Python client for Amore agent memory — mem0-compatible API, Rust core via MCP
Project description
amore — Python client
mem0-compatible Python wrapper for Amore agent memory.
Install
pip install amore
Requires amore-mcp on PATH (install once via npm install -g amore-mcp).
Quick start
from amore import Memory
m = Memory()
# Store a memory
m.add("Alice prefers dark mode", user_id="alice")
# Recall
results = m.search("UI preferences", user_id="alice", limit=3)
for r in results:
print(r["memory"], r["score"])
# List all memories for a user
all_mems = m.get_all(user_id="alice")
# Delete
m.delete(all_mems[0]["id"])
m.close()
Context manager form:
with Memory() as m:
m.add("Bob uses vim", user_id="bob")
hits = m.search("editor", user_id="bob")
Migration from mem0
Replace from mem0 import Memory with from amore import Memory.
add, search, get_all, and delete have the same signatures.
Binary path override
m = Memory(binary="/usr/local/bin/amore-mcp")
License
Apache-2.0
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
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 amore-1.1.0.tar.gz.
File metadata
- Download URL: amore-1.1.0.tar.gz
- Upload date:
- Size: 5.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cd95d4a2d3d27e1271573aee8e8fca35575ddd1da9de318df73c31ab8eab3361
|
|
| MD5 |
583f237eed9320f608865c12f48715d8
|
|
| BLAKE2b-256 |
6c574e49dbd554a88ebf538d85d7a2ce3ddf1a1c8f1017552326a153f7d10f15
|
File details
Details for the file amore-1.1.0-py3-none-any.whl.
File metadata
- Download URL: amore-1.1.0-py3-none-any.whl
- Upload date:
- Size: 5.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
55022eb95b0a1cc5cd3bcc09d6dc293efbcb20e98849f46d136a9518954111c3
|
|
| MD5 |
48f17ca9a70deeee36c5c12081743dd4
|
|
| BLAKE2b-256 |
0f065aaf53cddfdec0a662858669eb8ea7516e1b5a71571488867b465ed733a9
|