Design Partner Program: 10 seats open

Your agent can remember. Give it expertise.

SmartMemory keeps your agent's decisions and lessons as typed records, with as-of recall and a tamper-evident audit trail.

YouSet up the billing tables in MongoDB.

Agent

Before I do: your team decided billing uses a relational database, because ledger writes need relational guarantees. A document store was ruled out. Shall I use PostgreSQL instead?

Checked team memory
Decision
Billing uses a relational database.
Why
Ledger writes need relational guarantees.
Ruled out
Document store
Status
Current, decided Mar 3
Illustrative conversation.

Ask what your team decided

Which database does billing use?

A relational database.

Why
Ledger writes need relational guarantees.
Ruled out
Document store
Status
Current, decided Mar 3

Illustrative team memory and dates.

Read how decision memory works

Built for trust

A context graph, not just a knowledge graph

A knowledge graph says what exists. A context graph also keeps when it was true, where it came from, why it was recalled, and who may see it.

Time-aware facts

Every fact records when it was true and when SmartMemory learned it. Old facts are superseded, not deleted, so you can ask what was believed on any past date.

Trust and provenance

Every memory records where it came from, and decisions keep the evidence behind them, so you can trace a claim back to its source.

Explainability and audit

Memory changes are kept in a tamper-evident, hash-chained history, and an explain call shows how a memory came to be.

Access control

Every read and write is scoped to a workspace, user, or tenant, so one team never sees another team’s memory.

See it in action

From pip install to persistent memory.

A real terminal session: install SmartMemory, seed a project, ask it questions, and watch a brand-new session pick up the context at a fraction of the tokens. Under six minutes.

More on YouTube: Introduction · Getting started (all 8 parts) · SmartMemory in action

Decision memory

Decisions that keep their history

SmartMemory records what your agent decided. A decision can carry the reason behind it and a confidence score. Supporting evidence raises that score. When a decision is superseded or retracted, it stays in the record with the reason.

decision · choice

The events log uses PostgreSQL

Superseded

Confidence

0.8 → 0.82

Evidence

benchmark_result_id

Superseded by a new decision, confidence 0.9

The events log moves to MongoDB

Reason

New benchmarks show MongoDB handles our access patterns better.

Why SmartMemory

Knowledge tells an agent what is true. Expertise tells it what to do.

Decisions carry the why

Keep each choice with its reason and the evidence behind it, as one typed record.

Recall what was believed

Ask with an as-of date to recover the decision that was current then. On 25 synthetic reversed-decision questions it answered all 25 correctly on two seeds and two models. A notes file edited in place got 1 to 3.

A typed graph, not a flat list

Follow relationships among decisions, constraints, lessons, and reasoning instead of searching interchangeable notes.

In our test at 500 and 2,000 facts, SmartMemory injected about 470 tokens where a curated markdown file took about 11,700 to 12,000, roughly 25 times less, with no loss in answer quality. Single seed, 28 questions per size, synthetic coding-project corpus.

Frequently asked questions

Everything you need to know

Keep the decisions. Keep the reasons behind them.

Give every agent the judgment, constraints, and history it needs to move forward.