> ## Documentation Index > Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt > Use this file to discover all available pages before exploring further. # autogen.agentchat.contrib.captainagent.AgentBuilder

AgentBuilder

```python theme={null} AgentBuilder( config_file_or_env: str | None = 'OAI_CONFIG_LIST', config_file_location: str | None = '', llm_config: LLMConfig | dict[str, Any] | None = None, builder_model: str | list | None = [], agent_model: str | list | None = [], builder_model_tags: list | None = [], agent_model_tags: list | None = [], max_agents: int | None = 5 ) ``` AgentBuilder can help user build an automatic task solving process powered by multi-agent system.
Specifically, our building pipeline includes initialize and build.
(These APIs are experimental and may change in the future.) Parameters: | Name | Description | | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | | `config_file_or_env` | **Type:** str \| None

**Default:** 'OAI\_CONFIG\_LIST' | | `config_file_location` | **Type:** str \| None

**Default:** '' | | `llm_config` | **Type:** [LLMConfig](/docs/api-reference/autogen/llm_config/LLMConfig) \| dict\[str, typing.Any] \| None

**Default:** None | | `builder_model` | **Type:** str \| list \| None

**Default:** \[] | | `agent_model` | **Type:** str \| list \| None

**Default:** \[] | | `builder_model_tags` | **Type:** list \| None

**Default:** \[] | | `agent_model_tags` | **Type:** list \| None

**Default:** \[] | | `max_agents` | **Type:** int \| None

**Default:** 5 | ### Class Attributes #### AGENT\_DESCRIPTION\_PROMPT

#### AGENT\_NAME\_PROMPT

#### AGENT\_SEARCHING\_PROMPT

#### AGENT\_SELECTION\_PROMPT

#### AGENT\_SYS\_MSG\_PROMPT

#### CODING\_AND\_TASK\_SKILL\_INSTRUCTION

#### CODING\_PROMPT

#### DEFAULT\_DESCRIPTION

#### DEFAULT\_PROXY\_AUTO\_REPLY

#### GROUP\_CHAT\_DESCRIPTION

#### online\_server\_name

### Instance Methods #### build ```python theme={null} build( self, building_task: str, default_llm_config: LLMConfig | dict[str, Any], coding: bool | None = None, code_execution_config: dict[str, Any] | None = None, use_oai_assistant: bool | None = False, user_proxy: ConversableAgent | None = None, max_agents: int | None = None, **kwargs: Any ) -> tuple[list[ConversableAgent], dict[str, Any]] ``` Auto build agents based on the building task.
Parameters: | Name | Description | | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `building_task` | instruction that helps build manager (gpt-4) to decide what agent should be built.

**Type:** str | | `default_llm_config` | specific configs for LLM (e.g., config\_list, seed, temperature, ...).

**Type:** [LLMConfig](/docs/api-reference/autogen/llm_config/LLMConfig) \| dict\[str, typing.Any] | | `coding` | use to identify if the user proxy (a code interpreter) should be added.

**Type:** bool \| None

**Default:** None | | `code_execution_config` | specific configs for user proxy (e.g., last\_n\_messages, work\_dir, ...).

**Type:** dict\[str, typing.Any] \| None

**Default:** None | | `use_oai_assistant` | use OpenAI assistant api instead of self-constructed agent.

**Type:** bool \| None

**Default:** False | | `user_proxy` | user proxy's class that can be used to replace the default user proxy.

**Type:** [ConversableAgent](/docs/api-reference/autogen/ConversableAgent) \| None

**Default:** None | | `max_agents` | Maximum number of agents to create for the task.

If None, uses the value from self.max\_agents.

**Type:** int \| None

**Default:** None | | `**kwargs` | Additional arguments to pass to \_build\_agents.

- agent\_configs: Optional list of predefined agent configurations to use.

**Type:** Any | Returns: | Type | Description | | ------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------- | | tuple\[list\[[ConversableAgent](/docs/api-reference/autogen/ConversableAgent)], dict\[str, typing.Any]] | agent\_list: a list of agents. cached\_configs: cached configs. |
#### build\_from\_library ```python theme={null} build_from_library( self, building_task: str, library_path_or_json: str, default_llm_config: LLMConfig | dict[str, Any], top_k: int = 3, coding: bool | None = None, code_execution_config: dict[str, Any] | None = None, use_oai_assistant: bool | None = False, embedding_model: str | None = 'all-mpnet-base-v2', user_proxy: ConversableAgent | None = None, **kwargs: Any ) -> tuple[list[ConversableAgent], dict[str, Any]] ``` Build agents from a library.
