The memory OS
for AI agents.

The memory OS
for AI agents.

Not storage. Not RAG. A cognition engine that ranks, compresses and evolves
agent memory across any model, any framework, at any scale.

Protect what matters most with insurance that's simple, reliable, and built for you.

Perspectiva clients:

Memory infrastructure built for every agent you'll ever run

Memory infrastructure built for every agent you'll ever run

From solo developers to teams running hundreds of agents, Thrindex gives every agent the memory layer it needs to keep improving.

  • SDK

    1
    pip install thrindex
    2
     
    3
    from thrindex import Client
    4
    client = Client(api_key="th_live_...")
    5
     
    6
    # Write
    7
    client.add(
    8
    content="User prefers email over phone",
    9
    agent_id="support-agent",
    10
    user_id="user-42",
    11
    )
    12
    # Search
    13
    results = client.search(
    14
    query="how should we contact this user?",
    15
    agent_id="support-agent",
    16
    user_id="user-42",
    17
    )
  • API

    1
    import httpx
    2
     
    3
    API_KEY = "th_live_..."
    4
    headers = {"Authorization": f"Bearer {API_KEY}"}
    5
    # Write
    6
    httpx.post(
    7
    "https://api.thrindex.com/v1/memories",
    8
    headers=headers,
    9
    json={
    10
    "content": "User prefers email over phone",
    11
    "agent_id": "support-agent",
    12
    "user_id": "user-42",
    13
    },
    14
    ).raise_for_status()
    15
     
    16
    # Search
    17
    r = httpx.post(
    18
    "https://api.thrindex.com/v1/memories/search",
    19
    headers=headers,
    20
    json={
    21
    "query": "how should we contact this user?",
    22
    "agent_id": "support-agent",
    23
    "user_id": "user-42",
    24
    },
    25
    )
    26
    results = r.json()["results"]

Intelligence before the query

Intelligence before the query

Agents write and search. Cognition runs in the background - never while your agent waits.

Read in under 50ms

POST /v1/memories/search uses pre-ranked cache + multi-signal scoring. No LLM on the read path.

Read in under 50ms

POST /v1/memories/search uses pre-ranked cache + multi-signal scoring. No LLM on the read path.

Write in milliseconds

POST /v1/memories returns immediately. Dedup, importance, compression and conflict resolution run async.

Write in milliseconds

POST /v1/memories returns immediately. Dedup, importance, compression and conflict resolution run async.

Under the hood

Memory is more than storage. The rest is what makes it intelligent.

Speed

Speed

Speed

Full protection

Full protection

Full protection

Personalized

Personalized

Personalized

Trusted

Trusted

Trusted

Clear data

Clear data

Clear data

Simple to use

Simple to use

Simple to use

Every agent memory, one dashboard

Browse, search and map what agents store - plus keys and analytics. Built for teams shipping AI in production.

Memory map

Your agent's entire memory, visible at once. See what's related, what's redundant and where knowledge is thin.

Memory map

Your agent's entire memory, visible at once. See what's related, what's redundant and where knowledge is thin.

Semantic search

Run the exact search your agent runs. See what it gets back, how fast and whether it came from cache.

Semantic search

Run the exact search your agent runs. See what it gets back, how fast and whether it came from cache.

Analytics

Latency, cache hits, ops volume and queue depth in one view. Memory you can actually monitor in production.

Analytics

Latency, cache hits, ops volume and queue depth in one view. Memory you can actually monitor in production.

Helping thousands protect their most valuable assets

15+

Year

Founded in 2009, growing from a local insurer to an international company.

98%

Satisfaction

Nearly all our customers rate their experience as excellent & reliable.

50k

Customers

Trusted by individuals and businesses who rely on us to protect what matters.

10k

Claims Resolved

Processed claims to help families and businesses get back on track.

48

Hour Claims

Average processing time is 2 days. You need help fast, we deliver faster.

$2M

Paid Monthly

Over 2 million euros in claims, helping customers recover and rebuild quickly.

15+

Year

Founded in 2009, growing from a local insurer to an international company.

98%

Satisfaction

Nearly all our customers rate their experience as excellent & reliable.

50k

Customers

Trusted by individuals and businesses who rely on us to protect what matters.

10k

Claims Resolved

Processed claims to help families and businesses get back on track.

48

Hour Claims

Average processing time is 2 days. You need help fast, we deliver faster.

$2M

Paid Monthly

Over 2 million euros in claims, helping customers recover and rebuild quickly.

Meet Thrindex

Meet Thrindex

We started with a simple idea. Insurance doesn't have to be complicated. Today, we help thousands of customers protect what matters most with coverage they can understand and trust.

GET STARTED

Creating memories

Tell us about your property and we'll create a custom insurance plan just for you in less than 5 minutes.

GET STARTED

Creating memories

Tell us about your property and we'll create a custom insurance plan just for you in less than 5 minutes.

GET STARTED

Creating memories

Tell us about your property and we'll create a custom insurance plan just for you in less than 5 minutes.

Create a free website with Framer, the website builder loved by startups, designers and agencies.