curl --request GET \
--url https://api.memcontext.in/api/memories/search \
--header 'X-API-Key: <api-key>'const options = {method: 'GET', headers: {'X-API-Key': '<api-key>'}};
fetch('https://api.memcontext.in/api/memories/search', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://api.memcontext.in/api/memories/search"
headers = {"X-API-Key": "<api-key>"}
response = requests.get(url, headers=headers)
print(response.text){
"found": 123,
"memories": [
{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content": "<string>",
"relevance": 0.5,
"createdAt": "2023-11-07T05:31:56Z",
"category": "preference",
"scope": "<string>",
"project": "<string>"
}
]
}Search memories
Search saved memories with a natural-language query. Use filters such as scope, project, and category when your app needs narrower results.
curl --request GET \
--url https://api.memcontext.in/api/memories/search \
--header 'X-API-Key: <api-key>'const options = {method: 'GET', headers: {'X-API-Key': '<api-key>'}};
fetch('https://api.memcontext.in/api/memories/search', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://api.memcontext.in/api/memories/search"
headers = {"X-API-Key": "<api-key>"}
response = requests.get(url, headers=headers)
print(response.text){
"found": 123,
"memories": [
{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content": "<string>",
"relevance": 0.5,
"createdAt": "2023-11-07T05:31:56Z",
"category": "preference",
"scope": "<string>",
"project": "<string>"
}
]
}Authorizations
API key created from the MemContext dashboard. Keys are prefixed with mc_, bound to one workspace, and API-key requests cannot override that workspace.
Query Parameters
Natural language search query. Use full sentences for best results.
1000Maximum number of results to return.
1 <= x <= 10Filter results to a single category.
preference- User likes or dislikes (e.g. "prefers dark mode").fact- Objective information (e.g. "uses macOS").decision- Choices made (e.g. "chose the new billing provider").context- Background information (e.g. "working on e-commerce app").
preference, fact, decision, context Hard isolation boundary. When provided, search runs only inside that scope. Omit to search only unscoped/global memories.
200Filter results to a specific project within the selected scope.
Search strictness. Higher values return broader matches. Use 0.6
as the default unless you have tested a different value.
0 <= x <= 1Response
Ranked search results.
Number of results returned.
Hide child attributes
Hide child attributes
Relevance score from 0 (least relevant) to 1 (most relevant).
0 <= x <= 1preference- User likes or dislikes (e.g. "prefers dark mode").fact- Objective information (e.g. "uses macOS").decision- Choices made (e.g. "chose the new billing provider").context- Background information (e.g. "working on e-commerce app").
preference, fact, decision, context