Odyssey is memory infrastructure for AI systems. Ingest knowledge, inspect what was retrieved and why, edit memory structure directly, and govern access across projects.
Authentication flow uses OAuth 2.0 with PKCE for secure token exchange...
Token refresh happens automatically when the access token expires...
Rate limiting is enforced at 100 requests per minute per API key...
Odyssey is memory infrastructure for AI applications. It combines memory ingest, retrieval inspection, memory graph editing, project scoping, and usage enforcement into a single operational layer.
Push documents and chunks via API
See what was returned and why
Edit entities, relations, and tags
Isolate memory per project
Set limits and track consumption
See exactly which chunks were retrieved for every query. View scores, ranking, source documents, and token counts. Understand why the system returned what it did.
Manipulate memory directly through entities, relations, and tags. Link chunks to graph items. Adjust how memory is organized without re-ingesting.
Every document, chunk, entity, and relation belongs to a project. Retrieval is isolated by default. Build multi-tenant AI products without cross-contamination.
Set quotas per project and API key. Track ingest and retrieve calls. Enforce limits before costs spiral. Control who can access what memory.
Odyssey is both a web application and an API. Use whichever surface fits your workflow.
Set up a project to scope all memory, keys, and usage. Each project is a separate memory domain.
Push documents, chunks, or structured data via API. Tag with metadata and link to entities.
Query memory and view full retrieval traces. See scores, sources, and ranking decisions.
Manipulate entities, relations, and tags in the Studio. Set usage limits in the Dev Console.
You are not guessing why the AI returned something. You can inspect it directly: query, matched chunks, relevance scores, source documents, and linked entities.
The billing module calculates usage based on metered events. Each event is tagged with a customer_id and project_id for attribution.
Metered billing events are batched every 60 seconds and written to the events table with deduplication by event_id.
Usage summaries are computed nightly and stored in the usage_daily table partitioned by customer.
Odyssey is equal parts web application and REST API. Use the dashboard for exploration and debugging. Use the API for production integrations.
# Ingest memory
POST /api/v1/ingest
{
"project_id": "acme-copilot",
"chunks": [{ "content": "...", "source": "..." }]
}
# Retrieve context
POST /api/v1/retrieve
{
"project_id": "acme-copilot",
"query": "How does auth work?",
"top_k": 5
}Odyssey is free to start. Set up project-scoped memory with full retrieval inspection in minutes.