Anyone shipping an agent that must be auditable

Belief revision

The agent changed its mind. Can you show the receipt?

Try it live

0/2

Press Play — watch the same writes hit ordinary memory and CLS++ side by side.

Ordinary memory

now—

history—

CLS++ memory

now—

kept (archived, never deleted)

nothing superseded yet

The problem

Your agent told a customer one thing last Tuesday and the opposite today. Compliance asks why. You open the memory store — and the old belief is gone. Delete-on-conflict left you with a story you can't reconstruct.

Delete-on-conflict — a contradiction wipes the old memory and its history.

Documented in mem0 #4536

How CLS++ handles it

CLS++ treats a contradiction as reconsolidation, not deletion. An evidence-gated revision archives the superseded fact with full lineage and an incremented version, and surfaces the new belief. Default reads return the current belief; the entire change history is one query away.

Under the hood — the real script

"I love Chinese food" becomes "I now hate Chinese food." Watch the old belief survive.

python Benchmarking/conflict_resolution.py

BEFORE  (after first statement):
   CURRENT :   'love'  | 'I love Chinese food'   (version=1)
AFTER   (after contradicting statement + reconsolidation):
   CURRENT :   'hate'  | 'I now hate Chinese food'  (version=2)
   ARCHIVED:   'love'  | 'I love Chinese food'  (superseded=True, lineage_of=[...])

Default retrieval returns current belief ('hate'): yes
Old 'love' fact archived with lineage, not deleted — history preserved.

The belief can change. The record of how it changed can't be silently erased.

Run the reliability proofs See other use cases