Skip to main content

​
The problem

Your AI agent forgets everything between conversations. Users repeat themselves, context is lost, and the experience feels broken.

​
The solution

Memory gives your agent persistent, searchable storage for facts extracted from conversations. When a user says “I prefer dark mode” or “The client is risk-averse,” those facts are stored and can be retrieved later.

​
How it works

  1. Add memories - Pass conversation messages, we extract discrete facts
  2. Search memories - Query by meaning, not just keywords
  3. Filter by tags - Scope memories using 12 generic indexed tag fields
The API handles:
  • Fact extraction (turning “I like X but hate Y” into separate facts)
  • Deduplication (updating existing facts instead of creating duplicates)
  • Semantic search (finding “investment preferences” when you stored “conservative strategies”)

​
Quick start

# Add a memory
curl -X POST https://api.case.dev/memory/v1 \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {"role": "user", "content": "Remember that this client prefers conservative investments."}
    ],
    "tag_1": "client_123",
    "tag_2": "matter_456",
    "category": "preference"
  }'

# Search memories
curl -X POST https://api.case.dev/memory/v1/search \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "investment preferences",
    "tag_1": "client_123",
    "top_k": 5
  }'

​
Tag fields

Memory provides 12 generic indexed tag fields (tag_1 through tag_12) for filtering. You decide what each tag means for your application:
Use Casetag_1tag_2tag_3tag_4
Legalclient_idmatter_idattorney_idsession_id
Healthcarepatient_idencounter_idprovider_iddepartment
E-commercecustomer_idorder_idproduct_idsession_id
Supportuser_idticket_idagent_idchannel
All tag fields are indexed for fast filtering. Use them for any dimension you need to query by.
# Store a memory scoped to client + matter
curl -X POST https://api.case.dev/memory/v1 \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {"role": "user", "content": "The patent filing deadline is March 15th, 2026."}
    ],
    "tag_1": "client_acme_corp",
    "tag_2": "matter_patent_2026_001",
    "tag_3": "atty_jane_smith",
    "category": "deadline"
  }'

# Search only this client's deadlines
curl -X POST https://api.case.dev/memory/v1/search \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "upcoming deadlines",
    "tag_1": "client_acme_corp",
    "category": "deadline",
    "top_k": 10
  }'

# List all memories for a specific matter
curl "https://api.case.dev/memory/v1?tag_1=client_acme_corp&tag_2=matter_patent_2026_001" \
  -H "Authorization: Bearer $CASEDEV_API_KEY"

​
Categories

The category field is free-form text - you define your own categories. Here are suggested categories for different domains:
CategoryDescriptionExample
factGeneral facts about client/matter”Client founded company in 2019”
preferenceCommunication or work preferences”Client prefers email updates”
deadlineFiling deadlines, court dates”Motion due March 15th”
decisionDecisions made by client/court”Client approved settlement terms”
contactContact information”Client’s assistant is Jane (jane@acme.com)“
relationshipRelationships between parties”Defendant is client’s former business partner”
court_rulingCourt rulings and precedents”Judge denied motion to dismiss”
proceduralProcedural information”Case assigned to Judge Thompson”

​
Healthcare categories

CategoryDescription
allergyPatient allergies
medicationCurrent medications
preferenceTreatment preferences
historyMedical history
family_historyFamily medical history
socialSocial/lifestyle factors

​
Filtering by category

# Get only deadline memories for a client
curl "https://api.case.dev/memory/v1?tag_1=client_123&category=deadline" \
  -H "Authorization: Bearer $CASEDEV_API_KEY"

# Search preferences only
curl -X POST https://api.case.dev/memory/v1/search \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "communication method",
    "tag_1": "client_123",
    "category": "preference"
  }'

​
Listing memories

# List all memories for a client
curl "https://api.case.dev/memory/v1?tag_1=client_123&limit=50" \
  -H "Authorization: Bearer $CASEDEV_API_KEY"

# List with multiple filters
curl "https://api.case.dev/memory/v1?tag_1=client_123&tag_2=matter_456&category=deadline&limit=20&offset=0" \
  -H "Authorization: Bearer $CASEDEV_API_KEY"

​
Deleting memories

​
Delete a single memory

curl -X DELETE https://api.case.dev/memory/v1/mem_abc123 \
  -H "Authorization: Bearer $CASEDEV_API_KEY"

​
Bulk delete by tags

curl -X POST https://api.case.dev/memory/v1/delete-many \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'
Bulk delete removes all matching memories. Use with caution.

​
Memory events

When you add memories, the API returns what happened to each extracted fact:
EventDescription
ADDNew memory created
UPDATEExisting memory was updated/merged
DELETEContradicting info caused memory deletion
NONEDuplicate - memory already exists
curl -X POST https://api.case.dev/memory/v1/add \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

​
Direct storage (skip extraction)

To store a fact directly without LLM extraction, set infer: false: 
curl -X POST https://api.case.dev/memory/v1/add \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

​
Custom extraction prompts

For domain-specific extraction, provide a custom prompt: 
curl -X POST https://api.case.dev/memory/v1/add \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

​
Pricing

OperationCost
Add memory$0.001 per operation
Search$0.001 per operation
List/Get/DeleteFree
LLM usage for fact extraction and embeddings is billed separately through the LLM service at standard rates.

LLMs

Use memories as context for chat completions

Vault

Store documents, use Memory for extracted facts