Hyponema Docs
Hyponema is a platform for AI agents that keep context across conversations.
Use these docs to create workspaces, configure personas, connect speech and model providers, launch web or telephony sessions, attach tools, and inspect what happened after each turn.
Hyponema is currently in private beta. Some features require an enabled workspace, provider credentials, or a Hyponema-issued API key.
Start here
Section titled “Start here”- Follow the quickstart to create your first agent and session.
- Read the concepts if you are mapping Hyponema to your product model.
- Use the guides when wiring the widget, text chat, voice WebSocket, tools, telephony, or observability.
- Use the API reference for supported public integration flows.
What Hyponema gives you
Section titled “What Hyponema gives you”- Persistent memory for repeat conversations.
- Versioned personas, agents, and runtime guardrails.
- Vendor-neutral STT, LLM, and TTS configuration with cascading fallbacks.
- Web widget, text chat (SSE), voice WebSocket, and telephony entry points.
- Workspace tools (HTTP and MCP), knowledge base, dynamic variables, and listening profiles.
- Outbound calling, scheduled callbacks, and webhook delivery.
- Trace-level observability, evaluations, and post-session extraction runners.
Common paths
Section titled “Common paths”| Goal | Start with |
|---|---|
| Try the smallest integration | Quickstart |
| Understand what an agent is | Agents |
| Model users and memory | Users and Memory |
| Add Hyponema to a website | Web widget |
| Stream text responses | Text chat SSE |
| Build a voice client | Voice WebSocket |
| Let the agent act on your product | Tools |
| Give the agent reference material | Knowledge base |
| Place outbound calls | Outbound and scheduling |
| Review production behavior | Observability |