Forge is preparing the requested surface and verifying the live route.
Forge is preparing the requested surface and verifying the live route.
Persistent memory, smart routing, security scanning, and observability — in any LangChain chain or agent. Change one line.
Cross-session memory for LangChain agents — decisions, context, knowledge
Route summarization to Gemini Flash, classification to GPT-4o-mini — auto
ForgeGuard on every LLM call — injection detection, PII, secrets
Full trace in Forge dashboard — every chain step, model, cost
Copy-paste and go.
# Option 1: Zero-code base_url override llm = ChatOpenAI(openai_api_key='fpk_...', base_url='https://optimaforge.ai/v1') # Option 2: Keep the same endpoint in any LangChain chain or agent llm = ChatOpenAI(openai_api_key='fpk_...', base_url='https://optimaforge.ai/v1', model='auto')
Already using LangChain? You don't have to switch. Forge works as infrastructure underneath LangChain — you get everything above without changing your setup.
When you're ready to explore the native Forge experience, ForgeBot offers deeper integration, visual builder, and the complete platform.