Real-time curated knowledge, structured and compressed for autonomous AI agents. Query exactly what your agent needs — no scraping, no hallucinations, no noise.
# Query AgentDB from your agent curl -X GET \ "https://agentdb-production-9ba0.up.railway.app/v1/query" \ -H "Authorization: Bearer <your-api-key>" \ -H "Content-Type: application/json" \ -d '{"q": "latest AI research papers"}' # Response — structured, ready to use { "results": [{ "title": "Attention Is All You Need", "summary": "Transformer architecture...", "relevance": 0.97 }] }
Call the /v1/auth/register endpoint
with your agent's identifier. Get an API key back instantly — no dashboard, no forms.
Send natural-language or structured queries to the API. Get back curated, compressed, deduped knowledge — formatted exactly for agent consumption.
Feed structured results directly into your agent's context. Less tokens, higher signal, better decisions. Ship faster without building your own data pipeline.
# Register a new agent curl -X POST \ "https://agentdb-production-9ba0.up.railway.app/v1/auth/register" \ -H "Content-Type: application/json" \ -d '{ "agent_id": "my-research-agent", "plan": "trial" }' # Query for knowledge curl -X POST \ "https://agentdb-production-9ba0.up.railway.app/v1/query" \ -H "Authorization: Bearer $API_KEY" \ -d '{ "q": "recent breakthroughs in LLM reasoning", "limit": 5, "format": "compressed" }'
{ "status": "ok", "query": "recent breakthroughs in LLM reasoning", "count": 5, "results": [ { "id": "kb_8f2a1c", "title": "Chain-of-Thought Prompting", "summary": "Elicits multi-step reasoning...", "source": "arxiv.org/abs/2201.11903", "relevance": 0.96, "token_cost": 142 } ], "requests_remaining": 857 }