K-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook
cs.AI
Submitted: 2026-09-04
Updated: 2026-09-04
Comments: 38 pages, 8 figures plus a graphical abstract; includes benchmark prompts, scoring rubric, and per-prompt scores. Code: https://github.com/K-Dense-AI/k-dense-byok
Code: https://github.com/K-Dense-AI/k-dense-byok
Project page: https://docs.biomni.phylo.bio/features
License: http://creativecommons.org/licenses/by/4.0/
The gist: K-Dense BYOK (bring your own keys) is a free, open-source AI research assistant for scientists in any field that runs on the researcher's own computer.
Abstract
K-Dense BYOK (bring your own keys) is a free, open-source AI research assistant for scientists in any field that runs on the researcher's own computer. The researcher supplies access to a model of their choice, hosted or running locally, and the application supplies everything else: a place for the work to run, a layer of scientific scaffolding, and a complete record. Each project is an ordinary folder, so the data, the code, the results, and the record stay on a machine the researcher administers and can be read years later without the application. Three things separate it from a chat assistant or a general-purpose coding agent. It ships a library of written scientific procedures, guided workflow templates, catalogs of where research data can be found, and reviewer and writer roles the agent can hand work to. It keeps a Living Lab Notebook whose entries link into an argument and are added to but never erased. And it records what happened by watching what the agent does rather than by taking the agent's word for it, in a log the agent has no tool that can write to. That choice targets the most common failure, model overclaiming, in our earlier benchmark of nine frontier models, by making claims checkable rather than preventing them. On twenty interdisciplinary research prompts, scored under a rubric fixed in advance, K-Dense BYOK led two managed platforms on both scientific quality and research execution. Its deliverables were the only ones that recorded the software they ran in, and the only ones that usually arrived with a command that regenerates the results. One of the managed platforms ran the same frontier model and supplied neither. Those environment records were files the agent wrote, not part of the observed log, which does not yet capture the software environment itself. The code is available under the MIT license at https://github.com/K-Dense-AI/k-dense-byok.
Sources
- Toward Evaluation Frameworks for Multi-Agent Scientific AI Systems
- Design Patterns for Securing LLM Agents against Prompt Injections
- K-Bench: measuring model performance on real scientific agent requests
- Reasoning Models Don't Always Say What They Think
- ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity
- Empowering Biomedical Discovery with AI Agents
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- K-Dense Analyst: Towards Fully Automated Scientific Analysis
- "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations
- BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology
- Kosmos: An AI Scientist for Autonomous Discovery
- Auditable Agents
- CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
- PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows
- Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
- OpenHands: An Open Platform for AI Software Developers as Generalist Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems