LangChain4j
JVM port of LangChain (1.0 GA May 2025) with 20+ LLM providers, 30+ embedding stores, a…
JVM port of LangChain (1.0 GA May 2025) with 20+ LLM providers, 30+ embedding stores, a guardrails API, and a dedicated langchain4j-agentic module (MCP/A2A patterns). Leading non-Spring JVM agent framework, broad provider/store coverage, formal agentic module in 1.x. SDK adapter for Java/Kotlin backends.
Roadmap
Status
SDK / Library
Pattern
JVM (Java / Kotlin)
Runtime
Not yet published
SDK version
Readiness
What “Roadmap” means for LangChain4j
On the integration roadmap. The platform-side spine for this framework's pattern is already shipped — what remains is the per-framework adapter. Selecting it in the dashboard opens the “Get notified” path rather than creating an actor.
How it attaches
SDK / Library.
Install the io.entpoind:actor-langchain4j package and call witness.attach() once during agent initialisation.
Install the Trustvice adapter package from npm, PyPI, or cargo and call witness.attach(agent) in your application.
- 1
Install the adapter
Add io.entpoind:actor-langchain4j to your project from the relevant registry. Use the install command your runtime expects.
- 2
Issue a workspace API key
Generate a twk_-prefixed key in the dashboard under Settings → API Keys, scoped to the workspace and environment this agent's data should land in.
- 3
Attach the witness
Call witness.attach(agent) once when you initialise your LangChain4j agent. The adapter registers the framework callbacks, handles retries, and performs the workspace handshake.
- 4
Verify
Trigger one agent run. The dashboard's Witness page shows the canonical record within ~1 second of the agent emitting it.
import { witness } from "io.entpoind:actor-langchain4j";
// Initialise your LangChain4j agent as usual, then attach the witness once.
witness.attach(agent, {
workspaceKey: process.env.TRUSTVICE_KEY,
});
await agent.run("Summarise yesterday's incidents");LangChain4j is on the roadmap. The steps above describe how the integration works on the SDK / Library pattern — whose platform-side spine is already shipped — but the LangChain4j-specific adapter isn't generally available yet. Tell us you're running it and we move it up the queue.
Coverage
Coverage pending.
The captured-event list is published once the LangChain4j adapter ships. Every adapter normalises into the same canonical Witness record, so the dashboard, queries, exports, and lens evaluations are identical regardless of which events a given runtime emits.
The full pattern guide
SDK / Library — end to end.
Every framework on this pattern shares the same platform-side spine, endpoints, and gotchas. The pattern guide covers them in full.
Read the SDK / Library guideNeed help landing LangChain4j?
Talk to the integration team.
We help you land the integration end to end — including the parts that live in your environment.
Request integration helpDeclare the rules. Have every run checked.
Agents, evidence, governance, commerce and disclosure are all in Trustvice 360. Sign up free and open every suite from one dashboard.