All use cases

Teams running more than one agent against shared memory

Swarm & multi-agent

In a single agent, lineage memory is insurance. In a swarm, it's load-bearing.

Try it live
0/3

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nothing superseded yet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

A single agent has one writer to memory, so conflicts are rare. A swarm has many agents reading and writing the same shared memory at once. Every blind overwrite becomes a race — one agent's wrong belief silently propagates to every other agent that reads it next, with no record of who changed what or why.

Last-write-wins shared memory keeps no history of a belief change. If a wrong write lands last, the next agent acts on silently-corrupted state and cannot tell.

How CLS++ handles it

CLS++ turns shared memory into an append-only, lineage-tracked ledger. Every belief change is attributable to the agent that made it, versioned, and replayable. The current belief is always clean; every superseded belief is archived — never deleted — and linked by lineage. Contradictions between agents are logged, not dropped. The value compounds with the number of agents.

Under the hood — the real script

Three agents write conflicting beliefs about one shared customer record, then a fourth agent reads it. No server, no API key.

python sales/demo/swarm_memory_demo.py
[   triage-agent] writes  'pro'  — Customer record loaded: plan tier = Pro.
[  billing-agent] writes 'free'  — Saw a failed renewal webhook; assumed downgrade.
[retention-agent] writes 'enterprise'  — Payments API confirms upgrade to Enterprise.

  NAIVE shared memory:
     change history: NONE — overwritten, unrecoverable
  CLS++ memory:
     CURRENT  : 'enterprise'  v3  by retention-agent
     ARCHIVED :  'pro'  v1  by triage-agent   superseded -> lineage_to_current
     ARCHIVED : 'free'  v2  by billing-agent  superseded -> lineage_to_current
     contradictions logged: 3

Conflicting writes from many agents are exactly the failure mode that silently corrupts shared state — and CLS++ is the only memory that preserves, attributes, and audits every one of them.