Evidence tier Source Confirmed · 2 captures on record
What the publisher says
As described on Microsoft Marketplace.
AG2 is an open-source multi-agent AI framework designed for building, orchestrating, and coordinating collaborative AI agents to solve complex tasks. It provides an extensible environment for developing agent-based workflows, integrating large language models, using tools, and creating autonomous or human-assisted AI applications.
Key Features of AG2:
Show the rest of the publisher’s description (25 more lines)
- Open-source framework for developing multi-agent AI applications.
- Supports collaboration and communication between multiple AI agents.
- Provides an extensible architecture for creating custom agents and workflows.
- Supports complex multi-agent task-solving workflows.
- Enables configurable agent roles, behaviors, and interactions.
- Supports autonomous and human-assisted agent workflows.
- Provides capabilities for integrating tools and external services.
- Supports integration with compatible large language models and APIs.
- Allows developers to customize agent conversations and workflows.
- Supports building task-oriented and conversational AI applications.
- Provides an environment for experimenting with multi-agent systems.
- Can be self-hosted on Linux servers and cloud infrastructure.
- Suitable for developing agentic AI and automated workflow applications.
- Useful for research, experimentation, prototyping, and AI application development.
- Suitable for developers, researchers, AI teams, and organizations building multi-agent AI solutions.
AG2 Usage:
$sudo su
$ cd /opt/ag2
$ source venv/bin/activate
$ python --version
$ python -c "import ag2; print(ag2.__version__)"
$ pip show ag2
AG2 Installation Directory: /opt/ag2
Disclaimer:
AG2 is open-source AI software developed by its respective contributors and community. AG2 is not affiliated with or endorsed by any third-party AI organization, cloud provider, operating system, hardware manufacturer, or AI model provider mentioned for compatibility, integration, or deployment purposes.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment · as of 2026-08-29
Reconciled on 9/3/2026
Sources
Publisher resources
1 linkLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.