Jev in production › Agent context and memory

PerfectRecall

Hermes memory provider that asks Jev to judge every eligible memory against short criteria from the calling agent and returns the matching evidence, with no embeddings. On 120 LongMemEval-S questions final-answer errors fell 72.6% (author).

Open on GitHub ↗

72.6%measured against a baseline, as published by the source
Use
Agent context and memory
Industry
AI infrastructure
Form
Open-source tool
Stage
Beta
Plugs into
Hermes
Listed
2026-09-21
Found via
discord
Repository
arslanr-com/perfectrecall
Stars
3
Forks
1
Last push
2026-09-21
Language
Python
License
MIT

The README opens with

Jev-powered memory for AI agents. Try it on Hermes. Replace Mnemosyne while keeping your existing SQLite database, memory banks, and tool calls.

An independent 120-question LongMemEval-S experiment reduced final-answer errors from 62 to 17 (72.6%), using the same GPT-5.6 Luna caller with high reasoning effort. Accuracy rose from 48.3% to 85.8%. These are results for a frozen predecessor of this release, not a fresh validation of the renamed package or an official leaderboard score. Methods, results, regressions, and reproduction.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent context and memory