DA-Forge: Streamlining Declarative Agent Creation for Copilot Notebooks
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
DA-Forge is a Python-based tool by Microsoft designed to automate the creation and deployment of Declarative Agents for Copilot Notebooks. It significantly reduces the manual effort and time required to set up AI assistants with specific grounding references, transforming an 85-minute process into just a few minutes. This tool is essential for developers and researchers working with Copilot Notebooks and Declarative Agents.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
DA-Forge is an innovative open-source tool developed by Microsoft, designed to significantly streamline the creation and deployment of Declarative Agents for Copilot Notebooks. This Python-based utility automates a complex, multi-step process, enabling developers and researchers to ground AI agents with specific references like emails, meetings, files, and webpages in a matter of seconds. It transforms what was previously a time-consuming and error-prone manual task into an efficient, one-command operation.
For more details, visit the official repository: microsoft/da-forge
Why Use It and Key Benefits
The process of creating Declarative Agents as a proxy for Copilot Notebooks for research or development purposes traditionally involves significant manual effort and time. Developers often face challenges such as:
- Manual Manifest Creation: Generating complex manifest files with specific formats can take around 40 minutes.
- Unique ID Extraction: Manually extracting and formatting unique IDs from files, emails, and meetings uploaded as Notebook references can consume another 30 minutes.
- Special Formatting Requirements: Each capability type has its own ID structure and JSON schema, adding to the complexity.
- DA Initiation and Sideloading: Multiple manual steps for agent initiation and sideloading are prone to errors and take about 15 minutes.
Collectively, these steps can amount to approximately 85 minutes per agent, coupled with a high error rate.
DA-Forge provides a robust solution by automating this entire process. By simply extracting the socket JSON from your Copilot Notebook configuration, you can deploy a Declarative Agent in roughly 2 minutes. This drastic reduction in deployment time, from 85 minutes to just 2, makes DA-Forge an invaluable tool.
Key features and benefits include:
- Zero External Dependencies: Built purely with Python's standard library, ensuring minimal overhead and easy integration.
- Automated Manifest Generation: Generates manifest files from templates with automatic GUID generation.
- Smart Capability Injection: Automatically categorizes and injects capabilities, handling both regular and experimental types.
- One-Command Deployment: Simplifies the entire workflow, from creation and revision to zipping and sideloading, into a single command.
- Socket-Based Configuration: Separates grounding data from boilerplate, allowing for cleaner and more manageable configurations.
Installation
To get started with DA-Forge, follow these installation steps.
Prerequisites
- Python 3.10+
- Teams Toolkit CLI for sideloading
Installation Options
Option 1: Install from GitHub (Recommended)
# Install latest release
pip install git+https://github.com/microsoft/da-forge.git
# Or install a specific version
pip install git+https://github.com/microsoft/da-forge.git@v1.0.0
Option 2: Install from Source (for development)
# Clone the repository
git clone https://github.com/microsoft/da-forge.git
cd da-forge
# Install in editable mode
pip install -e .
After installation, the da-forge command will be available globally.
Examples
Here’s how to use DA-Forge to deploy your Declarative Agents.
Step 1: Set up your project
mkdir my-agents
cd my-agents
mkdir sockets
Step 2: Extract and save socket JSON
Detailed instructions for extracting the socket JSON from your Copilot Notebook configuration can be found in the official documentation: docs/capabilities.md.
Save the extracted socket JSON to sockets/my-agent.json.
Step 3: Deploy your agent
da-forge deploy my-agent
The tool will automatically perform the following actions:
- Use bundled templates from the package.
- Create
raw_manifests/with generated manifest files. - Create
zipped_manifests/with the deployment package. - Sideload to Teams (or skip with
--skip-sideload).
Your Declarative Agent will then be deployed to Teams with all the grounding context from your Copilot Notebook.
CLI Commands
Deploy an agent:
da-forge deploy <name> [--description TEXT] [--instruction TEXT] [--skip-sideload]
Examples:
# Basic deployment
da-forge deploy my-copilot
# With custom description and instructions
da-forge deploy my-copilot --description "Email assistant" --instruction "Help with emails"
# Skip sideloading (just create package)
da-forge deploy my-copilot --skip-sideload
List available agents:
da-forge list
This command shows all socket files located in the sockets/ folder.
Links
- Official GitHub Repository: microsoft/da-forge
- Teams Toolkit CLI: Learn more about Teams Toolkit CLI
- Capabilities Documentation: Detailed guide on extracting socket JSON
- Development Documentation: Instructions for development setup, testing, and formatting
- License: MIT License
Related repositories
Similar repositories that may be relevant next.

Curie: Automated and Rigorous Scientific Experimentation with AI Agents
September 12, 2026
Curie is an innovative AI-agent framework designed for automating rigorous scientific experimentation. It streamlines the entire research lifecycle, from hypothesis formulation to result interpretation, ensuring precision, reliability, and reproducibility. This empowers scientists to accelerate their research processes significantly.

Tau: A Minimalist Python Coding Agent for Your Terminal
September 8, 2026
Tau is a Python port of Pi's minimalist coding agent, designed to live in your terminal. It allows users to make requests like "explain this repo" or "add tests," and it can read files, edit code, and run commands. Beyond its utility, Tau also serves as a teaching project, demonstrating how coding agents are built with a small, readable codebase.

Awesome Harness Engineering: Building Reliable AI Agent Systems
September 7, 2026
Awesome Harness Engineering is a comprehensive curated list dedicated to the discipline of designing robust AI agent harnesses. It offers a wealth of resources, patterns, and templates essential for building reliable AI agent systems. Developers can explore tools, best practices, and foundational concepts across various critical areas of agent development.
Best of Agent Harnesses: A Curated List for AI Agent Development
September 7, 2026
RyanAlberts' Best of Agent Harnesses is a comprehensive, curated, and ranked list of over 100 AI agent harnesses and orchestration frameworks. It provides valuable insights for building reliable agentic systems, offering both human-readable guides and machine-readable formats for agents themselves. The repository is rescored weekly to ensure up-to-date recommendations.
Source repository
Open the original repository on GitHub.