🧠 Live in production · API v0.2

Your AI agents
never forget
again.

Plug-and-play memory infrastructure for B2B AI agents.
Three endpoints. One API key. Your agent goes from
amnesiac to contextually aware in minutes.

TRY THE DEMO → VIEW API DOCS
3
Core endpoints
<50ms
Avg recall time
Memories per agent
EU
Data residency
// how it works

Three endpoints.
Infinite memory.

No new architecture. Drop three API calls into your existing agent and it remembers everything.

01 / STORE

Remember anything

Text → embedding → pgvector. Your agent stores facts, events, preferences. We handle the vectorization.

await fetch("/remember", {
body: { content: "Alice is premium" }
})
02 / SEARCH

Recall by meaning

Cosine similarity on HNSW index. Retrieves the most relevant memories for any query in milliseconds.

await fetch("/recall", {
body: { query: "billing issue", topK: 5 }
})
03 / INJECT ✨

Context in one call

The killer feature. Pass the user message, get a context block to prepend to your system prompt. That's it.

const ctx = await fetch("/inject-context", {
body: { message: userMsg }
})
// paste ctx.block before system prompt
04 / RESULT

Your agent knows everything

Without a single line of prompt engineering. Your LLM receives full context automatically, every time.

// System prompt becomes:
[KRONVEX CONTEXT]
- Alice: premium, prefers email
- Last session: billing unresolved
// integration concrète

Comment l'intégrer
dans votre agent.

Avant Kronvex, votre agent oublie tout. Après, il se souvient de chaque utilisateur.

✗ WITHOUT KRONVEX
✓ WITH KRONVEX
// 3 LIGNES DE CODE SUFFISENT
VOTRE AGENT — AVANT vs APRÈS
AVANT (code actuel)
def chat(user_message):
  system = "You are a helpful assistant."
  # pas de contexte
  response = llm.call(
    system,
    user_message
  )
  # rien n'est sauvegardé
  return response
APRÈS (+3 lignes Kronvex)
def chat(user_message):
  ctx = kronvex.inject(user_message) # ← 1
  system = f"{ctx}
" + "You are a helpful assistant."
  response = llm.call(
    system,
    user_message
  )
  kronvex.remember(user_message)    # ← 2
  kronvex.remember(response)        # ← 3
  return response
OpenAI
GPT-4o, GPT-4
Anthropic
Claude 3.5, Claude 3
Mistral
Mistral Large, 8x7B
Any LLM
LangChain, CrewAI...
// api reference

Clean REST API.
No SDK required.

Auth via X-API-Key header. Every response typed. EU data residency.

POST
/auth/keys
Create an API key — no auth needed. Returns full_key once, store it securely.
POST
/api/v1/agents
Create an isolated agent memory space.
POST
/api/v1/agents/{id}/remember
Store a memory. Supports episodic, semantic, procedural types.
POST
/api/v1/agents/{id}/recall
Semantic similarity search. Returns top-K memories ranked by score.
POST
/api/v1/agents/{id}/inject-context
Returns a formatted context block ready to prepend to your system prompt.
★ KILLER FEATURE
GET
/api/v1/agents
List all agents scoped to your API key.
DEL
/api/v1/agents/{id}/memories
Wipe all memories for an agent. GDPR compliant.
// live demo

Try it now.
No signup required.

This is the real API running in production. Enter your key and agent ID to start.

● LIVE
API KEY
AGENT ID
MEMORY CONTENT
MEMORY TYPE
RESPONSE
// Response will appear here...
// getting started

Live in 5 minutes.

01

Get API Key

POST /auth/keys
Copy full_key

02

Create Agent

POST /agents
One per use case

03

Store Memories

POST /remember
After each interaction

04

Inject Context

POST /inject-context
Before each LLM call

05

Ship 🚀

Your agent now
remembers everything

// pricing

Simple. Usage-based.
Scales with you.

STARTER
€99/mo
1 agent · 10k memories
  • 1 agent
  • 10,000 memories
  • API key access
  • Community support
POPULAR
GROWTH
€499/mo
5 agents · 100k memories
  • 5 agents
  • 100,000 memories
  • Session filtering
  • Priority support
  • 99.9% SLA
SCALE
€1499/mo
20 agents · unlimited
  • 20 agents
  • Unlimited memories
  • Custom embeddings
  • Dedicated support
  • GDPR DPA
ENTERPRISE
Custom
Unlimited everything
  • Unlimited agents
  • On-premise option
  • Custom SLA
  • SOC2 in progress
SUBSCRIBE
STARTER — €99/mo
Powered by Stripe · Cancel anytime · EU data residency