@praveencs/agent 0.7.3 → 0.7.5

package/README.md

@@ -185,6 +185,14 @@ Want to understand how this agent works under the hood? Check out our 5-part arc
 4.  [**Memory & Context**](docs/articles/04-memory-persistence.md) - SQLite & Vector storage.
 5.  [**Self-Improvement**](docs/articles/05-self-improvement.md) - Metrics & The Auto-Fixer.
 
+## 🔮 What's Next?
+
+We are just getting started. The future includes **Multi-Agent Swarms**, **Sandboxed Execution**, and **Voice Interfaces**.
+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.
+
+### Comparisons
+- [**vs OpenClaw**](docs/comparisons/openclaw.md) - How we differ from other AI OS projects.
+
 ## 🤝 Contributing
 
 We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for details on how to set up your development environment.

package/ROADMAP.md

@@ -0,0 +1,35 @@
+# 🛣️ Roadmap: The Future of @praveencs/agent
+
+We have built a robust autonomous agent runtime (`v0.7.x`). But this is just the beginning.
+Here is our vision for the next major milestones.
+
+## Phase 1: Robustness & Safety (Current Focus)
+- [ ] **Sandboxed Execution**: Run all shell skills inside ephemeral Docker containers to prevent accidental system damage.
+- [ ] **Permission Scopes**: Fine-grained access control (e.g., "Allow read access to `/project` but write access only to `/project/src`").
+- [ ] **Secrets Management**: Secure, encrypted storage for API keys integrated with system keychains.
+
+## Phase 2: Multi-Agent Collaboration (The Swarm)
+- [ ] **Agent-to-Agent Protocol**: Define a standard schema for agents to send messages and delegate tasks to each other.
+- [ ] **Specialized Personas**:
+    - `Coder Agent`: Writes and tests code.
+    - `Reviewer Agent`: Critiques pull requests.
+    - `Architect Agent`: High-level system design.
+- [ ] **Orchestrator**: A master process that spins up specialized agents for a complex goal.
+
+## Phase 3: Multimodal Interfaces
+- [ ] **Voice Interface**: Speak to your agent ("Deploy this to prod") and hear responses.
+- [ ] **Vision Capabilities**: Allow the agent to "see" your screen or read images (e.g., "Fix the CSS on this screenshot").
+- [ ] **IDE Integration**: VS Code extension to have the agent live in your editor sidebar.
+
+## Phase 4: The Agent Cloud
+- [ ] **Skill Hub**: A public registry (npm-style) to share and install community skills.
+- [ ] **Remote Execution**: Run the heavy agent logic on a cloud server while controlling it from your laptop.
+- [ ] **Web Dashboard**: Real-time visualization of agent thought processes, memory graph, and task plans.
+
+## 🤝 Join the Mission
+This is an open-source journey. We need help with:
+- Writing new Skills (see `docs/articles/03-skill-execution.md`)
+- Improving the Planner prompt engineering
+- Building the Web Dashboard
+
+Submit a PR and let's build the future of work, together.

package/dist/src/cli/index.js

@@ -18,7 +18,7 @@ export function createCLI() {
     program
         .name('agent')
         .description('Agent Runtime — autonomous, goal-oriented AI agent with skills, plans, memory, and permissioned tools')
-        .version('0.7.3')
+        .version('0.7.5')
         .option('--verbose', 'Enable verbose output')
         .option('--no-color', 'Disable colored output')
         .option('--config <path>', 'Path to config file');

package/docs/comparisons/openclaw.md

@@ -0,0 +1,60 @@
+# Comparison: @praveencs/agent vs OpenClaw
+
+This document compares `@praveencs/agent` (this project) with [OpenClaw](https://github.com/openclaw/openclaw), a popular open-source AI operating system.
+
+## 1. Core Philosophy
+
+| Feature | @praveencs/agent | OpenClaw |
+|---|---|---|
+| **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. |
+| **Interaction** | **CLI-First.** You give it a goal, and it works silently. | **Chat-First.** You talk to it via various messaging platforms. |
+| **Persona** | A Junior Developer / Project Manager. | A Personal Assistant / OS Interface. |
+
+## 2. Architecture
+
+### @praveencs/agent
+- **Monolithic CLI/Daemon**: A single TypeScript application that runs locally.
+- **Daemon Loop**: A background process that polls a queue of tasks.
+- **Planner-Executor Split**: Explicit "Brain" (Goal Decomposition) and "Body" (Task Execution) separation.
+- **Database**: Uses `better-sqlite3` for high-performance, structured local storage.
+
+### OpenClaw
+- **Gateway Architecture**: A Hub-and-Spoke model with a central Gateway managing WebSocket connections to various "Channels" (Telegram, Discord).
+- **Service Mesh**: Decouples the "Brain" from the inputs/outputs via adapters.
+- **Markdown-First Memory**: Stores state and memory as flat Markdown files on disk.
+
+## 3. Capabilities & Skills
+
+| | @praveencs/agent | OpenClaw |
+|---|---|---|
+| **Skill Definition** | **Prompt-as-Code.** Skills are simple `.md` files with natural language instructions. | **Plugin System.** Code-based plugins to extend functionality. |
+| **Execution** | **Shell-Native.** Executes command-line tools natively (git, docker, npm). | **Sandbox-Native.** Heavily focuses on browser automation and secure sandboxing. |
+| **Self-Improvement** | **Built-in Auto-Fixer.** Monitors success rates and rewrites broken skills automatically. | **Manual/Plugin.** Relies on users or plugin updates. |
+
+## 4. Memory Implementation
+
+### @praveencs/agent
+- **Hybrid Storage**: Uses **SQLite** for structured data (tasks, metrics) and **Vector/FTS5** layers for semantic search.
+- **Why?**: Faster retrieval for large codebases and project histories. Allows complex queries ("Select tasks from 2 days ago related to 'database'").
+
+### OpenClaw
+- **File-System Storage**: Stores conversations and memories as Markdown files.
+- **Why?**: "Unix philosophy" - easy to read/edit by humans, no database dependencies.
+
+## 5. Use Case Recommendation
+
+**Choose @praveencs/agent if:**
+- You want an AI to **write code, manage servers, or automate dev workflows**.
+- You prefer a command-line interface.
+- You need structured planning and long-term project management.
+- You want a system that improves itself over time.
+
+**Choose OpenClaw if:**
+- You want to **chat with your AI** via WhatsApp/Discord.
+- You need a personal assistant to manage emails, calendars, and smart home devices.
+- You prefer storing data in plain text files.
+- You want deep browser automation capabilities.
+
+## Summary
+
+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".

package/package.json

@@ -1,10 +1,11 @@
 {
     "name": "@praveencs/agent",
-    "version": "0.7.3",
+    "version": "0.7.5",
     "files": [
         "dist",
         "bin",
         "README.md",
+        "ROADMAP.md",
         "docs",
         "src/index.d.ts"
     ],