A phone call is a context problem with a deadline
Voice memory is a lifecycle: recall before the first sentence, write back after hangup, and verify that the next interaction can observe the result.
Governed contextYour agent does not only have a memory problem
Stored history can still produce stale, conflicting, late, or untraceable context. The harder problem is deciding what an agent is allowed to rely on now.
ProductThree caller-memory endpoints, on purpose
Northsun keeps its frozen caller-memory REST contract to recall, write-back, and read-only lookup—while the hosted MCP tool surface evolves separately.
Agent operationsContext rot: when agent instructions become liabilities
A mandatory stale instruction is worse than a missing optional note. Here is how authority, freshness, routing, and falsifiers prevent context rot.
Deep diveDesigned for sub-300ms voice recall: inside the edge hot path
How Northsun (formerly Mnemix) keeps recall work bounded, reports request timing, and lets agent builders design honest fallbacks without treating an architecture target as a benchmark.
ComparisonChoosing Northsun or a general-purpose memory system
A non-comparative evaluation guide for deciding whether Northsun's memory, enrichment, caller REST lifecycle, and governed-context direction fit your agent.
EngineeringBi-temporal facts, explained through a voice interaction
A caller correction shows why valid time and transaction time are different—and why Northsun (formerly Mnemix) limits the full two-timeline model to evidence_refs and locked_facts.
Agent operationsThe preamble tax: what agents pay before useful work begins
Agent sessions spend context before the first useful action. The least visible part is often the context your rules require but your tooling does not automatically load.
TutorialAdd caller memory to Vapi with a custom HTTP lifecycle
Map Vapi server events to Northsun recall and call-end APIs, handle partial context safely, and verify write-back before relying on it.
EngineeringBi-temporal memory: what was true, and what did the system know?
Valid time and transaction time answer different questions. Keeping both lets an agent system preserve late-arriving facts, corrections, and prior belief.
Core conceptsSalience: the right context, not the biggest context
Why useful agent memory depends on selecting relevant, timely, governed context instead of filling the prompt with everything available.
EngineeringA check that does not run is a check that passes
How false-green verification happens, why exit code zero is not enough, and how to prove that a gate can reject the defect it claims to catch.
ArchitectureOne source of truth is a routing problem, not a slogan
Why declaring a canonical document is insufficient unless every writer, reader, index, and agent is reliably routed to it.
GuidesMCP or REST for agent memory?
How to choose between explicit HTTP lifecycle calls and model-visible MCP tools when connecting an agent to Northsun (formerly Mnemix).
GuidesRecall before, write back after
A durable agent-memory integration pattern: read context before the interaction, submit the completed event once, then verify it with a later recall.
Core conceptsEnrichment is context, not identity proof
How to use caller enrichment as nullable, correctable evidence without turning a phone-number lookup into an identity-verification claim.
Voice agentsNull enrichment is not an error
A caller-memory integration should become less personalized when optional enrichment is missing—not less functional.
API designWhat 204 No Content proves—and what it does not
A successful calls/end response confirms the interaction is already committed durably. Enrichment and other background processing remain separately asynchronous.
Production practiceRetrying an agent-context call without creating a storm
Retry only failures that can improve with time, cap the retry budget, add jitter, and keep voice fallbacks independent from optional context.
Agent architectureCross-agent coherence without making every agent identical
Shared context should be an explicit grant between bounded Context Spaces, not one giant memory bucket or uncontrolled copying between agents.
Developer trustChangelogs are part of the API contract
An API change is not complete when code merges. Builders need a dated, state-accurate explanation of what changed, what remains compatible, and what to verify.
Memory engineeringA false memory retrieved perfectly is still false
Memory contamination — one hallucinated fact, written once, poisoning every later step — is the failure mode retrieval cannot fix. New research formalizes it. Here is what memory builders should do at the write path.
MCPMCP's enterprise phase: easier to deploy, harder to trust
The 2026-07-28 stateless spec made MCP servers trivial to run; nine days later GitHub shipped enterprise allowlists. Thousands of servers are coming. The enterprise question is now: why should yours be on the list?
ArchitectureThe agent stack standardized connectivity. Context is next.
A2A found a home beside MCP, GitHub shipped a portable plugin standard, and MCP itself went stateless. The connective tissue of the agent economy is settling — which makes the one layer nobody is standardizing the interesting one.
EngineeringTool permissions are not context permissions
Your agent can be authorized to call the CRM and still have no business reading the record it gets back. Access control for tools is a solved idea; access control for context is a different primitive — and pretending otherwise leaks data politely.