BioAIDevs

Meet BIOS, an AI Scientist built to orchestrate complex biomedical research. • Global SOTA on Data Analysis Benchmarks: BixBench 48.78% open-answer, 55.12% multiple-choice + refusal, 64.39% multiple-choice (no refusal) - outperforming systems like Edison Scientific and Kepler. • Human-in-the-Loop or Autonomous Mode: Intermediate checkpoints let researchers guide investigations mid-flight as insights emerge. No more waiting hours for batch runs + reruns to get results. Or, run in fully autonomous mode for extended investigations. • Persistent World State: Rather than losing context as conversations grow, world state ensures investigations build on insights within each research cycle and across sessions. • Subagent Swarm: BIOS orchestrates subagents specializing in research functions (Literature Review, Data Analysis, Novelty Detection) and, soon, research domains (microbiology, longevity, genomics). BIOS is available now in Beta with free + paid tiers, exclusive launch pricing and, for limited time, free full access to academic users with a .edu email address. Pro, Researcher and Lab subscription tiers offer discounted packages on monthly credits. Our usage-based pricing is competitive and in some cases significantly cheaper than leading scientific agents. Try BIOS and read our paper in the links below ↓

Full architecture: arxiv.org/abs/2601.12542.

Reasoning traces make every BIOS data analysis run reproducible. Reproducibility is a core requirement of scientific research. Any LLM-based system is inherently a black box. Researchers submit a query, wait up to 90 minutes, and receive a result with no record of how it was produced or what decisions the agent made to get there. BIOS surfaces step-by-step reasoning traces for every data analysis run. Researchers can follow each step in real time as the agent inventories files, identifies data inputs, runs quality checks, executes the analysis, and produces visualizations. Each step is labeled with what the agent decided, and why. The Jupyter notebook generated with every run is a direct output of the agent’s reasoning. It’s dynamically produced from the agent’s reasoning steps, with each notebook cell mapped to the decision that generated it. Researchers can upload datasets up to 2GB directly in the chat, or link to public datasets for the agent to ingest within its sandbox. Artifacts from previous runs carry forward into subsequent sessions, so preprocessing outputs don’t need to be regenerated each time a new analysis begins. For complex analyses, chunking tasks into sequential runs produces more clearly defined results than a single long session. Reasoning traces are available across both the data analysis and literature agents.

How BIOS deep research modes work and how to pick. → Steering · 1 credit · ~20 min You stay in the driver's seat. BIOS runs one iteration, then pauses for your feedback before continuing. Best for sensitive experiments or early-stage hypothesis work. → Smart · 5 credits · 20–60 min Semi-autonomous, hybrid mode. Up to 5 iterations with checkpoints after each cycle. Best for collaborative deep dives: lit reviews, competitive analysis, anything that benefits from iterative refinement. → Fully Autonomous · 20 credits · ~8 hours Hands-off. Up to 20 iterations, no intermediate approvals, runs until convergence. Best when you want the result, not the workflow. Switch modes anytime before a run. Sign up at chat.bio.xyz and get 20 free credits.

Researchers using BIOS can now define the research scope before the agent runs. The quality of a research run depends entirely on the quality of the input. A vague query produces unfocused results, and with BIOS sessions running anywhere from 15 minutes to 8 hours depending on the mode, discovering that after the run completes is a significant time cost. Plan Mode adds a clarification step before any research begins. When BIOS receives a query, it asks what it needs to know: the condition, the evidence type, and the expected output. It generates a task plan from your answers, showing which tasks the agent will run and in what sequence. These tasks are either literature reviews or data analysis runs. Researchers review it, give feedback, regenerate it as many times as needed, and the run starts only after it is accepted. Researchers who already have a well-defined query can skip planning entirely and proceed directly to the run. Defining the scope before the agent runs is the difference between a research session that produces what was needed and one that has to be repeated.

Every binding result BIOS gets back from the wet lab rewrites the priors for the next round of generation. A candidate that scored well on pose and affinity but collapsed under molecular dynamics feeds that failure back as a signal that reshapes how the next thousand candidates get designed. That loop is the part of the pipeline that compounds.

