@praveencs/agent 0.7.4 → 0.7.5
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 +3 -0
- package/dist/src/cli/index.js +1 -1
- package/docs/comparisons/openclaw.md +60 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -190,6 +190,9 @@ Want to understand how this agent works under the hood? Check out our 5-part arc
|
|
|
190
190
|
We are just getting started. The future includes **Multi-Agent Swarms**, **Sandboxed Execution**, and **Voice Interfaces**.
|
|
191
191
|
Check out our detailed [**ROADMAP.md**](ROADMAP.md) to see where we are heading and how you can help build the future of autonomous software development.
|
|
192
192
|
|
|
193
|
+
### Comparisons
|
|
194
|
+
- [**vs OpenClaw**](docs/comparisons/openclaw.md) - How we differ from other AI OS projects.
|
|
195
|
+
|
|
193
196
|
## 🤝 Contributing
|
|
194
197
|
|
|
195
198
|
We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for details on how to set up your development environment.
|
package/dist/src/cli/index.js
CHANGED
|
@@ -18,7 +18,7 @@ export function createCLI() {
|
|
|
18
18
|
program
|
|
19
19
|
.name('agent')
|
|
20
20
|
.description('Agent Runtime — autonomous, goal-oriented AI agent with skills, plans, memory, and permissioned tools')
|
|
21
|
-
.version('0.7.
|
|
21
|
+
.version('0.7.5')
|
|
22
22
|
.option('--verbose', 'Enable verbose output')
|
|
23
23
|
.option('--no-color', 'Disable colored output')
|
|
24
24
|
.option('--config <path>', 'Path to config file');
|
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
# Comparison: @praveencs/agent vs OpenClaw
|
|
2
|
+
|
|
3
|
+
This document compares `@praveencs/agent` (this project) with [OpenClaw](https://github.com/openclaw/openclaw), a popular open-source AI operating system.
|
|
4
|
+
|
|
5
|
+
## 1. Core Philosophy
|
|
6
|
+
|
|
7
|
+
| Feature | @praveencs/agent | OpenClaw |
|
|
8
|
+
|---|---|---|
|
|
9
|
+
| **Primary Goal** | **Autonomous Task Execution.** Designed to be a headless "digital employee" that plans and builds software in the background. | **AI Operating System.** Designed to be a "24/7 Jarvis" that integrates with chat apps (Discord, Telegram) and manages your digital life. |
|
|
10
|
+
| **Interaction** | **CLI-First.** You give it a goal, and it works silently. | **Chat-First.** You talk to it via various messaging platforms. |
|
|
11
|
+
| **Persona** | A Junior Developer / Project Manager. | A Personal Assistant / OS Interface. |
|
|
12
|
+
|
|
13
|
+
## 2. Architecture
|
|
14
|
+
|
|
15
|
+
### @praveencs/agent
|
|
16
|
+
- **Monolithic CLI/Daemon**: A single TypeScript application that runs locally.
|
|
17
|
+
- **Daemon Loop**: A background process that polls a queue of tasks.
|
|
18
|
+
- **Planner-Executor Split**: Explicit "Brain" (Goal Decomposition) and "Body" (Task Execution) separation.
|
|
19
|
+
- **Database**: Uses `better-sqlite3` for high-performance, structured local storage.
|
|
20
|
+
|
|
21
|
+
### OpenClaw
|
|
22
|
+
- **Gateway Architecture**: A Hub-and-Spoke model with a central Gateway managing WebSocket connections to various "Channels" (Telegram, Discord).
|
|
23
|
+
- **Service Mesh**: Decouples the "Brain" from the inputs/outputs via adapters.
|
|
24
|
+
- **Markdown-First Memory**: Stores state and memory as flat Markdown files on disk.
|
|
25
|
+
|
|
26
|
+
## 3. Capabilities & Skills
|
|
27
|
+
|
|
28
|
+
| | @praveencs/agent | OpenClaw |
|
|
29
|
+
|---|---|---|
|
|
30
|
+
| **Skill Definition** | **Prompt-as-Code.** Skills are simple `.md` files with natural language instructions. | **Plugin System.** Code-based plugins to extend functionality. |
|
|
31
|
+
| **Execution** | **Shell-Native.** Executes command-line tools natively (git, docker, npm). | **Sandbox-Native.** Heavily focuses on browser automation and secure sandboxing. |
|
|
32
|
+
| **Self-Improvement** | **Built-in Auto-Fixer.** Monitors success rates and rewrites broken skills automatically. | **Manual/Plugin.** Relies on users or plugin updates. |
|
|
33
|
+
|
|
34
|
+
## 4. Memory Implementation
|
|
35
|
+
|
|
36
|
+
### @praveencs/agent
|
|
37
|
+
- **Hybrid Storage**: Uses **SQLite** for structured data (tasks, metrics) and **Vector/FTS5** layers for semantic search.
|
|
38
|
+
- **Why?**: Faster retrieval for large codebases and project histories. Allows complex queries ("Select tasks from 2 days ago related to 'database'").
|
|
39
|
+
|
|
40
|
+
### OpenClaw
|
|
41
|
+
- **File-System Storage**: Stores conversations and memories as Markdown files.
|
|
42
|
+
- **Why?**: "Unix philosophy" - easy to read/edit by humans, no database dependencies.
|
|
43
|
+
|
|
44
|
+
## 5. Use Case Recommendation
|
|
45
|
+
|
|
46
|
+
**Choose @praveencs/agent if:**
|
|
47
|
+
- You want an AI to **write code, manage servers, or automate dev workflows**.
|
|
48
|
+
- You prefer a command-line interface.
|
|
49
|
+
- You need structured planning and long-term project management.
|
|
50
|
+
- You want a system that improves itself over time.
|
|
51
|
+
|
|
52
|
+
**Choose OpenClaw if:**
|
|
53
|
+
- You want to **chat with your AI** via WhatsApp/Discord.
|
|
54
|
+
- You need a personal assistant to manage emails, calendars, and smart home devices.
|
|
55
|
+
- You prefer storing data in plain text files.
|
|
56
|
+
- You want deep browser automation capabilities.
|
|
57
|
+
|
|
58
|
+
## Summary
|
|
59
|
+
|
|
60
|
+
While OpenClaw builds a bridge between AI and *Communication Channels*, `@praveencs/agent` builds a bridge between AI and *Work Execution*. We are focused on the "Agent as a Worker" paradigm, whereas OpenClaw focuses on "Agent as an Interface".
|