team of specialists to achieve the objective. |
|
|
56
|
-
| **Provider Agnostic** | Full support for Claude, Gemini, and OpenAI, allowing you to choose the best provider for each task or agent. |
|
|
57
|
-
| **100% Local & Private** | Your data, memory, and configurations stay on your machine. No cloud services, no data privacy concerns. |
|
|
60
|
+
- ✅ **Persistent Memory**: Agents remember everything. A local, zero-cost SQLite FTS5 database enables sub-millisecond context retrieval.
|
|
61
|
+
- ✅ **Autonomous Delegation**: Agents intelligently delegate tasks to each other, creating workflows that run on their own.
|
|
62
|
+
- ✅ **Context on Autopilot**: Agents automatically get the context they need from past conversations. Never repeat yourself again.
|
|
63
|
+
- ✅ **A Team That Learns**: Your AI team gets smarter and more effective with every task, building a shared knowledge base over time.
|
|
64
|
+
|
|
65
|
+
**The result? You save hours per week, produce higher-quality work, and build a system that grows more valuable with every interaction.**
|
|
58
66
|
|
|
59
67
|
---
|
|
60
68
|
|
|
61
|
-
##
|
|
62
|
-
|
|
63
|
-
AutomatosX
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
69
|
+
## 🧠 Core Feature: Persistent Memory
|
|
70
|
+
|
|
71
|
+
AutomatosX remembers every conversation, decision, and piece of code automatically. This knowledge is instantly searchable and injected into future tasks, ensuring perfect context every time.
|
|
72
|
+
|
|
73
|
+
### How It Works
|
|
74
|
+
|
|
75
|
+
```bash
|
|
76
|
+
# 1. A task is completed and automatically saved to memory.
|
|
77
|
+
ax run product "Design a calculator with add/subtract features"
|
|
78
|
+
# → Task and response are indexed in the local SQLite FTS5 database.
|
|
79
|
+
|
|
80
|
+
# 2. A related task is run later.
|
|
81
|
+
ax run backend "Implement the calculator"
|
|
82
|
+
# → Memory automatically finds the "calculator" design spec from the previous step.
|
|
83
|
+
# → The backend agent receives the design and can start work immediately.
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
- **Technology**: SQLite with FTS5 for fast, local full-text search.
|
|
87
|
+
- **Speed**: < 1ms search, even with thousands of entries.
|
|
88
|
+
- **Cost**: $0. No embedding APIs, no cloud services.
|
|
89
|
+
- **Privacy**: 100% local. Your data never leaves your machine.
|
|
90
|
+
|
|
91
|
+
[➡️ **Learn More: Memory System Guide**](docs/guide/agent-communication.md)
|
|
84
92
|
|
|
85
93
|
---
|
|
86
94
|
|
|
87
|
-
##
|
|
88
|
-
|
|
89
|
-
AutomatosX
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
-
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
|
|
95
|
+
## 🤝 Core Feature: Multi-Agent Orchestration
|
|
96
|
+
|
|
97
|
+
Stop micromanaging. With AutomatosX, you can give a high-level goal to one agent, and it will create a plan, delegate tasks, and orchestrate a team of specialists to get the job done.
|
|
98
|
+
|
|
99
|
+
### How It Works
|
|
100
|
+
|
|
101
|
+
```typescript
|
|
102
|
+
// 1. You give a high-level task to a coordinator agent.
|
|
103
|
+
ax run product "Build a complete user authentication feature"
|
|
104
|
+
|
|
105
|
+
// 2. The Product agent creates a plan and delegates to other agents.
|
|
106
|
+
/*
|
|
107
|
+
"I'll design the auth system with JWT and OAuth2.
|
|
108
|
+
|
|
109
|
+
@backend Please implement the JWT authentication API based on this design.
|
|
110
|
+
@security Please audit the implementation for security vulnerabilities."
|
|
111
|
+
*/
|
|
112
|
+
|
|
113
|
+
// 3. AutomatosX executes the plan automatically.
|
|
114
|
+
// - The backend agent receives the spec and implements the API.
|
|
115
|
+
// - The security agent receives the spec and the code, then performs an audit.
|
|
116
|
+
// - Results are aggregated and returned.
|
|
107
117
|
```
|
|
108
118
|
|
|
119
|
+
- **Natural Language Delegation**: Use simple `@mention` syntax to delegate.
|
|
120
|
+
- **Autonomous Workflows**: Agents work in parallel to complete goals faster.
|
|
121
|
+
- **Full Transparency**: The entire delegation chain is tracked and logged.
|
|
122
|
+
|
|
123
|
+
[➡️ **Learn More: Multi-Agent Orchestration Guide**](docs/guide/multi-agent-orchestration.md)
|
|
124
|
+
|
|
109
125
|
---
|
|
110
126
|
|
|
111
|
-
##
|
|
127
|
+
## 🎭 16+ Specialized Agents
|
|
128
|
+
|
|
129
|
+
AutomatosX comes with a pre-built team of 16+ agents, each with a specific role and expertise. This ensures the right specialist is always available for the task at hand.
