Memory layer and SDK for LLMs
Project description
Reca11 — Memory Layer for LLMs
Reca11 is a plug-and-play memory layer for your LLM apps. It captures three key aspects of every conversation — recent history, core facts, and evolving themes — delivering a complete memory system through a simple API.
Installation
pip install recall-core
⸻
Generate an API Key
Visit https://reca11-memory.onrender.com
Click the “Generate API Key” button to instantly receive your key.
⸻
Quickstart
from reca11 import Reca11
rc = Reca11(
api_key="your-api-key",
openai_key="your-openai-key",
project_name="my-project"
)
chat_pair = {
"user": "What did I say I wanted to build?",
"assistant": "You said you wanted to build a memory SDK for LLMs."
}
memory = rc.recall(chat_pair)
print(memory)
⸻
Health Check
To verify the backend is running, visit:
GET https://reca11-memory.onrender.com/health
Expected response:
{ "status": "ok" }
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
recall_core-0.1.0.tar.gz
(12.5 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file recall_core-0.1.0.tar.gz.
File metadata
- Download URL: recall_core-0.1.0.tar.gz
- Upload date:
- Size: 12.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0f57b793496a1d6a6887f1d336260140fdc38f5f28dbe85a3cc6f3e0b8e81d5d
|
|
| MD5 |
e77850c0328058f5aa2118e0ec62fe91
|
|
| BLAKE2b-256 |
a088b78e9000d6a9afd52c8e61dafec5e5d5e8b55d02de77a3208618ad5f48b7
|
File details
Details for the file recall_core-0.1.0-py3-none-any.whl.
File metadata
- Download URL: recall_core-0.1.0-py3-none-any.whl
- Upload date:
- Size: 14.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2da5ccb3e8194310fa1cbe6ded50109a770c7de04d6add63e41fc0b8e01a17b6
|
|
| MD5 |
03116aaedcf92defb05d634fb87866f1
|
|
| BLAKE2b-256 |
4746059747f31423db42593ccf54afb9acb52db05c880ad34630b66e6329fff3
|