The library is a list of agent configs, which contains the name and system\_message for each agent.
We use a build manager to decide what agent in that library should be involved to the task.
Parameters: | Name | Description | | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `building_task` | instruction that helps build manager (gpt-4) to decide what agent should be built.

**Type:** str | | `library_path_or_json` | path or JSON string config of agent library.

**Type:** str | | `default_llm_config` | specific configs for LLM (e.g., config\_list, seed, temperature, ...).

**Type:** [LLMConfig](/docs/api-reference/autogen/llm_config/LLMConfig) \| dict\[str, typing.Any] | | `top_k` | number of results to return.

**Type:** int

**Default:** 3 | | `coding` | use to identify if the user proxy (a code interpreter) should be added.

**Type:** bool \| None

**Default:** None | | `code_execution_config` | specific configs for user proxy (e.g., last\_n\_messages, work\_dir, ...).

**Type:** dict\[str, typing.Any] \| None

**Default:** None | | `use_oai_assistant` | use OpenAI assistant api instead of self-constructed agent.

**Type:** bool \| None

**Default:** False | | `embedding_model` | a Sentence-Transformers model use for embedding similarity to select agents from library.

As reference, chromadb use "all-mpnet-base-v2" as default.

**Type:** str \| None

**Default:** 'all-mpnet-base-v2' | | `user_proxy` | user proxy's class that can be used to replace the default user proxy.

**Type:** [ConversableAgent](/docs/api-reference/autogen/ConversableAgent) \| None

**Default:** None | | `**kwargs` | Additional arguments to pass to \_build\_agents.

**Type:** Any | Returns: | Type | Description | | ------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------- | | tuple\[list\[[ConversableAgent](/docs/api-reference/autogen/ConversableAgent)], dict\[str, typing.Any]] | agent\_list: a list of agents. cached\_configs: cached configs. |
#### clear\_agent ```python theme={null} clear_agent( self, agent_name: str, recycle_endpoint: bool | None = True ) -> ``` Clear a specific agent by name.
Parameters: | Name | Description | | ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `agent_name` | the name of agent.

**Type:** str | | `recycle_endpoint` | trigger for recycle the endpoint server.

If true, the endpoint will be recycled when there is no agent depending on.

**Type:** bool \| None

**Default:** True |
#### clear\_all\_agents ```python theme={null} clear_all_agents(self, recycle_endpoint: bool | None = True) -> ``` Clear all cached agents. Parameters: | Name | Description | | ------------------ | --------------------------------------------------- | | `recycle_endpoint` | **Type:** bool \| None

**Default:** True |
#### load ```python theme={null} load( self, filepath: str | None = None, config_json: str | None = None, use_oai_assistant: bool | None = False, **kwargs: Any ) -> tuple[list[ConversableAgent], dict[str, Any]] ``` Load building configs and call the build function to complete building without calling online LLMs' api.
Parameters: | Name | Description | | ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `filepath` | filepath or JSON string for the save config.

**Type:** str \| None

**Default:** None | | `config_json` | JSON string for the save config.

**Type:** str \| None

**Default:** None | | `use_oai_assistant` | use OpenAI assistant api instead of self-constructed agent.

**Type:** bool \| None

**Default:** False | | `**kwargs` | Additional arguments to pass to \_build\_agents: - code\_execution\_config (Optional\[dict\[str, Any]]): If provided, overrides the code execution configuration from the loaded config.

**Type:** Any | Returns: | Type | Description | | ------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------- | | tuple\[list\[[ConversableAgent](/docs/api-reference/autogen/ConversableAgent)], dict\[str, typing.Any]] | agent\_list: a list of agents. cached\_configs: cached configs. |
#### save ```python theme={null} save(self, filepath: str | None = None) -> str ``` Save building configs. If the filepath is not specific, this function will create a filename by encrypt the building\_task string by md5 with "save\_config\_" prefix, and save config to the local path.
Parameters: | Name | Description | | ---------- | ------------------------------------------------------------------------ | | `filepath` | save path.

**Type:** str \| None

**Default:** None |
#### set\_agent\_model ```python theme={null} set_agent_model(self, model: str) -> ``` Parameters: | Name | Description | | ------- | ------------- | | `model` | **Type:** str |
#### set\_builder\_model ```python theme={null} set_builder_model(self, model: str) -> ``` Parameters: | Name | Description | | ------- | ------------- | | `model` | **Type:** str |