Skip to main content

BindAI Agent

bindai-agent provides the agent layer of the BindAI framework.

It contains the core abstractions for creating, configuring, executing, and coordinating AI agents, including agent builders, configuration, state, delegation, registries, and agent teams.

Features

  • Agent creation and execution
  • Structured agent configuration
  • Agent builders
  • Agent state management
  • Agent registries
  • Agent delegation
  • Agent teams and team delegation
  • Assistant agents
  • YAML-based agent creation
  • Agent execution results

Public API

The package exposes the following primary components:

from bindai_agent import (
    Agent,
    AssistantAgent,
    AgentBuilder,
    AgentConfiguration,
    AgentDelegationTool,
    AgentRegistry,
    AgentResult,
    AgentState,
    AgentTeam,
    AgentTeamDelegationTool,
    create_agent,
    create_agent_from_yaml,
)

Basic Usage

Agents can be created using the builder API:

from bindai_agent import Agent

agent = Agent.builder().name("assistant").instructions("You are a helpful AI assistant.").build()

result = agent.run("Explain what BindAI is.")

print(result.output)

Factory Functions

The package also provides factory functions for creating agents:

from bindai_agent import create_agent

agent = create_agent(
    name="assistant",
    instructions="You are a helpful AI assistant.",
)

Agents can also be created from YAML configuration:

from bindai_agent import create_agent_from_yaml

agent = create_agent_from_yaml("agent.yaml")

Agent Delegation

Agents can delegate work to other agents through the delegation APIs provided by the package.

from bindai_agent import Agent, AgentDelegationTool

# Agent delegation capabilities are provided by the
# BindAI agent execution system.

For more advanced delegation and coordination patterns, see the BindAI documentation.

Agent Teams

AgentTeam and AgentTeamDelegationTool provide the foundation for coordinating multiple agents as part of a team.

from bindai_agent import AgentTeam

Agent teams are part of BindAI's broader multi-agent architecture.

Architecture

bindai-agent sits above the lower-level BindAI core components and provides the agent-specific execution layer.

Conceptually:

BindAI
  │
  ├── bindai-agent
  │     ├── Agents
  │     ├── Agent configuration
  │     ├── Agent state
  │     ├── Delegation
  │     └── Agent teams
  │
  └── BindAI Core
        ├── Execution
        ├── Context
        ├── Events
        └── Tools

The main bindai package builds on this agent layer together with the other BindAI components.

Documentation

For complete framework documentation, visit the BindAI documentation:

https://docs.bindai.dev

Development

This package is part of the BindAI workspace.

From the repository root:

uv sync
uv run pytest

To run the agent package tests specifically:

uv run pytest packages/bindai-agent/tests -q

License

BindAI is released under the MIT License.

Release files for bindai-agent 0.1.2

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

Source distribution (sdist)

Source distribution for bindai-agent 0.1.2
File Size Uploaded
bindai_agent-0.1.2.tar.gz 23.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for bindai-agent 0.1.2
File Interpreter ABI Platform
bindai_agent-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 53.6 kB

Release files / bindai_agent-0.1.2.tar.gz

Download URL bindai_agent-0.1.2.tar.gz
Size 23.6 kB
Tags Source
SHA-256 checksum
How to use checksums
2f27a24355134c867d7474d6678279f41336c0668e17c840f909a0962b6bd8da
BLAKE2b-256 checksum
How to use checksums
273939d1bce0994fde9eb720f3706f0bb261558ac64065dd1bd692ee523cd71a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release files / bindai_agent-0.1.2-py3-none-any.whl

Download URL bindai_agent-0.1.2-py3-none-any.whl
Size 30.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
78051c014102a76ccfb9d15cc29f834914907111050b5ff15bf2ae71f0dba022
BLAKE2b-256 checksum
How to use checksums
aa4cdae94653a747c114b3ce396af5f3b004de9fb8beb13a5633545bf7e9af03
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release history Release notifications | RSS feed

0.2.0

2 release files

This release

0.1.2 This release

2 release files

0.1.1

2 release files

0.1.0

1 release file

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