MarkDB

Quickstart

Mint an API key and route your first agent request through MarkDB.

This guide gets you from zero to a captured agent conversation in a few minutes.

1. Create a tenant and API key

Sign in to the dashboard and create a tenant. From Settings -> API keys, mint a key. It looks like:

mk_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Copy it now -- the plaintext is shown only once.

Bring your own model keys

MarkDB routes to the model provider on your behalf. Add your provider credentials under Settings -> LLM keys, or use a tenant default. The proxy resolves the right key per request.

2. Point a client at the proxy

The proxy is OpenAI-compatible and also speaks the OpenAI Responses API and the Anthropic Messages API. The base URL is:

https://proxy.markdb.cloud

Authenticate with your key as a bearer token. A raw curl smoke test:

curl https://proxy.markdb.cloud/v1/chat/completions \
  -H "Authorization: Bearer mk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{"role": "user", "content": "Say hello in three words."}]
  }'

You should get a normal chat completion back -- and the exchange is now captured in MarkDB.

3. Connect your coding agent

Pick your tool:

4. See it in the dashboard

Open the Work log to watch sessions and turns appear as your agent works. Within seconds the enrichment worker starts producing summaries you can search.