Memory API

The Memory API manages your AI Knowledge Base — persistent memories that help the AI personalize PRD generation across conversations. Memories are scoped per user and include preferences, decisions, project context, and feedback. See the Knowledge Base user guide for how memories work in the product.

List Memories

GET /api/memory

Retrieve your stored memories, sorted by importance and recent usage. Query parameters:

Parameter	Type	Default	Description
`limit`	integer	20	Max memories to return
`category`	string	—	Filter by category: `technical`, `business`, `process`, `style`, `team`
`type`	string	—	Filter by type: `preference`, `decision`, `project_context`, `feedback`
`active`	boolean	true	Set to `false` to include soft-deleted memories

curl https://app.thig.ai/api/memory?limit=10&category=style \
  -H "Authorization: Bearer YOUR_API_KEY"

const res = await fetch('https://app.thig.ai/api/memory?limit=10&category=style', {
  headers: { 'Authorization': 'Bearer YOUR_API_KEY' }
});
const { memories } = await res.json();

import requests

res = requests.get(
    'https://app.thig.ai/api/memory',
    params={'limit': 10, 'category': 'style'},
    headers={'Authorization': 'Bearer YOUR_API_KEY'}
)
memories = res.json()['memories']

Response:

{
  "memories": [
    {
      "id": "uuid",
      "userId": "user_123",
      "memoryType": "preference",
      "category": "style",
      "content": "User prefers detailed user stories with acceptance criteria in Given/When/Then format",
      "summary": "Prefers Given/When/Then acceptance criteria",
      "importance": 8,
      "isActive": true,
      "sourceProjectId": "proj_456",
      "lastUsedAt": "2026-03-05T14:30:00Z",
      "createdAt": "2026-02-15T10:00:00Z"
    }
  ]
}

Create Memory

POST /api/memory

Manually add a memory to your Knowledge Base. Body:

Field	Type	Required	Description
`memoryType`	string	Yes	`preference`, `decision`, `project_context`, or `feedback`
`category`	string	Yes	`technical`, `business`, `process`, `style`, or `team`
`content`	string	Yes	The memory content (clear, actionable statement)
`summary`	string	No	Brief 1-line summary
`sourceProjectId`	string	No	Project this memory originated from
`sourceConversation`	object[]	No	Conversation messages for context
`importance`	integer	No	1–10 (10 = most important for future context)

curl -X POST https://app.thig.ai/api/memory \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "memoryType": "preference",
    "category": "style",
    "content": "Always include acceptance criteria in Given/When/Then format",
    "summary": "Given/When/Then acceptance criteria",
    "importance": 8
  }'

const res = await fetch('https://app.thig.ai/api/memory', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    memoryType: 'preference',
    category: 'style',
    content: 'Always include acceptance criteria in Given/When/Then format',
    summary: 'Given/When/Then acceptance criteria',
    importance: 8
  })
});
const { memory } = await res.json();

Response:

{
  "memory": {
    "id": "uuid",
    "userId": "user_123",
    "memoryType": "preference",
    "category": "style",
    "content": "Always include acceptance criteria in Given/When/Then format",
    "summary": "Given/When/Then acceptance criteria",
    "importance": 8,
    "isActive": true,
    "createdAt": "2026-03-06T12:00:00Z"
  }
}

Delete Memory

DELETE /api/memory?id=MEMORY_ID

Soft-deletes a memory (sets isActive to false). The memory can still be retrieved by passing active=false to the list endpoint. Query parameters:

Parameter	Type	Required	Description
`id`	string	Yes	Memory ID to delete

curl -X DELETE "https://app.thig.ai/api/memory?id=MEMORY_ID" \
  -H "Authorization: Bearer YOUR_API_KEY"

await fetch(`https://app.thig.ai/api/memory?id=${memoryId}`, {
  method: 'DELETE',
  headers: { 'Authorization': 'Bearer YOUR_API_KEY' }
});

Response:

{
  "success": true
}

Extract Memories from Conversation

POST /api/memory/extract

Uses AI to analyze a conversation and automatically extract reusable memories — preferences, decisions, context, and feedback. Extracted memories are saved to your Knowledge Base. Body:

Field	Type	Required	Description
`conversation`	object[]	Yes	Array of message objects (max 50 messages, max 10,000 chars each)
`conversation[].role`	string	Yes	`user` or `assistant`
`conversation[].content`	string	Yes	Message content
`projectId`	string	No	Project the conversation belongs to

curl -X POST https://app.thig.ai/api/memory/extract \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "conversation": [
      {"role": "user", "content": "I prefer user stories with Given/When/Then acceptance criteria"},
      {"role": "assistant", "content": "Noted! I will use Given/When/Then format for all acceptance criteria going forward."},
      {"role": "user", "content": "Also, our tech stack is React + Node.js + PostgreSQL"}
    ],
    "projectId": "proj_123"
  }'

const res = await fetch('https://app.thig.ai/api/memory/extract', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    conversation: [
      { role: 'user', content: 'I prefer user stories with Given/When/Then acceptance criteria' },
      { role: 'assistant', content: 'Noted! I will use Given/When/Then format.' },
      { role: 'user', content: 'Our tech stack is React + Node.js + PostgreSQL' }
    ],
    projectId: 'proj_123'
  })
});
const { extracted, saved, memories } = await res.json();

Response:

{
  "extracted": 2,
  "saved": 2,
  "memories": [
    {
      "id": "uuid",
      "memoryType": "preference",
      "category": "style",
      "content": "User prefers Given/When/Then format for acceptance criteria",
      "summary": "Given/When/Then acceptance criteria",
      "importance": 8
    },
    {
      "id": "uuid",
      "memoryType": "project_context",
      "category": "technical",
      "content": "Tech stack: React, Node.js, PostgreSQL",
      "summary": "React + Node.js + PostgreSQL stack",
      "importance": 7
    }
  ]
}

Memory extraction uses your configured AI provider (respecting BYOK settings). The AI only extracts genuinely useful, reusable information — it skips trivial or project-specific details that won’t apply to future projects.

Memory Types

Type	Description
`preference`	User preferences about PRD style, detail level, terminology
`decision`	Key decisions made about requirements or architecture
`project_context`	Company, team, or technical stack information
`feedback`	Feedback about generated content that indicates future preferences

Overview

Endpoints

Memory / Knowledge Base

Memory API

List Memories

Create Memory

Delete Memory

Extract Memories from Conversation

Memory Types

Categories

Category	Description
`technical`	Technical architecture, stack, infrastructure
`business`	Business goals, KPIs, stakeholder preferences
`process`	Development methodology, workflow preferences
`style`	Writing style, format, detail level preferences
`team`	Team structure, roles, communication patterns

​Memory API

​List Memories

​Create Memory

​Delete Memory

​Extract Memories from Conversation

​Memory Types

​Categories

Memory API

List Memories

Create Memory

Delete Memory

Extract Memories from Conversation

Memory Types

Categories