N
Neura
FeaturesUse Cases

Agent Runtime

ReAct engine with multi-step iteration

200+ Connections

MCPX native handlers + Runtime sandbox

Knowledge & RAG

Memory buckets with hybrid search

GlassBox IDE

Chat-driven agent customization

Dataset Creation Lab

290M+ scholarly works · 9 AI agents

Training Pipeline

Fine-tune 33+ open-source models

Marketplace

Publish and monetize agents & datasets

View all features →
PricingDownloadDocsBlogAbout
Log inGet Started
FeaturesUse Cases
Agent Runtime
200+ Connections
Knowledge & RAG
GlassBox IDE
Dataset Creation Lab
Training Pipeline
Marketplace
PricingDownloadDocsBlogAbout
Toggle theme
Log inGet Started Free
N
Neura

Autonomous AI agents that connect to your world and actually get work done.

Product

  • Features
  • Pricing
  • API Docs
  • Use Cases
  • Blog

Platform

  • Agent Runtime
  • Connections
  • Knowledge & RAG
  • GlassBox IDE
  • Dataset Creation Lab
  • Training Pipeline
  • Marketplace

Company

  • About
  • Careers
  • Contact

Legal

  • Privacy Policy
  • Terms of Service

© 2026 Neura. All rights reserved.

Layer 3 — Memory

Knowledge & RAG

Per-job memory buckets with vector embeddings. Your agents remember everything — across sessions, across tasks — with hybrid RAG search.

Get Started Free All Features

How memory works

1
Create— Attach a memory bucket to any agent or job
2
Ingest— Upload documents, URLs, or let the agent research and add content
3
Embed— Content is chunked and embedded into vectors automatically
4
Search— Agent queries the bucket before every action for relevant context
5
Learn— Results and insights are saved back, growing the knowledge base

Memory Buckets

Scoped, persistent memory attached to jobs and agents. Every insight, document, and result is stored and searchable — across sessions, not just within one conversation.

Hybrid RAG Search

Combines dense vector similarity with keyword search for maximum recall. The agent queries its memory before every action, pulling relevant context automatically.

Multi-Format Ingestion

Upload PDFs, CSVs, Markdown, HTML, images, and web URLs. Documents are automatically chunked, embedded, and indexed for instant retrieval.

Auto-Context Injection

When an agent starts a job with an attached bucket, recent memories are automatically injected into the system prompt. No manual context management needed.

Isolated Per-Job

Memory buckets are scoped to individual jobs. Sensitive data from one project never leaks into another. Full access control at the bucket level.

Web Research Agent

A built-in research sub-agent crawls the web, extracts content, and saves structured findings directly into your bucket — building a knowledge base in real-time.

Give your agents perfect memory

Every agent remembers, every insight compounds.

Get Started Free