|
|
130
|
+
|
|
131
|
+
- **Backend** (API design, databases)
|
|
132
|
+
- **Frontend** (UI/UX, components)
|
|
133
|
+
- **Fullstack** (End-to-end development)
|
|
134
|
+
- **Mobile** (iOS/Android development)
|
|
135
|
+
- **DevOps** (CI/CD, infrastructure)
|
|
136
|
+
- **Security** (Audits, threat modeling)
|
|
137
|
+
- **Data Science** (ML models, analysis)
|
|
138
|
+
- **Data** (ETL, SQL, modeling)
|
|
139
|
+
- **Quality** (Testing, code reviews)
|
|
140
|
+
- **Design** (UX research, wireframes)
|
|
141
|
+
- **Writer** (Documentation, reports)
|
|
142
|
+
- **Creative Marketer** (Content strategy)
|
|
143
|
+
- **Product** (Roadmaps, strategy)
|
|
144
|
+
- **CTO** (Technical strategy)
|
|
145
|
+
- **CEO** (Business leadership)
|
|
146
|
+
- **Researcher** (Feasibility studies)
|
|
147
|
+
|
|
148
|
+
**Governance**: Agents have clear roles, permissions, and delegation limits (`maxDelegationDepth`) to ensure efficient and safe collaboration while preventing infinite loops.
|
|
149
|
+
|
|
150
|
+
[➡️ **See the Full Agent Directory**](examples/AGENTS_INFO.md)
|
|
151
|
+
|
|
152
|
+
---
|
|
153
|
+
|
|
154
|
+
## 🚀 Two Ways to Use AutomatosX
|
|
155
|
+
|
|
156
|
+
### 1. Claude Code Integration (Recommended)
|
|
157
|
+
|
|
158
|
+
Use natural language to collaborate with agents directly within your editor. Claude Code acts as an intelligent coordinator, providing project context and validating results.
|
|
159
|
+
|
|
160
|
+
```
|
|
161
|
+
# Let Claude Code think, plan, and coordinate
|
|
162
|
+
"please work with ax agent to implement user authentication"
|
|
163
|
+
"please work with ax agent to refactor this module with best practices"
|
|
164
|
+
```
|
|
165
|
+
|
|
166
|
+
For simple, direct tasks, use slash commands: `/ax:agent backend, write a function to validate emails`.
|
|
167
|
+
|
|
168
|
+
### 2. Terminal/CLI Mode (For Power Users)
|
|
169
|
+
|
|
170
|
+
Run agents directly from your terminal for scripting, automation, and CI/CD pipelines.
|
|
171
|
+
|
|
172
|
+
```bash
|
|
173
|
+
# Run a multi-agent workflow from your command line
|
|
174
|
+
ax run product "Design REST API for users"
|
|
175
|
+
ax run backend "Implement the API" # Auto-receives design from memory
|
|
176
|
+
ax run quality "Write tests for the API" # Auto-receives design + implementation
|
|
177
|
+
```
|
|
178
|
+
|
|
179
|
+
[➡️ **Read the Terminal Mode Guide**](docs/guide/terminal-mode.md)
|
|
180
|
+
|
|
181
|
+
---
|
|
182
|
+
|
|
183
|
+
## ✨ Key Features
|
|
184
|
+
|
|
185
|
+
| Feature | Traditional AI Chat | Claude Code | AutomatosX |
|
|
186
|
+
|---|---|---|---|
|
|
187
|
+
| **Long-Term Memory** | ❌ No | ❌ No | ✅ **Yes (SQLite FTS5, <1ms)** |
|
|
188
|
+
| **Multi-Agent System** | ❌ No | ❌ No | ✅ **Yes (16+ specialized agents)** |
|
|
189
|
+
| **Autonomous Delegation** | ❌ No | ❌ No | ✅ **Yes (Automatic workflows)** |
|
|
190
|
+
| **Context Retention** | Manual Copy-Paste | Session Only | ✅ **Persistent & Automatic** |
|
|
191
|
+
| **Knowledge Sharing** | ❌ No | ❌ No | ✅ **Yes (Across all agents)** |
|
|
192
|
+
| **Privacy** | Cloud-Based | Claude Servers | ✅ **100% Local** |
|
|
193
|
+
| **Cost** | Subscription | Included | ✅ **$0 (No API calls for memory)** |
|
|
194
|
+
|
|
195
|
+
---
|
|
112
196
|
|
|
113
|
-
|
|
114
|
-
|---|---|
|
|
115
|
-
| `ax init` | Initializes a new AutomatosX project and creates the configuration structure. |
|
|
116
|
-
| `ax run <agent> "[prompt]"` | Runs a specific agent with a given task prompt. |
|
|
117
|
-
| `ax agent <list|info>` | Lists all available agents or shows details for a specific agent. |
|
|
118
|
-
| `ax memory <search|clear>` | Searches the agent memory or clears all entries. |
|
|
119
|
-
| `ax status` | Displays the current configuration and project status. |
|
|
120
|
-
| `ax update` | Checks for and installs updates to the AutomatosX tool. |
|
|
121
|
-
| `ax list` | Lists available agents, teams, and abilities. |
|
|
122
|
-
| `ax clear` | Clears logs, cache, or other temporary files. |
|
|
197
|
+
## 📚 Documentation
|
|
123
198
|
|
|
124
|
-
[
|
|
199
|
+
- **[Quick Start Guide](docs/guide/quick-start.md)**
|
|
200
|
+
- **[Core Concepts](docs/guide/core-concepts.md)**
|
|
201
|
+
- **[Full CLI Command Reference](docs/reference/cli-commands.md)**
|
|
202
|
+
- **[Agent Directory](examples/AGENTS_INFO.md)**
|
|
203
|
+
- **[Troubleshooting Guide](TROUBLESHOOTING.md)**
|
|
125
204
|
|
|
126
205
|
---
|
|
127
206
|
|
|
@@ -137,4 +216,4 @@ AutomatosX is an open-source project. We welcome contributions!
|
|
|
137
216
|
|
|
138
217
|
## 📄 License
|
|
139
218
|
|
|
140
|
-
AutomatosX is [Apache 2.0 licensed](LICENSE).
|
|
219
|
+
AutomatosX is [Apache 2.0 licensed](LICENSE).
|