AI agent memory infrastructure for ai agents

Your AI tools
forget everything.
Fix that.

Persistent memory for Claude Code, Cursor, and every AI tool in your stack. Local-first. Cloud-synced. EU-hosted.

get started free view docs →
ai agent memory • semantic recall • vector embeddings • graph memory • pii masking • privacy-first • eu-hosted • <200ms p50 target • 99.5% uptime target • mcp native • rest api • ai agent memory • semantic recall • vector embeddings • graph memory • pii masking • privacy-first • eu-hosted • <200ms p50 target • 99.5% uptime target • mcp native • rest api • ai agent memory • semantic recall • vector embeddings • graph memory • pii masking • privacy-first • eu-hosted • <200ms p50 target • 99.5% uptime target • mcp native • rest api • ai agent memory • semantic recall • vector embeddings • graph memory • pii masking • privacy-first • eu-hosted • <200ms p50 target • 99.5% uptime target • mcp native • rest api •
‹ 01 ›

> what is memra

What is memra AI agent memory?

Memra is memory infrastructure for AI agents. Drop in a REST API or MCP server and your agents gain persistent, long-term memory, semantic recall, graph context, and PII masking. EU-hosted and privacy-first — it’s the AI memory agent layer built for teams who can’t afford to repeat themselves.

✓ ai agent memory ✓ persistent memory api ✓ memory layer ✓ llm memory ✓ mcp-native ✓ eu-hosted ✓ claude code ✓ cursor

> core systems

Everything your AI needs
to remember

01

persistent memory

Store decisions, patterns, and conventions. Your AI remembers your project context across every session. Never repeat yourself again.

store • retrieve • persist
02

semantic recall

Query by meaning, not keywords. 5-factor scoring with vector, temporal, importance, recency, and graph context. Finds the right memory every time.

vector • graph • temporal
03

privacy shield

PII detection and masking across 24 EU languages. Presidio + spaCy powered. Your users' data stays private, even from embedding providers.

presidio • spacy • masking
04

local + cloud

Run locally with zero data leaving your machine. Opt into cloud sync when your team needs shared knowledge. MCP + REST native.

local • cloud • hybrid
‹ 02 ›

> integration

Two lines to remember.
One line to recall.

works with any ai tool that supports mcp. or call the rest api directly.

terminal — memra api 
# store a memory
curl -X POST https://api.usememra.com/v1/memories \
  -H "Authorization: Bearer memra_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "content": "User prefers dark mode and concise responses",
    "type": "preference"
  }'

# recall relevant memories
curl -X POST https://api.usememra.com/v1/memories/recall \
  -H "Authorization: Bearer memra_live_..." \
  -H "Content-Type: application/json" \
  -d '{"query": "user preferences"}'_

also available: python sdk • php sdk • mcp server • rest api

‹ 03 ›

> metrics

Built for production

real infrastructure. real performance. real privacy.

EU
hosted
hetzner helsinki, finland.
data never leaves the eu.
<200ms
p50 latency
semantic search
in milliseconds.
Privacy
first
full erasure cascade.
pii masking built in.
5
factor recall
vector + temporal +
importance + recency + graph.
99.5%
uptime target
single-tenant
eu infrastructure.
11
endpoints
complete rest api.
store, recall, search, export.
‹ 04 ›

> data flow

How memory works

01

store

Your AI agent sends memories via REST API or MCP. Content is written atomically to the flat-file engine, metadata indexed in PostgreSQL, and embeddings queued asynchronously.

POST /v1/memories → queue → embed → index
02

process

Optional PII masking via Presidio + spaCy detects sensitive data in 24 EU languages. Embeddings are generated via OpenAI and cached with tenant-aware Redis keys for privacy.

pii scan → embed → cache → graph extract
03

recall

5-factor intelligent recall scores every memory against your query using vector similarity, temporal relevance, importance weighting, recency decay, and entity graph context. Built for sub-200ms p50 recall targets.

query → 5-factor score → ranked results → <200ms
‹ 05 ›

> pricing

Simple, transparent pricing

see full comparison →

hobby
Free
forever
  • + 200 memories
  • + 100 recalls/mo
  • + 1 project
  • + 2 API keys
  • + 30 req/min
start free
dev
EUR 39/mo
per account
  • + 25,000 memories
  • + 5,000 recalls/mo
  • + 5 projects
  • + intelligent recall
  • + graph memory
start dev
pro popular
EUR 99/mo
per account
  • + 250,000 memories
  • + 50,000 recalls/mo
  • + 15 projects
  • + intelligent recall
  • + graph memory
start pro
team
EUR 249/mo
per account
  • + unlimited memories
  • + unlimited recalls
  • + 100 projects
  • + intelligent recall
  • + graph memory
start team
.:*:.MEMORY.:*:.DATA.:*:.RECALL.:*:.VECTOR.:*:.GRAPH.:*:.EMBED.:*:.STORE.:*:.QUERY.:*:. .:*:.MEMORY.:*:.DATA.:*:.RECALL.:*:.VECTOR.:*:.GRAPH.:*:.EMBED.:*:.STORE.:*:.QUERY.:*:. .:*:.MEMORY.:*:.DATA.:*:.RECALL.:*:.VECTOR.:*:.GRAPH.:*:.EMBED.:*:.STORE.:*:.QUERY.:*:. .:*:.MEMORY.:*:.DATA.:*:.RECALL.:*:.VECTOR.:*:.GRAPH.:*:.EMBED.:*:.STORE.:*:.QUERY.:*:. .:*:.MEMORY.:*:.DATA.:*:.RECALL.:*:.VECTOR.:*:.GRAPH.:*:.EMBED.:*:.STORE.:*:.QUERY.:*:. .:*:.MEMORY.:*:.DATA.:*:.RECALL.:*:.VECTOR.:*:.GRAPH.:*:.EMBED.:*:.STORE.:*:.QUERY.:*:.

Stop repeating yourself
to your AI_

install memra-local in 30 seconds. free forever for personal use.

get started free
or try the live token compression demo →