Python client for Memnode, persistent memory for AI agents
Project description
memnode (Python)
Python client for Memnode, persistent memory for AI agents.
- Stdlib-only — no runtime dependencies (uses
urllib,json). - Wraps the v1 endpoints exposed by the Rust data plane.
- Typed response dataclasses.
Quickstart and proof
If you land on this package page first, use this order:
- Install + proof loop: https://memnode.dev/mcp
- Public demo article: https://memnode.dev/articles/claude-code-memory-demo
- Downloadable 14-second proof loop: https://memnode.dev/article-images/mcp-demo-loop.mp4
- Hosted docs: https://memnode.dev/docs
The shortest believable Memnode loop is still MCP-first:
- teach Claude Code one repo convention
- start a fresh task or later session
- recall it and inspect lineage
Install
Published package:
pip install memnode
Local development:
cd clients/python
pip install -e .
Usage
from memnode import MemnodeClient
client = MemnodeClient("https://api.memnode.dev", "mn_live_...")
result = client.recall("Where is the user moving?")
print(result.answer, result.confidence)
for hit in result.supporting_memories:
print(hit.node_id, hit.props.get("summary"), hit.score)
query = client.query(
"Observation",
filter={
"_memory_status": {"$in": ["supported", "canonical"]},
"_support_count": {"$gte": 3},
},
limit=10,
)
print(query.nodes[0].props.get("summary"))
client.feedback(memory_id=result.supporting_memories[0].node_id, helpful=True)
health = client.healthz()
print(health.ok)
Compatibility import still works:
from memnode_client import MemnodeClient
For the shortest proof loop, start with the local MCP path first and keep this package for hosted or app-backend use.
Endpoints
| Method | HTTP | Notes |
|---|---|---|
recall |
POST /v1/recall |
Returns typed RecallResponse |
feedback |
POST /v1/feedback |
Mark a supporting memory helpful / not helpful |
explain |
POST /v1/explain |
Raw JSON with per-edge scoring |
query |
POST /v1/query |
Structured query for memory inspection |
record_procedure |
POST /v1/procedures |
Persist a trigger → action-sequence procedure |
recall_procedures |
GET /v1/procedures |
Retrieve procedures, optionally by trigger |
memory_lineage |
GET /v1/lineage/{id} |
CORRECTS / SUPERSEDES / DERIVED_FROM chain |
healthz |
GET /healthz |
Liveness probe |
status |
GET /v1/status |
Control-plane lease + data-plane counters |
Recording raw observations over HTTP is not yet supported server-side. Until
POST /v1/record ships, use the MCP transport to record memories.
Errors
All errors inherit from MemnodeError:
MemnodeAuthError— 401/403MemnodeRateLimitError— 429, carriesretry_afterseconds when the server returns aRetry-AfterheaderMemnodeUnavailableError— 503 (control-plane lease gone, data plane shutting down, etc.)MemnodeHTTPError— other non-2xx responses, carriesstatusandbody
Tests
PYTHONPATH=clients/python python -m unittest discover clients/python/tests
Tests spin up an in-process http.server on a random port and drive the client
end-to-end — no mocks, no fixtures.
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 memnode-0.1.0.tar.gz.
File metadata
- Download URL: memnode-0.1.0.tar.gz
- Upload date:
- Size: 9.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8551238eaff5c2dc421e6aa2b368054afaefa2a2551c2d34e15da3b5a6f6ddd7
|
|
| MD5 |
a39202a1e3da91e1669b1fb52dd0aadf
|
|
| BLAKE2b-256 |
20596070a0814e6d4bf0ec8096e767891d456e234be7d79c18f48e2bae09c3dc
|
File details
Details for the file memnode-0.1.0-py3-none-any.whl.
File metadata
- Download URL: memnode-0.1.0-py3-none-any.whl
- Upload date:
- Size: 7.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e90fe68ee6ec12f8b143fe9b76f6f0d9bdd71cc28225e8f8b1598ff462e64ab1
|
|
| MD5 |
6f0054eccd8218f920e588cff399e02f
|
|
| BLAKE2b-256 |
5813d0eabe0e6443616d556242d039b26179de91d2e5fba8c1710cf556132109
|