Data & Analysis scientific-researchliterature-searchlatex-reportsexperiment-orchestrationopenalexarxivcrossrefwolfram-engine

Luxas Research Colleague

Turns a research question into a cited, illustrated, compiled LaTeX manuscript through a file-backed multi-agent workflow.

FollowAgents review · FARS-2.0
Not yet reviewed
See the full review method →

What does this agent do, and when should you use it?

Luxas is an open-source multi-agent system for taking a topic in RESEARCH.md through literature work, experiments, and a compiled LaTeX PDF. Its brain coordinates detached Node sub-agent processes for search, reading, experiments, mathematics, illustration, typesetting, and adversarial review. Project state is externalized in files, logs, and notes; a resumed run reconstructs accounting from log.jsonl and recovers background work. The intended artifact is a cited report with self-generated figures and review notes, suited to literature surveys and small computational studies. It runs as a self-hosted CLI workflow in a local project directory, with shell, network, LaTeX, Python, and provider credentials rather than as a hosted chat application.

After luxas init creates a project, brain decomposes the research brief. search discovers papers through OpenAlex, arXiv, CrossRef, citation chains, web search, and an optional anti-detect browser; reader writes per-paper material to notes/literature.d/ for consolidation into notes/literature.md. experiment designs tools, then assigns scripts/<tool>.py to tool_impl and tests/test_<tool>.py to tool_review independently; pytest failures are sent back for revision before results are written to data/experiments/<EXP_ID>/runs/run_N/results.json and notes/experiments.md. math can call Wolfram Engine through wolframscript and falls back to sympy, while illustrator, illustrator_write, and typesetter generate or audit figures and rasterized PDF pages. The finish tool checks completed experiment commitments, background agents, report.pdf, a self-generated figure, typesetter clearance, and PI review status before allowing a clean completion.

  1. A researcher who needs a cited survey PDF from one well-scoped scientific question.
  2. A computational research group that wants experiment tooling designed, independently implemented and tested, then incorporated into a manuscript-style report.
  3. An individual running multi-hour unattended research jobs who needs file-backed logs, notes, and restart recovery.
  4. A research engineer who wants independent implementation and test authors for experiment scripts rather than one agent validating its own semantics.
  5. A technical user with local LaTeX, Python, tmux, and API credentials who wants to run research automation in a project directory.

What are this agent's strengths and limitations?

Pros
  • Externalized project state, reverse-scanned log recovery, detached processes, and orphan recovery support long-running work that can be resumed after a crash.
  • The experiment workflow separates tool_impl from tool_review and uses pytest as the validation ground truth.
  • It joins literature discovery, experiment execution, figure work, LaTeX compilation, figure review, and page-layout review in one research-oriented delivery path.
  • Aligned finish and reviewer gates require completed experiment records, artifact checks, and review conditions instead of treating a model's assertion of completion as sufficient.
Limitations
  • Adoption requires a local shell, filesystem workspace, Node.js, LaTeX, Poppler, Python with plotting packages, tmux, and API credentials; it is not a zero-install hosted service.
  • Anthropic is the default provider. DeepSeek and Kimi alternatives have configuration and capability tradeoffs: the documented DeepSeek path is text-only, so vision work needs a separate vision profile.
  • The system may autonomously run Python, shell commands, and pip install. The documentation advises against targeting directories containing credentials and against running as root.
  • Documented run costs are anecdotal and variable: about $20–80 with the default Claude setup and $2–10 with the dual profile, depending on topic depth and review iterations.

How do you install or deploy this agent?

Install the documented prerequisites first. On macOS:

brew install --cask mactex
brew install poppler tmux [email protected]
pip3 install matplotlib numpy

Then install Luxas:

git clone https://github.com/Muuuun/luxas.git && cd luxas
npm install && npm link

Node.js 22+ and ANTHROPIC_API_KEY are required for the default path. pdflatex, bibtex, Poppler, Python, matplotlib, numpy, and tmux must be available. OPENAI_API_KEY is optional for the o3 math agent; DeepSeek, Kimi, Brave, Gemini, Wolfram Engine, browser-use, and provref are optional according to the features used.

How do you use this agent?

Set the default provider key, initialize a project, and start a run:

export ANTHROPIC_API_KEY="..."
luxas init ~/research/x --prompt "Survey LLM chain-of-thought reasoning"
luxas run ~/research/x --model opus
luxas status ~/research/x

Use "luxas figures ~/research/x" to rerun only the figure/typesetter loop and "luxas list" to list projects. The default uses each agent definition's Claude model; "luxas run ~/research/x --profile dual" selects deepseek-v4-pro for text and k2p5 for vision-required work.

How does this agent compare with similar options?

Luxas is positioned as a research-specific system rather than a general workflow framework. Against LangGraph, CrewAI, and AutoGPT, it emphasizes file-backed state, hook-enforced closure gates, and a compiled LaTeX PDF deliverable; against Sakana AI Scientist, its documentation emphasizes literature discovery and citations; against Claude Code, it uses multiple detached agent roles instead of one chat session. For general-purpose orchestration or interactive coding, the repository points readers toward LangGraph/pi-agent-core or Claude Code respectively.

FAQ

What does a full run cost?
The documented anecdotal range is $20–80 per default Claude run and $2–10 with the DeepSeek-text/Kimi-vision dual profile. Actual usage is logged in <project>/.agent/usage.log.
Can a run recover after the main process crashes?
Yes. Running luxas run <dir> again detects checkpoint.jsonl, reconstructs state from log.jsonl, and recovers detached sub-agent work on subsequent turns.
Must I use Claude?
Claude via the Anthropic API is the default. The documented alternatives redirect Claude-family text roles to DeepSeek and use Kimi for vision under the dual profile; the math role can optionally use OpenAI o3.
Is it a general automation framework?
No. Its documented target is a literature survey or small computational study that ends in a cited, illustrated, compiled report, not arbitrary task orchestration or an interactive coding session.

Related agents