Equos Python SDK
Equos.ai official Python SDK.
Prerequisites
- Go to Equos Studio.
- Create an organization.
- Create an API Key.
Installation
pip install equos
Features
- Official Python SDK for Equos.ai
- High-level
EquosClientgrouped by resource (brains,characters,faces,voices,conversations,knowledge_bases,organizations,tokens,health) - Sync and async variants for every endpoint
- Type-safe generated models for all request / response bodies
- Escape hatch to the low-level generated client for full
httpxcustomization
Quick Start
import os
from equos import EquosClient
client = EquosClient(api_key=os.environ["EQUOS_API_KEY"])
# Health check
print(client.health.check())
# List the first 20 brains
print(client.brains.list())
You don't have an API key? Create one here.
Configuration
By default the client targets https://api.equos.ai. Override the endpoint via EquosOptions:
from equos import EquosClient, EquosOptions
client = EquosClient(
api_key=os.environ["EQUOS_API_KEY"],
options=EquosOptions(endpoint="https://develop-api.equos.ai"),
)
API Groups
Every group is available on the EquosClient instance. Each method has an async counterpart suffixed with _async.
client.brains
| Method | Description |
|---|---|
list(take=20, skip=0, client_query=UNSET) |
List brains |
get(id) |
Get a brain by id |
create(body) |
Create a brain (CreateEquosBrainRequest) |
update(id, body) |
Update a brain (CreateEquosBrainRequest) |
delete(id) |
Delete a brain |
client.characters
| Method | Description |
|---|---|
list(take=20, skip=0, client_query=UNSET) |
List characters |
get(id) |
Get a character |
create(body) |
Create a character (CreateEquosCharacterRequest) |
update(id, body) |
Update a character (UpdateEquosCharacterRequest) |
delete(id) |
Delete a character |
client.faces
| Method | Description |
|---|---|
list(take=20, skip=0, client_query=UNSET) |
List faces |
get(id) |
Get a face |
create(body) |
Create a face (CreateEquosFaceRequest) |
delete(id) |
Delete a face |
client.voices
| Method | Description |
|---|---|
list(take=20, skip=0, client_query=UNSET) |
List voices |
get(id) |
Get a voice |
create(body) |
Create a voice (CreateEquosVoiceRequest) |
update(id, body) |
Update a voice (CreateEquosVoiceRequest) |
delete(id) |
Delete a voice |
client.conversations
| Method | Description |
|---|---|
list(take=20, skip=0, client_query=UNSET) |
List conversations |
get(id) |
Get a conversation |
start(body) |
Start a conversation (CreateEquosConversationRequest) |
stop(id) |
Stop a conversation |
client.knowledge_bases
| Method | Description |
|---|---|
list(take=20, skip=0, client_query=UNSET) |
List knowledge bases |
get(id) |
Get a knowledge base |
create(body) |
Create a knowledge base (CreateKnowledgeBaseRequest) |
delete(id) |
Delete a knowledge base |
add_document(id, body) |
Add a document (CreateDocumentRequest) |
index_document(id, doc) |
Index a document |
delete_document(id, doc) |
Delete a document |
client.organizations
| Method | Description |
|---|---|
get_freemium_usage() |
Get the freemium usage for the current org |
client.tokens
| Method | Description |
|---|---|
create(body) |
Create a short-lived access token (CreateEquosTokenRequest) |
client.health
| Method | Description |
|---|---|
check() |
Health check |
Examples
Create and Fetch a Brain
from equos import EquosClient
from equos.models import CreateEquosBrainRequest
client = EquosClient(api_key="YOUR_API_KEY")
created = client.brains.create(CreateEquosBrainRequest(name="My Brain"))
print(created.id, created.name)
fetched = client.brains.get(created.id)
print(fetched)
Start a Conversation
from equos import EquosClient
from equos.models import CreateEquosConversationRequest
client = EquosClient(api_key="YOUR_API_KEY")
conversation = client.conversations.start(
CreateEquosConversationRequest(character_id="chr_...")
