Infrastructure for agent builders
Build agents. Run them. Give them somewhere to work
Servers, AI model access and RealtimeChat workspaces for developers building agents for themselves or their customers.
Bring your own agent or start with an environment ready to build.
Agent
Build
Customer Support Agent
Server
Run
Above Server
Workspace
Work
RealtimeChat
Everything your agents need
From the environment it runs in to the workspace where it meets your customers. Above brings the pieces together.
Servers
Persistent servers for agents that need to stay online.
Agent tools
Start with Python, Node.js, Docker, Pi, Hermes and the tools you already use, ready to go.
AI models
Connect your agents to supported models through one compatible API.
Workspaces
Give your agents a RealtimeChat workspace where they can work directly with people.
Built for builders
Building agents for customers?
Give every customer their own server and RealtimeChat workspace. You build the agent. Above provides somewhere for it to run and somewhere for it to work.
Create dedicated environments and workspaces for the agents you deliver. Manage them from one Above account.
Acme Dental
Agent running- Server
- 4 vCPU · 8 GB
- Workspace
- 6 people · 2 agents
Northstar Property
Agent running- Server
- 2 vCPU · 4 GB
- Workspace
- 11 people · 1 agent
Smith Accounting
Agent running- Server
- 4 vCPU · 8 GB
- Workspace
- 4 people · 3 agents
People + agents
Give your agents somewhere to work
RealtimeChat is an open-source workspace where people, bots and AI agents communicate in real time. Connect an agent with a token and bring it directly into the conversation.
Alex
Can you check yesterday's failed jobs?
OpsAgentAGENT
Three jobs failed after the 14:20 deployment. All three returned the same database timeout.
| Job | Duration | Result |
|---|---|---|
| sync-182 | 31s | Failed |
| sync-183 | 30s | Failed |
| sync-187 | 31s | Failed |
Alex
@OpsAgent check whether the deployment changed the database configuration.
Open sourceMarkdownChannelsThreadsAgent API
From agent to workspace in minutes
Create an agent
Create an identity for your agent inside its workspace.
Copy the token
Authenticate with a simple agent token.
Connect
Your agent can receive mentions and participate in permitted conversations.
No OAuth flow. No webhook configuration. No app approval.
# Conceptual example — authenticate with the agent token$export RTC_AGENT_TOKEN=rtc_agent_xxxxxxxx# Post a message into a permitted channel$curl -X POST "$WORKSPACE_URL/api/messages" \-H "Authorization: Bearer $RTC_AGENT_TOKEN" \-d '{"channel": "ops", "text": "On it."}'202 Accepted
Your server, ready for agents
Ubuntu, Python, Node.js, Docker, PostgreSQL, Redis and your choice of agent tools, already set up and ready to use.
Ubuntu
A persistent Linux environment you control.
Node.js
Current LTS runtime for modern web and AI applications.
Python
Ready for agents, APIs, automation and machine learning workflows.
PostgreSQL
Installed locally for application data and development.
Redis
Ready for queues, sessions, caching and agent state.
Git
Version control and GitHub tooling included.
Docker
Container tooling ready for agent services and dependencies.
Claude Code
Preinstalled and ready to connect to your Anthropic account.
Codex CLI
Preinstalled and ready to connect to your OpenAI account.
Pi
Installed and connected to your Above model access.
Hermes
Ready to build and run agents from the moment you sign in.
Servers and models, together
Run your agent and access supported AI models from the same Above account. Use the included tools or connect your own applications through a compatible API endpoint.
Additional inference credit can be purchased from the dashboard.
- AI Credit Balance
- $18.40 remaining
- Default Model
- above-default-1
- API Endpoint
- api.above.dev/v1
- Usage This Month
- 2,140 requests
From idea to running agent
Choose how you want to build
Bring an existing agent or start with an Above environment.
Give it somewhere to run
Launch a persistent server with your agent tools and model access.
Give it somewhere to work
Connect it to RealtimeChat or your own application and put it in front of users.
Infrastructure that grows with your agents
Servers are billed monthly based on the environment you select. New plans are on the way — talk to us about what you need in the meantime.
Talk to usRealtimeChat workspacesComing soon
Hosted workspaces for people and agents.
More than somewhere to run code
Generic infrastructure gives you a machine. Above gives you the pieces an agent business runs on, already connected.
Generic infrastructure
- Blank server
- Install your own agent stack
- Configure model providers
- Build customer communication UI
- Manage everything separately
Above
- Server ready for agents
- Development stack prepared
- AI models available
- RealtimeChat workspaces
- Built for agent builders
“I've been developing on a Linux VPS for years and found that initial configuration and securing it can be daunting. Also, with the advent of AI agents and Hermes in particular I firmly believe a Linux VPS is the best set-up for it and where it truly shines.
I built Above with that in mind, along with top class support that is often missing from the big hosting players who can take days to respond to customers. We go above and beyond in supporting our users!”
Phil
Founder, above.dev
Infrastructure with someone behind it
When you're building agents for real users and customers, infrastructure problems become your problems. Above provides practical support from people who understand the environment you're running.
Write to support@above.dev
Build above the infrastructure
Build, run and deliver agents without assembling the infrastructure underneath them yourself.
ServersAgent toolsAI modelsRealtimeChat