HyperAgency is an Agentic AI Operating System designed for long-lived, self-improving systems with explicit control, memory, and governance β not a generic automation toolkit. It is an open-source self-hosted & cloud solution for building, orchestrating, and deploying collaborative systems of AI agents and humans. It has self-developing tools for building fully autonomous software companies. The agents can be generated in semi-automatic mode. It includes web3 marketplace for selling and buying hyper agents. The hyper agents can make deals with each other and with people on behalf of their users.
We envision a future where software companies can operate with minimal human intervention β composed of agents that code, plan, manage, and evolve. HyperAgency provides the framework and infrastructure to explore and build toward that future.
π§ Think of it as your operating system for autonomous workflows β distributed, flexible, and customizable.
HyperAgency is now publicly released as an open-source agentic AI platform.
This repository serves as the primary public entry point for the HyperAgency ecosystem, including core architecture, documentation, and integration guidelines. All previously internal submodules are now publicly available and governed under the same multi-license model as this repository.
HyperAgency is under active development. While core concepts and interfaces are stable, some components may still evolve. This repository is intended for developers, architects, and organizations exploring long-lived, agentic systems rather than turnkey automation scripts.
With HyperAgency, you can:
- β Create, deploy, and manage agents β quickly iterate and improve.
- π¬ Communicate across agents and humans β all in one unified interface.
- π§© Assemble smart, collaborative AI-human teams β for coding, design, planning, or operations.
- πΊοΈ Coordinate visually β with an intuitive Map view.
- π§ͺ Use an interactive playground β test flows step-by-step in real time.
- π Orchestrate conversations β with multi-agent dialog and memory.
- π Stay in control β enterprise-ready with secure APIs, self-hosting, and customizable source code.
- π Scale across distributed nodes β federated and connectable infrastructure.
β¨ Build your own autonomous AI-first organization β or enhance your existing one.
While still in active development, HyperAgency already includes many of the core components required to experiment with autonomous system coordination.
π See the Docs for full capabilities, architecture, and usage examples.
You can self-host HyperAgency locally in just a few steps β or skip the setup entirely and use our cloud environment for a faster start.
To run HyperAgency locally, install the following:
If you donβt want to manage infrastructure yourself, you can request access to our hosted HyperAgency Cloud, where everything is pre-configured and ready to use.
π Get Cloud Access
The cloud environment is perfect for early testing, team collaboration, or demoing agentic flows without running Docker or Vault locally.
mkdir hyperagency
cd hyperagency/
curl -fsSL https://raw.githubusercontent.com/vuics/h9y/refs/heads/main/install.sh | sh
# OPTIONALLY: Generate TLS certificates
./gen-certs.sh
# OPTIONALLY: Setup DNS with /etc/hosts
./setup-hosts.shRun:
docker compose upOpen h9y.localhost in the browser. To unlock Vault for secure storage of keys, see the section "Initialize Vault" below.
git clone git@github.com:vuics/h9y.git
cd h9y
git submodule update --init --recursiveCopy and customize .env files for the main platform and submodules:
cp env.example .env./gen-certs.shOn macOS, double-click each .crt file in ./certs/ to trust them in Keychain Access.
If your domain is h9y.localhost or anything on localhost, you may not need to configure the DNS, since the locahost often resolves to 127.0.0.1 automatically.
If your domain name does not resolve, set up /etc/hosts entries:
sudo ./setup-hosts.shUse Docker Compose to start all services:
docker-compose upAfter you started the stack, you can open in the browser:
| App Name | URL |
|---|---|
| App | h9y.localhost |
| API | api.h9y.localhost |
| Vault | vault.h9y.localhost |
| Langflow | langflow.h9y.localhost |
| Nodered | nodered.h9y.localhost |
NOTE: Replace h9y.localhost with your ${DOMAIN}.
- Open Vault (replace
h9y.localhostwith your${DOMAIN}), and input: β’ Key shares:5β’ Key threshold:3 - Set the env vars with displayed initial root token and the keys in the
.envfile in the format:
VAULT_TOKEN=(Initial root token)
VAULT_UNSEAL_KEYS=(Key 1),(Key 2),(Key 3),(Key 4),(Key 5)- Unseal the vault by inputing 3 of the keys, and sing into vault with the initial root token.
- Enable new engine with type KV (kv-v2) and path
secret. - Restart Docker Compose.
docker compose down
docker compose updocker-compose downHyperAgency ships with predefined Docker Compose profiles that let you start small, scale fast, and run exactly what you needβno more, no less. Profiles align the platform with your intent, from first exploration to a full, production-grade agentic stack.
| Profile Name | Description |
|---|---|
try |
Minimal, zeroβfriction setup to explore HyperAgency (default). Ideal for firstβtime users, quick demos, and experiments. |
h9y |
Core HyperAgency services included in the h9y repository. Best for active development and local iteration. |
all |
Complete HyperAgency Cloud stack, mirroring the services available at HyperAgency Cloud. |
You can find the exhaustive list of available profiles in the docker-compose.yaml.
Choose the profile that matches your current goal by setting it in the .env file:
COMPOSE_PROFILES=h9yYou can enable multiple profiles and Docker Compose will merge them into a single runtime configuration:
COMPOSE_PROFILES=try,logs,metricsThen start HyperAgency using Docker Compose as usual. Docker will run only the services associated with the selected profiles.
Special thanks to Hal Casteel and William McKinley for their early ideas, feedback, and discussions. Their insights into intelligent systems and automation inspired much of what became HyperAgency.
HyperAgency follows a clear separation between software licensing and brand ownership. This ensures maximum openness for developers while protecting the HyperAgency identity and trust.
The HyperAgency source code is available under a multi-license model, allowing you to choose the license that best fits your use case.
| Use Case | License |
|---|---|
| Personal, educational, non-commercial use | Apache-2.0-NC |
| Commercial projects that remain open-source | AGPL-3.0 |
| Commercial closed-source or proprietary use | Commercial License |
- Apache-2.0-NC β Free for personal, educational, and non-commercial usage
- AGPL-3.0 β Free for commercial use if modifications remain open-source
- Commercial License β Required for proprietary, closed-source, or SaaS offerings
Answers on the most frequent licensing questions are listed in Licensing FAQ.
For commercial licensing inquiries, contact artem@h9y.ai.
The HyperAgency name, logo, and visual identity are NOT covered by the open-source licenses above.
They are protected under trademark law and governed by the
β‘οΈ HyperAgency Trademark Policy.
This means:
- β You may use, install, modify, and distribute the code according to its license
- β You may NOT use the HyperAgency name or logo in ways that imply official endorsement, ownership, or affiliation unless explicitly permitted
This separation protects users from confusion while keeping the software ecosystem open and extensible.
In short: Open code encourages innovation. Protected branding ensures trust.
HyperAgency is an evolving framework for building agentic, autonomous systems β and eventually, fully autonomous software companies.
It already offers powerful capabilities for orchestrating agents, coordinating distributed systems, and integrating LLMs and humans in real-time workflows. By joining early, you can contribute to defining what autonomous organizations of the future look like.
π Explore. π€ Collaborate. π Build. Start building your own agentic stack with HyperAgency today.