)
print(conversation.id, conversation.token)
Async Usage
Every method has an _async variant that returns a coroutine:
import asyncio
from equos import EquosClient
async def main():
client = EquosClient(api_key="YOUR_API_KEY")
brains = await client.brains.list_async(take=50)
print(brains)
asyncio.run(main())
Pagination and Filtering
list* endpoints accept take, skip, and client_query:
page = client.characters.list(take=50, skip=0, client_query="external-user-123")
Models and Types
All generated request / response models are re-exported for convenience:
from equos.models import (
CreateEquosBrainRequest,
CreateEquosCharacterRequest,
CreateEquosConversationRequest,
CreateEquosFaceRequest,
CreateEquosVoiceRequest,
CreateKnowledgeBaseRequest,
CreateDocumentRequest,
CreateEquosTokenRequest,
# ...and all response models
)
from equos.types import UNSET, Unset, Response
Low-Level Client
For fine-grained control or endpoints not yet surfaced on EquosClient, use the generated client directly:
from equos.client import AuthenticatedClient
from equos.client.api.brain import get_brain
auth_client = AuthenticatedClient(
base_url="https://api.equos.ai",
token="YOUR_API_KEY",
auth_header_name="x-api-key",
prefix="",
)
with auth_client as c:
brain = get_brain.sync(id="brain_id", client=c)
print(brain)
Each generated endpoint module exposes four callables:
sync(...)— parsed response, orNonesync_detailed(...)—Response[Parsed]with status / headers / contentasyncio(...)/asyncio_detailed(...)— async variants
Advanced httpx Customization
import httpx
from equos.client import AuthenticatedClient
auth_client = AuthenticatedClient(
base_url="https://api.equos.ai",
token="YOUR_API_KEY",
auth_header_name="x-api-key",
prefix="",
httpx_args={"timeout": 30.0, "proxies": "http://localhost:8030"},
)
# Or swap in your own httpx.Client
auth_client.set_httpx_client(httpx.Client(base_url="https://api.equos.ai"))
Changelog
See Releases for version history.
Other Equos SDKs
| SDK | Platform | Package |
|---|---|---|
| @equos/browser-sdk | Browser (vanilla JS/TS) | npm |
| @equos/react | Browser (React) | npm |
| @equos/node-sdk | Node.js (server-side only) | npm |
| equos | Python (server-side only) | PyPI |
Reach Us
- Equos Slack Community: Join Equos Community Slack
- Support: Support Form
Documentation
- Official Documentation: https://docs.equos.ai
- Equos NodeJS Examples: https://github.com/EquosAI/equos-examples/tree/main/examples/equos-nextjs-integration
- Equos React Examples: https://github.com/EquosAI/equos-examples/blob/main/examples/equos-react-integration/README.md
Authors
Release files for equos 3.1.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| equos-3.1.5.tar.gz | 32.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| equos-3.1.5-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 128.8 kB
Release files / equos-3.1.5.tar.gz
| Download URL | equos-3.1.5.tar.gz |
|---|---|
| Size | 32.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0ebbb76f9063b55e60dba1b8fb279e61c2a9970746ea9bbd60f5453a0babb181
|
|
BLAKE2b-256 checksum How to use checksums |
555ced1fc0b44cd55bf82867fc6e17e843aebe53a468d5eefaf7ee778d5b7cf2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Apr 21, 2026.
Transparency logRelease files / equos-3.1.5-py3-none-any.whl
| Download URL | equos-3.1.5-py3-none-any.whl |
|---|---|
| Size | 96.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
eba367405c6953b7c64b2f4428b286086319ad97be79e0a577900d2fedc24815
|
|
BLAKE2b-256 checksum How to use checksums |
0664517fd19c0452f89e5bbef3473363a7431bcef53d23ae7ee051879fc4714d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Apr 21, 2026.
Transparency log