vaas-x
Episodic memory that persists, for AI agents and connected devices. It keeps what happened, what was done and how it turned out, and brings back what worked.
pip install vaas-x gives any device or agent a persistent, queryable
record of what it has seen: what happened, what it did, what the outcome
was. It retrieves the closest matching past episode in milliseconds, on
CPU, with no cloud round-trip required for the actual similarity search.
Install
pip install vaas-x
Get a free API key at vaasx.com: an email address, no card.
Quickstart
from vaasx import Bootstrap
brain = Bootstrap(api_key="...", device_id="my_device")
# Point it at a structured data stream (sensor readings, agent actions,
# API events: anything JSON-shaped) and it profiles the stream
# automatically, no schema design required.
brain.connect("https://your-data-stream.com/events")
# Query for the most similar past episodes, ranked by what actually
# worked, not just what is nearest in vector space.
hits = brain.query("engine running hot", k=5, prefer_success=True)
An agent that already knows its own outcome the moment it acts can log a full state/action/outcome episode in one call instead of a separate ingest-then-tag-later round trip:
resp = brain.ingest([{
"state": {"observation": observation},
"action": {"taken": action},
"outcome": {"success": result.success},
}])
episode_id = resp["episode_ids"][0]
Prefer no code? Use the connector
If you use Claude, Cursor, VS Code or another agent that supports MCP, you
do not need this package. Add https://mcp.vaasx.com/mcp as a remote MCP
server and the agent gets the same memory, with no key to paste. Whether an
agent uses its memory without being asked depends on the agent. You can see
and manage everything it remembers at app.vaasx.com
(sign in with an emailed code).
What the connectors read
A web address, file, WebSocket or MQTT topic can hold more than numbers, and the SDK looks at each record before it decides what to do with it (the "scout"):
- Numbers and true/false are profiled and classified as sensor channels, as before.
- Text, descriptions, titles, timestamps, ids and nested values are kept with their values in a readable episode, so an agent that recalls it can read it. Long text is split into parts.
- A web address can return JSON, an RSS or Atom feed, or a plain text or HTML page.
- A record that repeats exactly, such as a feed polled again with no new stories, is stored once. A numeric reading is never skipped. Pass
dedupe=Falsetoconnect()to turn this off.
Say what the fields mean
A feed gives names, not meanings: GitHub's watchers_count is the star count, and the real watchers are subscribers_count. Say what your fields mean once and every agent that recalls
the device reads the meaning next to the value:
brain.describe_fields({
"watchers_count": "the star count (an old GitHub name); real watchers are subscribers_count",
"size": "repository size in kilobytes",
})
# or as the source is connected
brain.connect("https://api.github.com/repos/VAAS-X/vaas-x", interval_s=60, field_notes={"size": "repository size in kilobytes"})
describe_fields() adds to what is there (replace=True makes it the whole dictionary; a blank meaning removes a note), field_notes() reads it and clear_field_notes() removes it.
Only the owner's key can change it: an agent connected through the MCP connector cannot. You can also edit it in the app, with the Fields button on a device.
Rate limits
The service limits how many requests one key can make in a minute (60 on Free, more on paid plans). When a request is refused for that reason, the SDK waits and tries again, for up to about a minute in total, before it raises an error. A request refused because your plan's note limit is full is never retried. Use Bootstrap(..., max_retries=0) to fail at once.
What it does
- Profiles a raw data stream automatically: statistical profiling, schema classification and anomaly detection all run locally before anything touches the network.
- Stores episodes as (state, action, outcome) triples, so retrieval can be weighted toward what worked last time in a similar situation, not just nearest by embedding distance.
- Runs on both a small edge device and a standard server: same codebase, no domain-specific build.
When files stop being enough
If one agent on one machine is all you have, a markdown file is a fine place to start. A memory service earns its place when several agents need the same memory, when facts change mid-project, and when you want recall ranked by what worked. Every published result has a reproduction guide you can run yourself: vaasx.com/guides. Comparisons: Mem0, Supermemory, a vector database.
