agent-orcha 0.0.1 → 0.0.2

package/README.md

@@ -1,6 +1,21 @@
+<p align="center">
+  <img src="docs/assets/images/logo.png" alt="Agent Orcha Logo" width="300">
+</p>
+
 # Agent Orcha
 
-A TypeScript framework for building and orchestrating multi-agent AI systems with LangChain, Model Context Protocol (MCP), and vector store integration.
+Agent Orcha is a declarative framework designed to build, manage, and scale multi-agent AI systems with ease. It combines the flexibility of TypeScript with the simplicity of YAML to orchestrate complex workflows, manage diverse tools via MCP, and integrate semantic search seamlessly. Built for developers and operators who demand reliability, extensibility, and clarity in their AI operations.
+
+## Why Agent Orcha?
+
+- **Declarative AI**: Define agents, workflows, and infrastructure in clear, version-controlled YAML files. No more spaghetti code.
+- **Model Agnostic**: Seamlessly swap between OpenAI, Gemini, Anthropic, or local LLMs (Ollama, LM Studio) without rewriting logic.
+- **Universal Tooling**: Leverage the **Model Context Protocol (MCP)** to connect agents to any external service, API, or database instantly.
+- **RAG Native**: Built-in vector store integration (Chroma, Memory) makes semantic search and knowledge retrieval a first-class citizen.
+- **Robust Workflow Engine**: Orchestrate complex multi-agent sequences with parallel execution, conditional logic, dynamic input interpolation, and state management.
+- **Production Ready**: Includes a high-performance Fastify REST API, Server-Sent Events (SSE) for real-time streaming, and comprehensive logging.
+- **Developer Experience**: Fully typed interfaces, intuitive CLI tooling, and a modular architecture designed for rapid iteration from prototype to production.
+- **Extensible Functions**: Drop in simple JavaScript functions to extend agent capabilities with zero boilerplate.
 
 ## Overview
 
@@ -12,6 +27,11 @@ Agent Orcha enables you to:
 - **Connect MCP servers** to extend agent capabilities with external tools
 - **Create local Functions** give your agents the ability to call your own custom code
 
+### Alpha Status and Security Notice
+
+**This project is currently in ALPHA state.** No security precautions have been implemented yet. This software should **ALWAYS** be deployed behind a firewall without open access to its APIs. It is designed for **internal use only** and should never be exposed directly to the public internet.
+
+
 ## Usage
 - **Use as is** check out and run
 - **Use as a library** in your TypeScript/JavaScript projects
@@ -882,36 +902,6 @@ The workflow flow diagram visualizes:
 - Tool badges (MCP servers, vector databases)
 - Input/output nodes
 
-## Publishing to npm
-
-To publish this package to npm:
-
-1. **Build the package:**
-```bash
-npm run build
-```
-
-2. **Update version in package.json:**
-```bash
-npm version patch  # or minor, or major
-```
-
-3. **Publish to npm:**
-```bash
-npm publish
-```
-
-The package includes:
-- Compiled TypeScript code (`dist/`)
-- CLI executable (`bin/cli.js`)
-- Template files for `init` command (`templates/`)
-- Web UI (`public/`)
-- Type definitions
-
-Users can then:
-- Use as CLI: `npx agent-orcha init`
-- Install as library: `npm install agent-orcha`
-
 ## License
 
 MIT

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-orcha",
-  "version": "0.0.1",
+  "version": "0.0.2",
   "description": "TypeScript Agentic Orchestration http server and framework for building multi-agent workflows with MCP tools and vector stores",
   "keywords": [
     "ai",

package/dist/templates/vectors/example-chroma.vector.yaml

@@ -1,43 +0,0 @@
-name: example-chroma
-description: Example vector store using Chroma for persistent storage
-
-source:
-  type: directory
-  path: vectors/sample-data
-  pattern: "*.txt"
-  recursive: false
-
-loader:
-  type: text
-
-splitter:
-  type: character
-  chunkSize: 1000
-  chunkOverlap: 200
-
-embedding: default  # References embedding config in llm.json
-
-store:
-  type: chroma
-  options:
-    # Path where Chroma will store data (relative to project root)
-    # Default: .chroma
-    path: .chroma
-
-    # Collection name for this vector store
-    # Default: uses the vector store name
-    collectionName: example-chroma
-
-    # Chroma server URL
-    # Default: http://localhost:8000
-    # Note: You need to run Chroma server separately
-    # Docker: docker run -p 8000:8000 chromadb/chroma
-    url: http://localhost:8000
-
-search:
-  defaultK: 4
-  scoreThreshold: 0.2
-
-metadata:
-  category: example
-  persistence: chroma