Your first memory in five minutes

Store a belief, query it, and see why it’s believed. Every snippet below is real and runs against the same API the dashboard uses.

1. 1

   Install and start the server

   Step 1: Install and start the server

   One package, no dependencies. Or run it straight from a clone — same server, same port, same first-run key. From source the dashboard needs building once (cd web && OMEM_STATIC=1 npm run build); in the wheel it is already bundled.

   From PyPIFrom source

   Copy code

   1pip install omem-infrastructure

   2omem-server # or: omem-server 9000

2. 2

   Create a client

   Step 2: Create a client

   The first run prints a project id and an API key. There is no signup call and nothing to configure — paste them straight in.

   Python

   Copy code

   1from omem import Memory

   2 

   3mem = Memory(api_key="omem_sk_...",

   4 base_url="http://127.0.0.1:8787",

   5 project="proj_...")

3. 3

   Remember a belief

   Step 3: Remember a belief

   `about` is any entity id you choose. `claim` is a token, not a sentence — OMEM normalises spelling, so three spellings of one claim stay one claim.

   Python

   Copy code

   1mem.remember(agent="support-bot",

   2 about="customer:alice",

   3 claim="prefers_annual_billing")

4. 4

   Query what it believes

   Step 4: Query what it believes

   Returns a four-valued state: BELIEVED_TRUE, BELIEVED_FALSE, CONTRADICTED, or UNKNOWN.

   Python

   Copy code

   1mem.believes(about="customer:alice",

   2 claim="prefers_annual_billing")

   3# -> 'BELIEVED_TRUE'

5. 5

   Contradict yourself

   Step 5: Contradict yourself

   The part a vector store cannot do. Tell OMEM two claims disagree, then assert the second one. Nothing is overwritten and nothing is lost.

   Python

   Copy code

   1mem.contradict("prefers_annual_billing",

   2 "prefers_monthly_billing")

   3 

   4mem.remember(agent="sales", about="customer:alice",

   5 claim="prefers_monthly_billing")

   6 

   7mem.believes(about="customer:alice",

   8 claim="prefers_annual_billing")

   9# -> 'CONTRADICTED'

6. 6

   Ask why

   Step 6: Ask why

   Both claims are still on record. Pass an assertion id to get the chain that led there — which agent said it, when, and on what basis.

   Python

   Copy code

   1beliefs = mem.about("customer:alice")

   2 

   3mem.why(beliefs[0]["id"])

   4# -> {'state': ..., 'provenance': [...]}