Skip to main content
NexoraLaunch home

Build log live

AI Agents & Infrastructure

Cogni

Memory that reasons

  • 0community votes
  • 4DR by Ahrefs no change since last check

Ahrefs Domain Rating signal 13 Nov 2026, signal shifted 1 Nov 2026.

An MCP memory server that gives any LLM connected memory following chains of facts across documents, with no LLM in the retrieval path.

What it is

Screenshot of the Cogni homepage
What getcogni.io looks like

Cogni is an MCP server that gives any LLM connected memory following chains of facts across documents. Its entity-graph spreading activation follows connections a plain vector store cannot reach, answering cross-vocabulary multi-hop questions where similarity search scores zero. Works with any model—Claude, GPT, Gemini, or local—with no language model and no GPU in the retrieval path. Recall stays constant as memory grows; a fact buried in 32,000 words returns at a fixed cost per query. The service runs no LLM of its own, letting you work with whichever model you choose at the same cost whether frontier or local.

Systems

  • Entity-graph spreading activation for cross-vocabulary retrieval
  • Works with any LLM model
  • No LLM or GPU in retrieval path
  • Point-in-time and windowed recall
  • Timestamped memories
  • Fixed recall cost as memory grows

Pricing

Pricing model: Freemium

Free plan at $0 USD; Pro plan at $5 USD per month.

Follow status. Log in to follow Cogni's status

Want to see what Cogni does next? Follow them for milestones, new products and stories by email.

Cogni metrics

Signal readout for getcogni.io: Ahrefs Domain Rating and Majestic link signals, arrows for the change since the last scan.

  • 4 Domain Rating no change since last check
  • 2 Trust Flow no change since last check
  • 21 Citation Flow no change since last check
  • 34 Referring domains no change since last check
  • 94 External backlinks no change since last check

Ahrefs Domain Rating signal 13 Nov 2026, signal shifted 1 Nov 2026. Strongest signal topic: Recreation (2). Majestic signal 1 Nov 2026, signal shifted 1 Nov 2026. Link signals from Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.

Cogni domain signal

Show the signal details

Public RDAP record, last read 10 Nov 2026, 23:33 UTC.

  • Domain age 4 months
  • Registered
  • Expires
  • Registrar Porkbun LLC
  • DNSSEC Not signed

Full signal for getcogni.io

Cogni post-launch signal

The record for Cogni after its launch on Nexora Launch (1 November 2026), from the readings we keep.

  • 4 Domain Rating (Ahrefs) no change since launch
    at launch: 4 (1 Nov 2026); latest: 13 Nov 2026
  • 2 Trust Flow (Majestic)
    first measured 1 Nov 2026
  • 34 Referring domains (Majestic)
    first measured 1 Nov 2026

Day 11 since launch. Next receipt: day 30, 1 Dec 2026. A change here is a reading, not a claim about its cause; lots of things move these figures. Anything we do not measure is not shown.

Biggest gains on Nexora Launch

Got a launch coming up?

Plan your launch with our free playbook, from preparing your listing to choosing more launch directories.

See the launch playbook

Quick answers

How do I connect Cogni to Claude or ChatGPT?
For Claude or ChatGPT, add Cogni as a custom connector with the URL https://mcp.getcogni.io/mcp and sign in through your browser—no API key required. For developer clients like Claude Code or Cursor, create an API key from a connector app first, then paste it into your client's configuration.
Why isn't my assistant calling Cogni?
Cogni's tools are model-driven and require the assistant to decide to call them. You can fix this by asking plainly in conversation ("Check Cogni for what you know about this"), loading the Cogni skill if your client supports it, or adding a standing instruction to your client's custom instructions so the model knows when to recall and remember.
Can Cogni work with local AI models?
Yes. Cogni runs no LLM of its own and works with any model—Claude, GPT, Gemini, or local models like llama3.1:8b. The advantage lives in retrieval, not in the model, so smaller local models gain the most from Cogni's better context.
How does Cogni handle memory as it grows?
Recall stays constant at a fixed cost per query no matter how large your memory becomes. Even with a 32,000-word history, Cogni returns relevant facts first, every time, in a fixed eight rows per query.

More on this profile

Cogni has a free listing. The owner can unlock the full profile with a paid launch for $5:

  • Founder story (locked)
  • Milestones (locked)
  • Demo video (locked)
  • Dofollow website link (locked)

Also on the frontier

  1. ActionBox logo

    Rank 1: ActionBox

    Human approval infrastructure for AI agents and automation workflows

    AI Agents & Infrastructure

    DR 5 no change since last check 0 votes. Log in to send ActionBox a vote
  2. Threadless AI logo

    Rank 2: Threadless AI

    Hosted memory for AI agents that forgets like people do

    AI Agents & Infrastructure

    DR 0 no change since last check 0 votes. Log in to send Threadless AI a vote
  3. RELAI logo

    Rank 3: RELAI

    The continual learning engine for AI agents

    AI Agents & Infrastructure

    DR 23 no change since last check 0 votes. Log in to send RELAI a vote
  4. AgentHub logo

    Rank 4: AgentHub

    MCP hub for coding agents

    AI Agents & Infrastructure

    DR 0 no change since last check 0 votes. Log in to send AgentHub a vote
Ask a question