Tiers
Free gets you an API key instantly (10,000 episodes, 500 queries a day, 1 device). Personal (£9.99 a month) adds the app, 50,000 notes, unlimited searches and 3 devices. Developer and Professional are self-serve SDK tiers with higher episode and device limits. Enterprise is contract-based, for teams wanting on-prem or air-gapped deployment. See vaasx.com/pricing for current details.
The honest caveat
This package ships as a compiled wheel, not source-available. The retrieval and indexing internals are proprietary and protected as a trade secret, not through patent filing. What is open: full API documentation, working examples, and the wire format, so you can see exactly what goes in and comes back even without reading the internals.
Multimodal support (vision/audio/depth/thermal, via the optional ac
extra) is real but still early: encoder models are in active training
and not yet production-tuned; treat it as a preview, not a finished
feature.
Links
License
Proprietary -- see LICENSE.
Metadata
Release files for vaas-x 0.1.16
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
Total release size: 14.0 MB
Release files / vaas_x-0.1.16-cp314-cp314-win_amd64.whl
| Download URL | vaas_x-0.1.16-cp314-cp314-win_amd64.whl |
|---|---|
| Size | 446.3 kB |
| Tags | CPython 3.14 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
f35cc8bf1ac03adb448480bc348385c5a1bd6f3742091b68b77a23b0fa75483a
|
|
BLAKE2b-256 checksum How to use checksums |
15d09369e210871c6420fd05c5ce7e7229db6201a9b4b73c3c1ea79aadf2fe75
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / vaas_x-0.1.16-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl
| Download URL | vaas_x-0.1.16-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 2.6 MB |
| Tags | CPython 3.14 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
e0fda7f7ac7b761bfce1c2747facb84390d4ff47b4deb9ab4bd671bc7a60bdde
|
|
BLAKE2b-256 checksum How to use checksums |
fc2b780c8b99d6abce03252a778ba733504dd6a583a49f257d6a51667b3d0219
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / vaas_x-0.1.16-cp313-cp313-win_amd64.whl
| Download URL | vaas_x-0.1.16-cp313-cp313-win_amd64.whl |
|---|---|
| Size | 444.6 kB |
| Tags | CPython 3.13 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
9a92ad3f124b02aefe9261be45575ad8500f2bf52bced892d46b0a0f40ae0174
|
|
BLAKE2b-256 checksum How to use checksums |
51c87c9f8d3d956adaad09a7352650fd06736572d556af610b17e7d765ddb34d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / vaas_x-0.1.16-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl
| Download URL | vaas_x-0.1.16-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 2.7 MB |
| Tags | CPython 3.13 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
aa10f5e96f508ca98b377d23cf0a483609d56e75b6e09a8aa92cb9e04a5cb085
|
|
BLAKE2b-256 checksum How to use checksums |
972d0f5947664f8db00f08e0dae92d94ad2bdaed60636bd6b7998f5c91ed74fd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / vaas_x-0.1.16-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl
| Download URL | vaas_x-0.1.16-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 2.7 MB |
| Tags | CPython 3.12 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
137e68db87a731e9ee33ef132672f50d3eaa0f61a6c9671d531996ae0f005276
|
|
BLAKE2b-256 checksum How to use checksums |
35979f4e05b1db285e65db3352036c31191ef46dbde188ba4957a645cd05ea91
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / vaas_x-0.1.16-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl
| Download URL | vaas_x-0.1.16-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 2.6 MB |
| Tags | CPython 3.11 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
e6a74b8708bb74a1d1ae7ddb3d22d0c121e284818dedb52a06a24edd9bb86d42
|
|
BLAKE2b-256 checksum How to use checksums |
88032594c7da2376a63065f2edeb49d936f92002f14e105ff8b8043c774e0a61
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / vaas_x-0.1.16-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl
| Download URL | vaas_x-0.1.16-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 2.5 MB |
| Tags | CPython 3.10 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
fe9cdd7c62059d3789ad8a88feb7e96ac0637440fc1a2dc0eb8cdef2353c9a8c
|
|
BLAKE2b-256 checksum How to use checksums |
05125509918f2eb76c6829d8b6542892066427e956fdc00b2a7165079f1042bf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Security for vaas-x 0.1.16
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.