Skip to main content

agenticwf-agent-client

The client of the AgenticWF agent: the Python AgentClient and the agenticwf agent command (with agenticwf-auth-client, installed with it).

pip install agenticwf-agent-client
agenticwf agent chat "hello"                      # a new chat; prints the reply
agenticwf agent chat "and then?" --session SID
agenticwf agent task "summarise run 42" --wait    # a background task
agenticwf agent approve CALL --session SID        # a tool call that waits for you

Only the agent's URL is needed: the agent tells how to sign in, and behind the AgenticWF server (Caddy, Logto) the server publishes the Logto settings. Sign in once with agenticwf login:

export AGENTICWF_AGENT_URL=https://host.example.org/app
agenticwf login

Scripts and CI use a personal access token instead (AGENTICWF_TOKEN=pat_…), or a machine client (AGENTICWF_CLIENT_ID + AGENTICWF_CLIENT_SECRET). AGENTICWF_AUTH_URL, AGENTICWF_API_URL, AGENTICWF_CLIENT_ID and AGENTICWF_RESOURCE, when set, take precedence over what the server publishes (an administrator gets them with docker exec agenticwf cat /var/lib/agenticwf/logto/clients.env).

The personal agent (agenticwf-agent serve) has its own token instead. On the same machine the URL is enough (the token is read from ~/.agenticwf-agent/token, or $AGENTICWF_AGENT_HOME); otherwise use the sign-in link it printed as the URL, or give the token:

export AGENTICWF_AGENT_URL=http://127.0.0.1:8765
export AGENTICWF_AGENT_URL='http://127.0.0.1:8765/?token=…'   # or: the sign-in link
export AGENTICWF_AGENT_TOKEN=…                                # or: the token (or _TOKEN_FILE)

From Python (AgentClient.from_env() finds the agent and its token as the command does):

from agenticwf.agent.client import AgentClient

with AgentClient.from_env() as agent:
    sid = agent.create_session("demo")["id"]
    print(agent.send(sid, "hello")["reply"])
    print(agent.wait_task(agent.submit_task("summarise run 42")["task_id"])["result"])

Metadata

Release files for agenticwf-agent-client 0.0.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agenticwf-agent-client 0.0.2
File Size Uploaded Provenance Actions
agenticwf_agent_client-0.0.2.tar.gz 9.4 kB Without provenance Details for agenticwf_agent_client-0.0.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for agenticwf-agent-client 0.0.2
File Interpreter ABI Platform Actions
agenticwf_agent_client-0.0.2-py3-none-any.whl Python 3 none any Details for agenticwf_agent_client-0.0.2-py3-none-any.whl

Total release size: 17.7 kB

Release files / agenticwf_agent_client-0.0.2.tar.gz

Download URL agenticwf_agent_client-0.0.2.tar.gz
Size 9.4 kB
Tags Source
SHA-256 checksum
How to use checksums
4a2d84f01d4829594e8a8cd401b05f2c0723f573177180f48e40d332fe77e033
BLAKE2b-256 checksum
How to use checksums
2b492a7ae4fc878df463460ab5816731563c36ff7297b13939e92e9706d06f19
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.15

Release files / agenticwf_agent_client-0.0.2-py3-none-any.whl

Download URL agenticwf_agent_client-0.0.2-py3-none-any.whl
Size 8.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e03aae2b715ff1e717cf4b4728e975589231014a9da227d72ec3d240c7738e29
BLAKE2b-256 checksum
How to use checksums
916bdd09847ae16aaccfc130acf7ec060c5fb0d0d8725b13658e780f12e8adc6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.15

Security for agenticwf-agent-client 0.0.2

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page