Letta gives one agent a memory of its own.
memco gives every agent the network's.

01The difference

• What it remembers

  Letta

  The agent's own state: a git-backed memory of files it can edit.

  memco

  What all agents in the network learned doing the work.

• What improves over time

  Letta

  That agent, over its own conversations.

  memco

  Every agent's behavior on the next task, measured.

• Who learns from whom

  Letta

  Mainly each agent from itself; cloud agents can share memory repositories.

  memco

  Everyone in the network, across frameworks and models.

02Honest overlap

Where the products genuinely overlap.

1. Both persist memory across sessions.
2. Both let an agent write to its memory.
3. Both work with many models.

03Where each product starts

Different centers of gravity.

• Letta · Stateful agent

  Run persistent agents that keep and edit their own memory over time.

  • Primary inputs: one agent's conversations, explicit teaching and its own tool work.
  • Outcome: a stateful agent whose memory and skills improve with use.

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

• What they can represent

  Letta can save the senior engineer's correction in the first agent's memory; another agent sees it only if both are cloud agents attached to a shared memory repository.

• 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.

Scroll sideways →

06Choose honestly

Two good answers to two different questions.

• Choose Letta if

  • You are building long-running agents and want each one's state managed for you.
  • The agent's own self-editing memory is the design.
  • You want an agent runtime, not only a memory.

• 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.
  • You run several agents, on several frameworks, that should learn from each other.

07For your customers

If you are building memory into a product

• Letta SDK

  An agent runtime with per-agent state; each deployed agent carries its own memory.

• memco SDK

  A memory network per customer that any agent framework, Letta included, can read and contribute to. Metered by use.

  Build with the memco SDK →

08Proof, not vibes

The reuse test.

Do not stop at 'the agent remembered.' If the main job is one long-running agent that manages its own state, evaluate Letta. If the job is to make real engineering learning travel across people, agents and tools, run the reuse test.

1. Pick one repository and one repeated failure, correction or convention.
2. Record the baseline behavior without the shared insight.
3. Let Agent A hit the problem and capture the source-backed correction.
4. Review and scope the candidate insight using the product states actually available.
5. Give Agent B a related task in another session or tool.
6. Measure repeated-error rate, completion, agent steps, review corrections and source/scope integrity.
7. Record 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 test →Read the research →

09Questions

What evaluating teams ask.