Agen V2.0.0 - Swarm AI CLI

🚀 Agen V2.0.0 - Swarm AI Architecture Release

Welcome to the official 2.0 release of Agen! This release completely rebuilds the core engine from the ground up, transforming the CLI from a simple text interface into a fully autonomous, multi-agent AI software engineer.

✨ Major Features

• Multi-Agent Swarm Orchestration (backend.swarm): The main agent can now spawn independent, asynchronous clone subagents in the background using the invoke_subagent tool to tackle multi-threaded software tasks concurrently.
• Model Context Protocol (MCP): Dynamic integration with the MCP registry. The agent can instantly boot up servers like Tavily, Puppeteer, GitHub, or Postgres and execute external tools natively.
• RAG Semantic Memory: Replaced simple file-attachments with a local ChromaDB vector database. Running /index allows the agent to semantically search and recall relevant snippets across your entire codebase.
• Interactive REPL UI (prompt_toolkit & rich): Enjoy beautiful gradient rendering, LaTeX math parsing, native / commands, and intelligent @ file/folder attachment parsing without relying on shell commands.
• Multi-Provider Support: Switch between Cloud mode (Google Gemini) and Local hardware execution (Ollama Llama3/Gemma) instantly via /gemini or /ollama.
• Workspace Security Boundaries (New!): Agents are now strictly sandboxed to your active workspace folder. Any attempt to read, write, or list directories outside this boundary triggers an interactive terminal prompt, granting you manual override control.
• Embedded Autonomous Skills (.agent/): The engine now natively ships with an embedded framework of agent "skills" (secure-scripting, ci-cd, etc.), ensuring all background subagents adhere to strict engineering standards.

📦 Installation

You do not need to install Python to use Agen. The entire engine (including RAG databases and MCP protocols) has been heavily optimized and compiled down to a single ~170MB standalone binary.

The Terminal Way (Recommended):

• Windows: irm https://raw.githubusercontent.com/AmanBanik/Agen/v2-stable/setup.ps1 | iex
• macOS / Linux: curl -sSL https://raw.githubusercontent.com/AmanBanik/Agen/v2-stable/install.sh | bash

The Manual Way:
Simply download the agen.exe binary attached below, drop it in your project folder, and start building!

For contributors, you can clone the repository and run pip install -e . to install it directly into your Python environment.

🛠️ Internal Refinements

• Removed legacy V1 polling limits in favor of Server-Sent Events (SSE) streaming.
• Wiped all hardcoded API keys and implemented secure .env placeholders.
• Integrated a full GitHub Actions CI/CD pipeline for open-source contributions.
• Included a standard CODE_OF_CONDUCT.md for community building.
• Aggressively stripped heavy data-science dependencies (pandas, scipy, cv2) to shrink the Windows binary from 300MB down to 170MB.

v0.2.0 - High-Performance Dual-Engine AI CLI for Windows x64

⚡ Terminal Agent v0.2.0

High-Performance Split-Brain Agentic AI & Development Assistant for Windows x64

We are thrilled to announce the official inaugural release of Terminal Agent (v0.2.0)! Designed with a custom Stealth Hardware Aesthetic and engineered specifically for Windows 64-bit developers, this release introduces a revolutionary Split-Brain Architecture separating asynchronous backend reasoning from instant-start terminal execution.

---

🔥 Highlights & New Features

• 🧠 Dual-Engine LLM Support (Cloud + Offline):
  • Cloud Mode: Flagship integration with Google's gemini-3.5-flash for heavy reasoning/refactoring and gemini-3.1-flash-lite for high-speed file lookups.
  • Offline Local Mode: Native Ollama routing over port 11434. Switch instantly to local offline models (gemma:7b, gemma4, llama3) for unlimited free tokens and private dataset analysis!
• 🔌 14 Model Context Protocol (MCP) Connectors:
  Connect external data silos natively: motherduck (local DuckDB), postgresql, sqlite, bigquery, filesystem, github, docker, puppeteer, tavily, and more!
• 🛠️ 13 Pre-Built Domain Agent Skills:
  Modular engineering standards for Data Science & Deep Learning (EDA, Feature Extraction, Predictive Modeling, PyTorch DL scripting) and Software Engineering (Code Review Loops, PEP 484 style, Custom ADK).
• ⚡ Terminal-Native Workflow:
  • @filepath Syntax: Dynamically inject file contents directly into your prompts (e.g., agen chat "Find bugs in @backend/main.py").
  • Interactive REPL: Control sessions and LLM providers on the fly with /session, /clear, /local, /gemini, and /help.

---

📦 Installation & Setup (Windows x64)

Option 1: Standalone Executable (Recommended for Workstations)

1. Download agen.exe from the Assets below.
2. Place it in your desired folder or add it to your Windows PATH.
3. Open PowerShell or CMD and type: agen --help or agen init --profile ds!

Option 2: PowerShell Web Installer (irm | iex)

For CI/CD and automated developer setup, run in PowerShell:

irm [https://raw.githubusercontent.com/AmanBanik/Agen/main/deploy/install.ps1](https://raw.githubusercontent.com/AmanBanik/Agen/main/deploy/install.ps1) | iex