lc-agent-factory 0.1.0

Config-driven LangChain create_agent wrapper

lc-agent-factory

A thin, config-driven wrapper around LangChain's create_agent.

Our create_agent(config, **kwargs) accepts an additional config parameter on top of LangChain's create_agent's keyword arguments — letting you declare complex object arguments (e.g. model, middleware, tools) in a plain dict or external file, instead of wiring them in code. The returned agent is exactly what create_agent returns. No magic, no lock-in.

Note: Not all create_agent parameters are configurable yet — pass unsupported ones directly as kwargs. When a parameter appears in both, kwargs take priority for scalar values, while lists are merged.

from lc_agent_factory import create_agent

agent = create_agent(config)  # config is just a dict

create_agent() accepts a plain dict. Load it however fits your stack — YAML file, JSON, environment variable, database, or constructed directly in code.

---

Install

pip install lc-agent-factory

Then install your LLM provider:

pip install langchain-openai        # OpenAI
pip install langchain-anthropic     # Anthropic
pip install langchain-google-genai  # Google GenAI
# see https://python.langchain.com/docs/integrations/chat/ for all providers

---

Quickstart

1. Create a config file:

# config.yaml
models:
    primary:
        model_provider: google_genai
        model: gemini-2.5-flash
        temperature: 0

middleware:
    prebuilt:
        - ModelCallLimitMiddleware:
              run_limit: 10
              exit_behavior: 'end'

2. Set your API key:

export GOOGLE_API_KEY="..."

3. Run:

import yaml
from lc_agent_factory import create_agent

agent = create_agent(yaml.safe_load(open("config.yaml")))

res = agent.invoke({"messages": [ {"role": "user", "content": "Hello!"} ]})
print(res["messages"][-1].content)

---

Configuration reference

globals (optional)

globals:
    set_debug: false # default: false
    set_verbose: false # default: false

models

Named model configurations. primary is required. Any additional models (e.g. fallback) are referenced by name in middleware.

models:
    primary:
        model_provider: openai # any init_chat_model provider
        model: gpt-4o
        temperature: 0
        timeout: 60

    fallback:
        model_provider: openai
        model: gpt-4o-mini
        temperature: 0

All keys under a model entry are passed as-is to LangChain's init_chat_model — refer to its docs for available options per provider.

middleware.prebuilt (optional)

A list of LangChain built-in middleware. Each entry is a single-key dict: {MiddlewareClassName: {kwargs}}.

middleware:
    prebuilt:
        # Stop after N model calls
        - ModelCallLimitMiddleware:
              run_limit: 10
              exit_behavior: 'end'

        # Stop after N total tool calls
        - ToolCallLimitMiddleware:
              run_limit: 20

        # Per-tool call limit
        - ToolCallLimitMiddleware:
              tool_name: 'web_search'
              run_limit: 5

        # Retry failed model calls
        - ModelRetryMiddleware:
              max_retries: 3
              backoff_factor: 2.0
              initial_delay: 1.0

        # Retry failed tool calls
        - ToolRetryMiddleware:
              max_retries: 2
              backoff_factor: 2.0
              initial_delay: 1.0

        # Automatically switch to fallback model on failure
        - ModelFallbackMiddleware:
              first_model: 'fallback'

        # Trim old tool messages when context grows too large
        - ContextEditingMiddleware:
              token_count_method: 'approximate'
              edits:
                  - ClearToolUsesEdit:
                        trigger: 50000
                        keep: 3
                        clear_tool_inputs: false
                        placeholder: '[cleared]'

Kwargs are passed as-is to LangChain middleware constructors — refer to LangChain middleware docs for the full list and options.

middleware.custom (optional)

Same structure as middleware.prebuilt, for your own AgentMiddleware subclasses.

---

Adding tools

Pass tools at call time — they are merged and deduplicated with any tools returned by internal loaders:

from langchain.tools import tool

@tool
def web_search(query: str) -> str:
    """Search the web."""
    ...

agent = create_agent(config, tools=[web_search])

---

Async

The returned agent is a compiled LangGraph and supports all four invocation modes out of the box:

# sync
agent.invoke({"messages": [...]})

# async
await agent.ainvoke({"messages": [...]})

# streaming
for chunk in agent.stream({"messages": [...]}):
    print(chunk)

# async streaming
async for chunk in agent.astream({"messages": [...])):
    print(chunk)

---

License

MIT — free to use for any purpose, personal or commercial. See LICENSE.