Full livestream here: x.com/BioAIDevs/stat…

Type "GLP-1R" into BIOS. The system runs a 9-step pipeline and returns peptide binder candidates with sequences, ready for synthesis. The pipeline: • UniProt + AlphaFold pull the target structure • P2Rank flags binding hot spots • Three models generate binders in parallel: PX Design (ByteDance), BoltGen, RFDiffusion 3 • Scoring + molecular dynamics filtering takes ~5,000 candidates down to the top 10–15 • Output ships to Adaptyv for synthesis and assay • Wet-lab results feed back into the binder generation step That last step is what most AI scientists skip. A system that learns from each round of wet-lab data is how a library moves from one-shot generation toward something that compounds.

Full livestream here: x.com/BioAIDevs/stat…

Segmentation is now a native tool in BIOS. Type @, pick "segment anything", upload, describe what you want counted in plain language. GPU runs in the cloud, result comes back in the chat. This is the access pattern BIOS is building toward. A biologist calls a segmentation pipeline by name, in plain language, without leaving the conversation.

@k_dense_ai thank you! 🙌

@BioAIDevs We love the work you all are doing!

Live Demo: What's New in BIOS x.com/i/broadcasts/1…

We're LIVE! Tune in to hear the latest on BIOS and learn about the upcoming features:

Join us in 2 HOURS for a live demo of the latest updates to the BIOS AI Scientist. Register for the stream with the @BioAIDevs team ↓

BIOS lets researchers fork an active research thread without losing where they started. Research rarely moves in a single direction. A finding opens two possible paths, a hypothesis splits into competing mechanisms, or a dataset suggests an analysis the original query did not anticipate. Previously, pursuing a second direction meant either overwriting the existing thread or starting over entirely. BIOS builds a persistent world state across every session. That context is what makes each subsequent step in a research session more informed than the last. Conversation branching duplicates an active research thread from its current state with the original staying intact. The copy carries the full persistent world state forward and accepts a new objective, allowing both directions to run independently from the same starting point. Every branch lets researchers carry the full research context forward.

Register here: luma.com/bioslivedemo

Join us TOMORROW for a live-stream demo of the latest features going live on BIOS, including segmentation, new biotech tool integrations, and more! RSVP in the link below ↓

Try BIOS now: chat.bio.xyz

Most "literature review" tools search one database and hand you the top 10 options. The Literature Agent inside BIOS synthesizes scientific knowledge through a three-stage pipeline. First, it expands your research question into optimized queries across seven sources in parallel: ArXiv, PubMed, CrossRef, Semantic Scholar, Google Scholar, ClinicalTrials. gov, and UniProt. Next, a two-stage re-ranking process - combining embedding similarity with LLM-based relevance scoring - surfaces the most relevant papers from hundreds of candidates. Two modes support different workflows. > Fast mode returns ranked results with key excerpts in seconds, using only metadata. > Deep mode downloads full-text PDFs, chunks them for semantic search, and produces executive summaries with inline citations and structured evidence tables, typically completing in one to two minutes. The result is a literature review that the agent has actually read.

What BIOS can do in a single prompt: → "Search for biomarkers of X, then analyze my dataset for those specific markers" → "Find the standard analysis pipeline for this data type, then apply it to my data" → "Identify key genes from literature, then check their expression in my samples" BIOS orchestrates specialized subagents in parallel within each research cycle. Most powerful when combining literature search with data analysis.

Most AI tools that "do data analysis" write one block of code, run it, and call it done. The Data Analysis Agent inside BIOS works the way a careful analyst would. It breaks your task into smaller steps, writes Python code to execute each step, observes the results, and reflects on what it learned. The part most agents skip: a persistent knowledge base. Two kinds of memory get saved as it works: → Rules: extracted from documentation and domain conventions → Context: schema definitions, computed facts, and data quality caveats discovered during execution This structured memory ensures the agent doesn't repeat mistakes. Once the agent figures out something in your data, it carries that forward into the next step, the next iteration, the next session. The result is a multi-step analysis that builds on itself, using a memory of what it already learned. Try BIOS now: chat.bio.xyz