Vector stores
Find relevant passages across your documents.
Build agents through a familiar API, backed by managed vector stores, knowledge graphs, memory, and persistent sessions.
Your interface, workflows, and business logic.
Agents · sessions · turns · events
OpenAI, Anthropic, and supported models through OpenRouter.
MCP servers, hosted functions, and other agents.
Create agents, open persistent sessions, and stream their activity through Ragwalla’s implementation of the OpenAI Agents API.
Read the API documentationPOST /agents{
"name": "Research assistant",
"model": "claude-sonnet-4-6"
}POST /agents/sessions{
"agent_id": "<returned-agent-id>",
"environment": { "type": "none" },
"input": "Start a research session."
}Send these requests to https://api.ragwalla.com/gateway/v1 with your Ragwalla API key. Use the first response’s agent ID in the second request.
Configure the models your agents use and bring your own provider keys. Keep sessions, knowledge, and tool connections in Ragwalla as you evaluate which models work best for your application.
Documents, relationships, remembered context, and conversation history. Each has a place in your application’s data layer.
Find relevant passages across your documents.
Connect entities and follow their relationships.
Keep useful context across interactions, with explicit access controls.
Keep conversation history and the work performed during each turn.
Give agents access to your systems through MCP and hosted functions. Control which tools each agent can use.
Let agents coordinate with specialists, run recurring tasks, and return to work at a scheduled time.
Connect agents to your application, email, Slack, Teams, and other messaging channels.
Set tool permissions and memory access. Track usage, configure retention, and inspect audit records as your application grows.