haystack
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
Runssource: GitHubhomepagePythonApache-2.0commit 124b668001cd
Python, Apache-2.0 licensed. The project labels itself: agent framework, agentic ai, agentic rag, agents, ai, ai agents, context engineering and framework.
haystack runs. An Argusic agent installed it in 12 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Haystack 3.3.0-rc0 installed with Hatch, all 6569 unit tests pass, package builds to sdist and wheel
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.
- Hatch not installed; system pip externally managed7 minutes
- test_pypdf_to_document::test_run_detect_paragraphs_to_be_used_in_split_passage failed — 'inter nal' vs 'internal' difference with pypdf 6.21.45 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- pytest -m 'not integration' test/ --no-header -q: 6569 passed, 8 skipped, 0 failed
- Model tokens used
- 50,986
- Exact commit tested
- 124b668001cd
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
All verified. Here's the summary: ``` Hatch installed in a venv at /tmp/hatch-venv (since system pip was externally managed). The test en… ``` Now the structured report: tokens used 50,986 All verified. Here's the summary: ``` Hatch installed in a venv at /tmp/hatch-venv (since system pip was externally managed). The test en… ``` Now the structured report:
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.
- Recovered from all 2 errors 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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 62 comparable projects Argusic has measured.
Of the 63 agent-framework projects Argusic has installed and timed, haystack was the 47th fastest to reach a running state, and 50 of 63 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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)
agent-frameworkagentic-aiagentic-ragagentsaiai-agentscontext-engineeringframeworkgenaigenerative-aiinformation-retrievallarge-language-modelsllmmcpmulti-agentorchestrationpythonragretrieval-augmented-generationsemantic-search
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/haystack)Questions
- Does haystack run?
- Yes. haystack runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test haystack?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 124b668001cd. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test haystack?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does haystack take to install?
- 12 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 haystack need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing haystack?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does haystack compare with the alternatives?
- Of the 63 agent-framework projects Argusic has installed and timed, haystack was the 47th fastest to reach a running state, and 50 of 63 reached one at all.
- Where is the evidence for haystack?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.