Practical overview
When it fits
Use AgC when a project needs an infrastructure layer for deploying and coordinating agent workloads, with a separate API, management UI and documented Docker Compose setup.
Who it is for
- Developers building services that deploy and coordinate AI agents.
- Organizations operating agent workloads on shared infrastructure.
Documented uses
- Deploy and run AI agents as compute workloads.
- Coordinate work across multiple agents.
- Use the platform's described runtime, memory, model-routing, tracing and testing capabilities.
Requirements & limits
The repository points to a hosted version at platform.agc.dev. It also documents Docker Compose setup and describes the project as open-core; the repository lists an Apache-2.0 license.
- The project lists Kotlin as its primary language.
- The README describes integrated long-term, episodic and vector memory, dynamic model routing, tracing and observability, and sandboxed testing and replay.
- Repository topics name DeepSeek, Gemini, Groq and Ollama, but specific integrations and compatibility details are not documented in the supplied material.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Start AgC with Docker Compose
Set up the AgC platform locally and open its documented UI and API addresses.
Before you start
- A cloned AgC repository
- Docker Compose
Steps
Clone the AgC repository and change into its directory.
Change into deploy/docker/.
Run docker-compose up.
Open the UI at http://localhost:6645 or the API at http://localhost:6644.
Expected outcome
The documented default configuration starts the platform, with separate local addresses for the UI and API.
Guide limitations
- The README does not specify additional environment or hardware requirements.
Compare options for Agent orchestration
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Agc | Deploy and run AI agents as compute workloads. | Cloud, Docker, Self-hosted, Server | The repository points to a hosted version at platform.agc.dev. It also documents Docker Compose setup and describes the project as open-core; the repository lists an Apache-2.0 license. |
| Agentfm Core | Run a containerized agent in a Podman sandbox on a worker machine | Desktop, Docker, Self-hosted | The README lists desktop installers for macOS and Linux; it says the Windows app is in progress. Its desktop quick start says the bundled node connects to the public mesh. The README notes that the v1 installers are unsigned and macOS may block the first launch. |
| Plano | Route incoming requests to agents based on their declared roles. | Self-hosted, Server | Plano is public source code under the Apache-2.0 license. The README describes hosted Plano models free of charge in the US-central region for a first-run developer experience; for production scale it points to running models locally or contacting the project for API keys. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 13 October 2026
- Original website title
- masaic-ai-platform/AgC · Official homepage title · retained in its source language