Enki – memory for AI agents that keeps ~half as much and answers as well

Enkilabs1 pts0 comments

GitHub - stephen487/enki-benchmarks · GitHub

/" data-turbo-transient="true" />

Skip to content

Search or jump to...

Search code, repositories, users, issues, pull requests...

-->

Search

Clear

Search syntax tips

Provide feedback

--><br>We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

-->

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

stephen487

enki-benchmarks

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star

master

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>1 Commit<br>1 Commit

results

results

LICENSE

LICENSE

README.md

README.md

View all files

Repository files navigation

Enki — Long-Term Memory for AI Agents

Enki is a memory engine for LLM agents. This repository publishes evaluation results only — the engine is closed-source. No configuration, internals, or methodology beyond what is described below is included here.

LongMemEval — Enki vs mem0 (head-to-head)

Both systems ingest identical conversation histories from LongMemEval-S. Each system's<br>retrieved memories are answered by the same model (Claude Haiku) and graded by the<br>same LLM-as-judge, at equal retrieval depth (K=10). The only variable is the memory layer.

Validated slice: 25 instances (full-benchmark run in progress).

Question type<br>Enki<br>mem0

Multi-session reasoning<br>4 / 5<br>2 / 5

Knowledge update<br>3 / 5<br>3 / 5

Single-session (user)<br>3 / 5<br>3 / 5

Single-session (assistant)<br>2 / 5<br>2 / 5

Single-session (preference)<br>2 / 5<br>2 / 5

Total<br>14 / 25<br>12 / 25

Storage: Enki answers from 0.49× the stored facts mem0 keeps on the same<br>conversations (mean 138 vs 283).

Standout: multi-session reasoning (4/5 vs 2/5).

Honest framing. This is a small, hand-validated slice; the overall margin (14 vs 12)<br>is modest and within what a 25-item sample can show. The robust, repeatable result is<br>comparable answer accuracy at roughly half the memory footprint , with a clear<br>multi-session advantage. Further evaluation is ongoing.

Retrieval latency (CPU-only)

Measured on a ~139-fact store, CPU-only (no GPU), 240 samples:

Percentile<br>Latency (ms)

mean<br>7.6

p50<br>6.1

p95<br>11.9

p99<br>13.0

Reproducibility

Full methodology and per-question results are available on request.

Enki Labs (UK) · 2026

About

No description, website, or topics provided.

Resources

Readme

License

MIT license

Uh oh!

There was an error while loading. Please reload this page.

Activity

Stars

stars

Watchers

watching

Forks

forks

Report repository

Releases

No releases published

Packages

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

You can’t perform that action at this time.

enki session reload memory search results

Related Articles