Behavioral memory for AI agents
Give your agent memory of what the customer does.
Conversation memory recalls what the customer said. Signals is behavioral memory: it hands your agent what this customer has been doing. One prompt to your coding agent adds it.
- 6ms p50 serve, in-region
- 1 prompt to your coding agent
- Free tier, no card
Teams running on Snowplow







Siggy, the agent below, is reading your session.
An agent is talking to you
connectingSiggy, with Signalsreading your session
reading your session
Keyed on an anonymous session id. Siggy sees this visit and nothing else.
Why it starts from nothing
The model is good. It cannot see what happened three minutes ago.
Before
Memory that stops at the transcript
Conversation memory recalls what the customer said last time. The three failed searches and the page they are stuck on right now never reach the agent.
memory = what_was_saidWith Signals
Memory of what they did
Signals collects what the customer does and turns it into a compact context, structured for a tool call or written out for a system prompt.
minutes_on_checkout = 4Result
The first reply already knows
The agent answers the question the customer actually has, rather than asking them to describe what your own product just watched them do.
one call, before the replyWhy perception
What a customer-facing agent can do once it can see the session.
None of this works from a profile that lags behind the conversation. By the time it catches up, the conversation is over.
Stop asking what already happened
Three failed searches, four minutes on the checkout page, a basket that has not moved: the agent opens holding all of it, so the first three questions never get asked.
handle time · first contact resolutionEscalate on behavior, not on sentiment
A rule over live attributes hands the conversation to a human the moment the pattern says it is going badly, rather than after the customer says so.
escalation rate · satisfaction scoreAnswer from what they were looking at
A shopping agent that knows which two jackets were compared and which size guide was opened can answer the real question instead of a generic one.
assisted conversion · basket valueSmaller prompts, fewer tokens
A short context computed from the stream beats stuffing raw history into the prompt, which costs tokens on every turn and still misses the moment.
tokens per conversationHow it works
The same events, shaped so a model can use them.
One SDK, no event pipeline to build first. Signals collects the customer's activity and renders it as JSON for a tool call or as a narrative for a system prompt.
- 01Collect. Add a Snowplow SDK to your application and behavioral events start flowing in.
- 02Shape. Choose what the agent should know about, and whether it arrives as JSON or as a narrative.
- 03Read. What the customer just did is in the context <1s later, and the agent asks for it in 6ms p50, from your framework, the REST API or the MCP server.
Signals → your app6ms p50
minutes_on_current_page4
failed_searches_session3
items_compared2
basket_value184.00
recent_activitylast 30 events
Trigger escalate_to_humandelivered to your agent
One tool call, mid-conversation
OUTPOSTSupport, online now
Hi, I have a question before I buy.
tool callgetAgenticContext({ name: "checkout_context", format: "narrative" })
250 seconds on the current page. Session started 430 seconds ago. Based on last 20 recorded events for the last 600 seconds.
seconds_since_start_of_session, event, url, event_context
0, add_to_cart, /cart, {cart_value: 184.2}
180, page_view, /checkout, {}
250, site_search, /checkout, {terms: 'returns policy'}
330, site_search, /checkout, {terms: 'returns policy'}
Happy to help. Sorry the returns search came up empty: anything unworn can come back free within 30 days. Your $184.20 cart is still at checkout. Want me to take you back there?
Write a message
Works with
- Claude
- LangChain
- LangGraph
- LlamaIndex
- CrewAI
- OpenAI Agents SDK
- Vercel AI SDK
- Mastra
- Pydantic AI
- Google ADK
- CopilotKit
- Amazon Bedrock
- Vertex AI
Questions
Before you sign up
Is this a memory framework?
It is memory of a different kind. A memory framework remembers the conversation: what was said, what the agent learned. Signals is behavioral memory: it computes what the customer has been doing from their own events and serves it as context. Teams run both, one side holds the dialogue, the other sees the behavior.
Do I need an event stream already?
No. Collection is part of Signals. Add a Snowplow SDK to your web, mobile or server application and events start flowing in, validated against your schemas on the way. If you already run Snowplow, Signals reads the pipeline you have.
Which agent frameworks does this work with?
Any of them. Ask through the Python or Node.js SDK, the REST API, or the MCP server, as one tool call. Signals supplies what the customer has been doing; your model decides what to do with it.
Is this a vector store?
No, and it holds neither your documents nor your conversation history. Behavioral memory is computed from the customer's own events as they happen, not retrieved from a store you fill.
Where does it run?
Managed SaaS, or a private deployment in your own AWS or GCP account. Identical architecture either way, so what you evaluate is what you run. On a private deployment the activity Signals computes stays in your own cloud; what your agent then sends to a model is your call either way.
What does the free tier include?
The full product against your own traffic, up to 5 million events a month, with no card and no sales call. You should see an attribute updating against your own traffic in the first session.
Hand your own agent the last five minutes today.
Add the SDK, define one attribute, then ask for a customer's context from the agent you already run. The panel at the top of this page is the same thing, reading you.
The real engine · no card · no sales call
Or hand it to your coding agent
Then: Let's add Snowplow Signals to this agent. Understand the app first, then fetch the customer's recent activity as narrative and put it in the system prompt before the first reply.npx plugins add snowplow/skills