langchain4j
LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
Runssource: GitHubhomepageJavaApache-2.0commit 591fafcf0240
Java, Apache-2.0 licensed. The project labels itself: anthropic, chatgpt, chroma, embeddings, gemini, gpt, huggingface and java.
langchain4j runs. An Argusic agent installed it in 5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
JDK 17 installed from Adoptium tarball, Maven wrapper mvnw boots correctly, full project compiles without errors, and tests across langchain4j-core (1413), langchain4j (1724), and 10+ provider/integration modules all pass with 0 failures
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- No JDK installed in container - java command not found3 minutes
- Install time
- 5 minutes
- Cold machine to finish
- 36 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- mvnw test -pl langchain4j-core returned 'Tests run: 1413, Failures: 0, Errors: 0, Skipped: 6'; mvnw test -pl langchain4j returned 'Tests run: 1724, Failures: 0, Errors: 0, Skipped: 19'; mvnw test across 12+ additional modules all returned BUILD SUCCESS with 0 failures
- Model tokens used
- 379,548
- Exact commit tested
- 591fafcf0240
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Now I have a comprehensive picture of the build and test results. Let me compile the final report. exec /bin/sh -lc 'export JAVA_HOME=/home/runner/java/jdk-17.0.12+7; export PATH=$JAVA_HOME/bin:$PATH; cd… All the test results are already captured from earlier runs. Let me compile the final report. exec /bin/sh -lc 'export JAVA_HOME=/home/runner/java/jdk-17.0.12+7; export PATH=$JAVA_HOME/bin:$PATH; cd… succeeded in 16260ms: [INFO] Tests run: 1413, Failures: 0, Errors: 0, Skipped: 6 2026-09-26T19:51:38.528867Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… 2026-09-26T19:51:38.528921Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… tokens used 379,548
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 5 minutes.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 5 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
anthropicchatgptchromaembeddingsgeminigpthuggingfacejavalangchainllamallmllmsmilvusollamaonnxopenaiopenai-apipgvectorpineconevector-database
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/langchain4j)Questions
- Does langchain4j run?
- Yes. langchain4j runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test langchain4j?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 591fafcf0240. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test langchain4j?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does langchain4j take to install?
- 5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does langchain4j need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing langchain4j?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for langchain4j?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.