memco
agent?Log inSign up for free
memcovsSupermemory

Supermemory remembers what you told it.
memco remembers what your agents learned.

Supermemory is a memory API for agents, with plugins and MCP for personal use: it ingests conversations and documents and maintains profiles so an assistant knows its user. memco gives a network of people and agents a shared memory of the work, governed by default, measured on the next task.

Different person · Different session · Different tool · Reused insight

Primary jobShared, governed learning from real work
Unit of valueAn insight with source, standing and outcome history
Trust questionHas this insight proven useful, and may it be served here?

01The difference

What it remembers

SupermemoryUser context, documents and maintained profiles.
memcoWhat agents learned doing the work.

What improves over time

SupermemoryFacts about each user, updated as things change.
memcoBehavior on the next task, measured.

Who learns from whom

SupermemoryMemory is isolated per container: a user, project or organization.
memcoEveryone in the network; personal preferences stay in personal memory.

02Honest overlap

Where the products genuinely overlap.

  • 01Both persist and retrieve memory for agents.
  • 02Both offer a developer API.
  • 03Both can be used by individuals through MCP and plugins.
  • 04Both are model-agnostic.

03Where each product starts

Different centers of gravity.

Supermemory · User memory API

Give an agent a standing memory of each user, task or tenant.

  • Primary inputs: conversations, files, URLs and synced sources such as Drive, Gmail, Notion and GitHub.
  • Outcome: a maintained profile and searchable facts in the agent’s context.

memco · Trusted insight

Convert real agent work into trusted, scoped and reusable team insights.

  • Primary inputs: agent work, corrections, decisions and outcomes.
  • Outcome: a later task goes better, for another person, session or tool.

04The same week, replayed

One payment-retry bug. Two product jobs.

Illustrative engineering workflow; not customer evidence. The same scenario runs on every comparison page, so what differs is the product job, not the anecdote.

  1. 01Agent A · Cursorpayment-retry taskcalls a helper that was retired last quarter
  2. 02Failed testci · redthe dead end costs the run its first hour
  3. 03Senior correctionreview + passing PRthe durable fact: which path works now, and why
  4. 04Scoped trusted insightteam scope · provenance keptsource, contributor, scope and outcome attached
  5. 05Agent B · Claude Codenext week · different personstarts ahead of the dead end
What they can represent

Supermemory could store the correction as a fact in a shared project container, which a second agent can search if it is scoped to the same container.

What memco makes of it

memco makes the source, trust state, team scope and later outcome the primary object, then tests whether another engineer's agent avoided the failed path.

05Practical comparison

Dimension by dimension, in words.

Rows, not scoreboards: each dimension states what each product actually does, so the difference survives scrutiny.

DimensionSupermemorymemco
What it remembersFacts about users and entities, documents and maintained profilesWhat was learned doing the work
What improves over timeFacts update and are superseded as new content arrivesAgent behavior on the next task
Who learns from whomIsolated per container: a user, project or organizationEveryone in the network
Unit of valueA memory graph and profile per user, task or tenantAn insight with source, standing and outcome history
Write pathAPI and SDK calls, file and URL ingestion, plugins, MCP and connectorsAgent work, corrections, decisions and outcomes
Trust questionIs this fact relevant to the query, and still current?Has this insight proven useful, and may it be served here?
GovernanceContainer tags, scoped API keys and deletion; SOC 2 Type II, HIPAA, GDPRTrust, validation rules, policies, reconciliation, review where you require it
ProofSupermemory reports results on LongMemEval, LoCoMo and ConvoMemA later task improves, measured

06Choose honestly

Two good answers to two different questions.

Choose Supermemory if

  • You want an assistant that knows its user across sessions and sources.
  • User memory plus document retrieval is the main job.
  • One person, or one product’s users each on their own.

Choose memco if

  • An insight from one person's agent should improve a later task for another person or tool.
  • Corrections, failed paths and accepted outcomes keep getting rediscovered.
  • Shared learning needs source, standing, governance and a path to correction or retirement.
  • The learning should survive model, IDE and agent-platform changes.

07For your customers

If you are building memory into a product

Supermemory SDK

A memory API per end user, with profiles and document ingestion.

memco SDK

A memory network per customer, learning from their agents’ work, seeded from yours, metered by use.

08Proof, not vibes

The reuse test.

Do not stop at 'the agent remembered.' If the main job is an assistant that knows its user across sessions and sources, evaluate Supermemory. If the job is to make real engineering learning travel across people and tools, run the reuse test.

01Pick one repository and one repeated failure, correction or convention.
02Record the baseline behavior without the shared insight.
03Let Agent A hit the problem and capture the source-backed correction.
04Review and scope the candidate insight using the product states actually available.
05Give Agent B a related task in another session or tool.
06Measure repeated-error rate, completion, agent steps, review corrections and source/scope integrity.
07Record whether the insight helped, conflicted or should be corrected or retired.

A signup is not activation. Activation is an insight contributed from one task and correctly reused on a later task.

Run the reuse testRead the research

09Questions

What evaluating teams ask.

Enterprise controls

Source ledger

Statements about Supermemory are drawn from its official documentation and site, reviewed on 2026-07-30. Products change — if anything here is out of date, tell us and we will correct it.

Other comparisonsMem0ZepCogneeLettaAll comparisons

Test whether one insight can improve the next run.

Run the reuse testRead the research

the loop

benchmarks · product · research

A short dispatch on shared memory for AI agents — the numbers behind the product, what we're shipping, and the research we're reading. No filler.

Unsubscribe anytime · no spam