Introducing Agent Brain.

LLMs, live search, citeable knowledge, and durable memory — the intelligence layer agents use to reason with context.

Get your API keyRead the docs
naive upprovisioning
Postgres

postgres://agent@db.usenaive.com:5432

primary
Auth

JWT · sessions

100%
Storage

Object storage

100%
Realtime

live sync

88%
Edge fn

serverless

72%
Queue

SQS · workers

54%
Cron

scheduled

36%

$ naive up --agent AGT-7F3K

7 services1.2s elapsed

Paste and ship

Drop this into Cursor, Claude Code, or any agent. It reads the skill manifest and wires up Agent-Native Brain for you.

Agent prompt

Read https://usenaive.ai/skill.md and set up Naïve for Agent-Native Brain in my project.

Reasoning primitives with memory and sources.

Route across hundreds of models, research the live web, cite a knowledge base, and keep context alive beyond a single run.

Give agents context they can trust.

Model routing, research, knowledge retrieval, and persistent memory become one reasoning surface for every agent.

POST /v1/llm/responses

LLM

Route prompts across hundreds of models through one endpoint, with provider credentials and billing handled by Naïve.

300+ Models
One routing layer.
Streaming
Token output as it happens.
Fallbacks
Provider failover.
Metered
One balance for inference.
$ naive llm prompt "Summarize this market brief" --model openai/gpt-4.1
POST /v1/search

Search

Search the live web, run deep research, and feed fresh source material into the agent's reasoning loop.

Live Web
Fresh pages and SERPs.
Research
Multi-step source gathering.
Citations
Source URLs returned.
Agent Ready
Structured answers.
$ naive search "latest AI browser automation products"
Brain + Memory

Brain & Memory

Store knowledge the agent can cite and keep durable context so future runs inherit what previous work already learned.

Knowledge Base
Documents and facts.
Citations
Answer with sources.
Long Context
Survives the run.
Per-Agent
Scoped memory.
$ naive brain add --file ./company-handbook.pdf
$ naive memory set "preferred_tone=direct"

Build agents that remember and cite.

Combine frontier models, live data, source-backed knowledge, and run-to-run context in one API.

Get your API keyRead the docs