Skip to main content

Jentic SDK [Beta]

Jentic SDK is a comprehensive library for discovery and execution of APIs and workflows.

The Jentic SDK is backed by the data in the Jentic Public APIs repository.

Core API & Use Cases

The main entry point is the Jentic class.

Quick Start – search → load → execute

import asyncio
from jentic import Jentic, SearchRequest, LoadRequest, ExecutionRequest

async def main():
    client = Jentic()

    # 1️⃣ find a capability
    results = await client.search(SearchRequest(query="send a Discord DM"))
    entity_id = search.results[0].id  # op_... or wf_...

    # 2️⃣ load details (inspect schemas / auth, see inputs for operations)
    resp = await client.load(LoadRequest(ids=[entity_id]))
    inputs = resp.tool_info[entity_id].inputs

    # 3️⃣ run it
    result = await client.execute(
        ExecutionRequest(id=entity_id, inputs={"recipient_id": "123", "content": "Hello!"})
    )
    print(result)

asyncio.run(main())

LLM Tool Definition & Execution

A typical agent loop with tool use looks like this:

from jentic.lib.agent_runtime import AgentToolManager

manager = AgentToolManager(format="anthropic")
llm_tools = manager.generate_tool_definitions()  # pass to your LLM

# --- within your agent loop ---
while response.stop_reason == "tool_use":
    tool_call = next(b for b in response.content if b.type == "tool_use")
    name      = tool_call.name
    inputs    = tool_call.input

    result = await manager.execute_tool(name, inputs)
    # ... handle result ...

Components

agent_runtime

A library for generating, managing, and executing LLM-compatible tools from Arazzo workflows and OpenAPI operations.

Features:

  • Generate dynamic tool definitions for OpenAI and Anthropic LLMs from project workflows and API operations
  • Execute workflows and operations as tools via a unified interface
  • Provide runtime classes for tool management (AgentToolManager), tool specification (LLMToolSpecManager), and execution (TaskExecutor)
  • Return standardized results for workflow and operation execution

api

A client for the Jentic API Knowledge Hub.

Set JENTIC_API_URL to set the base URL for the API hub client for local testing or testing against the development environment.

Installation

For Development

To install the package in development mode:

# From the current directory
pip install -e .

Then you can import it in your projects:

import jentic

You can also import it to other projects by referencing the package directory by specifying the following in your pyproject.toml:

dependencies = [
    "jentic @ file:///path/to/jentic/sdk"
]

For Production

pip install jentic

API Key

See the root README for instructions on creating an agent and exporting your JENTIC_AGENT_API_KEY. Remember to set it in the environment before running any examples.

Testing

# Run unit tests for jentic
pdm run test

# Run integration tests for dev environment
pdm run integration-dev

# Run integration tests for production environment
pdm run integration

Integration Test Configuration

Integration tests require environment variables to be set in environment-specific files. An example file is provided that you need to copy and configure:

# For development testing
cp tests/integration/.env.example tests/integration/.env.dev

# For production testing
cp tests/integration/.env.example tests/integration/.env.prod

After copying, edit these files to include your API credentials and configuration:

  1. For development testing: tests/integration/.env.dev
  2. For production testing: tests/integration/.env.prod

Example configuration:

# Required UUIDs for Discord API testing
DISCORD_GET_MY_USER_OPERATION_UUID="your_operation_uuid_here"
DISCORD_GET_USER_DETAILS_WORKFLOW_UUID="your_workflow_uuid_here"

# Base URL for Jentic API (Uncomment for Dev)
JENTIC_API_URL=https://directory-api.qa1.eu-west-1.jenticdev.net

# Your Discord bot token
DISCORD_BOTTOKEN="your_bot_token_here"

The integration tests validate:

  1. Loading operation and workflow execution information
  2. Executing Discord operations and workflows
  3. Searching API capabilities
  4. Generating LLM tool definitions
  5. Running LLM tools including both operations and workflows

Linting & Formatting

# Run all linting for jentic
pdm run lint

Metadata

Release files for jentic 0.10.0

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

Source distribution (sdist)

Source distribution for jentic 0.10.0
File Size Uploaded
jentic-0.10.0.tar.gz 56.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for jentic 0.10.0
File Interpreter ABI Platform
jentic-0.10.0-py3-none-any.whl Python 3 none any Details

Total release size: 97.7 kB

Release files / jentic-0.10.0.tar.gz

Download URL jentic-0.10.0.tar.gz
Size 56.8 kB
Tags Source
SHA-256 checksum
How to use checksums
4bec8b7549c44005c861f930085aa78dcc12605ee23ae65dd48b0145f8029d39
BLAKE2b-256 checksum
How to use checksums
f3d203a27712812c328ff1d4c7ad54d872564cb7c2a6af96817b95bfb1d1acf8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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 Feb 24, 2026.

Transparency log

Release files / jentic-0.10.0-py3-none-any.whl

Download URL jentic-0.10.0-py3-none-any.whl
Size 40.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
78c89e42fed8b634134e4ff9417ae3f3919453def9e1f511fb3bf467e8a25d07
BLAKE2b-256 checksum
How to use checksums
81170f5575d901a94f77e917bb817fc9fdf858bdde7eb0b5438854d4371895cc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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 Feb 24, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.10.0 This release

2 release files

0.9.8

2 release files

0.9.7

2 release files

0.9.6

2 release files

0.9.5

2 release files

0.9.4

2 release files

0.9.3

2 release files

0.9.2

2 release files

0.9.1

2 release files

0.9.0

2 release files

0.8.4

2 release files

0.8.3

2 release files

0.8.2

2 release files

0.8.1

2 release files

0.8.0

2 release files

0.7.14

2 release files

0.7.11

2 release files

0.7.10

2 release files

0.7.9

2 release files

0.7.8

2 release files

0.7.7

2 release files

0.7.6

2 release files

0.7.5

2 release files

0.7.4

2 release files

0.7.3

2 release files

0.7.2

2 release files

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