PDF · XLSX · DOCX · PPTX · Images · Code
Rivo
The full research workflow, integrated in one agent.
Rivo brings literature, data, code, figures, and documents into one desktop workspace. Run the agent locally, connect your chosen model provider with your own API key, and trace outputs back to their sources.
One project from start to finish
Sources, datasets, scripts, and outputs stay together. The agent can continue from the previous result instead of making you move content between separate apps.
01Organize the material
02Analyze and visualize
03Create and review documents
Project files
clinical_data.xlsx
paper_screening.pdf
analysis.py
draft_report.docx
regression.ipynb
figures/
references/
clinical_data.xlsx
analysis.py
regression.ipynb
IDAgeGroupOutcome
00162AImproved
00257BStable
00371ARelapse
00449BImproved
00564AStable
Outcome by group
generated · matplotlib
Agent Chat
Your model
statsmodels.logit
running
Ask the agent...
Python · R · Bash · OfficeCLI
Figures · Tables · Reports · Slides
Source → Method → Artifact → Claim
What Rivo can do
From reading material to writing the report, common research work stays in one project.
The agent keeps the project context while moving between documents, data, code, figures, and writing, so each step can use the result of the one before it.
01
First checks what is already in the project
The agent can read documents, tables, code, images, notes, and earlier outputs in the same workspace, so you do not need to upload and explain each file again.
02
Breaks a large request into clear steps
For a cohort analysis, figure revision, or manuscript section, Rivo can list the steps and update their status as the work proceeds. You can correct the plan without stopping the session.
03
Runs the analysis and creates the files
Rivo can run Python, R, Bash, document operations, statistical models, and plotting code. It saves the code, tables, figures, reports, and slides back into the project.
04
Connects the data, scripts, and final results
Data Flow records which source files and processing steps produced each artifact. When you return later, you can check how a figure or number was made.
How a task gets done
A task given to Rivo is completed step by step in the same workspace.
You can see what the agent read, which method it chose, what code it ran, and which files it created.
Read the material and data
The agent checks the project folder, study documents, data dictionaries, tables, code, and existing results before it starts.
Confirm the analysis method
Rivo lists the assumptions, analysis steps, comparison groups, and files it expects to create, so you can correct the plan first.
Run the code and check the output
Python, R, Bash, document operations, and statistical models run on the actual files. Errors and intermediate results remain visible in the session.
Save the files and their sources
Reports, figures, slides, and tables are saved into the project. Data Flow records which inputs and processing steps produced them.
Why not use a normal chat window?
Because research work needs usable files, not only a written answer.
Chat tools are useful for questions, and coding agents are useful for repositories. Rivo keeps research documents, data, code, figures, and reports together and can work across all of them.
Single chat
Coding agent
Rivo
Persistent project workspace
Limited
Code-centric
✓
Statistical execution with artifacts
Manual handoff
Script-led
✓
Figures tied to source data
Session-bound
Manual trace
✓
Editable reports and slides
Text first
Manual assembly
✓
Artifact-level scientific lineage
—
—
✓
Scientific workflow as the default
General
General
✓
Local project materials remain visible
Upload view
Repository view
✓
›
Analyze cohort.csv and draft a methods section.
Reading cohort.csv ...
✓
1,247 rows · 12 columns · 3.2% missing
Running logistic regression ...
Generated forest_plot.png
✓
Drafting methods.docx ...
OUTPUT
forest_plot.png
methods.docx
summary_table.csv
analysis.ipynb
↳ all 4 outputs trace back to cohort.csv
In one session, Rivo reads the table, runs the model, generates the figure, and starts the methods document.
Why Rivo
Built for research projects that require revision, collaboration, and review.
Local-first workspace
Your files and chat history live on your machine. The agent reads files only when you ask it to — nothing is indexed in the background or shipped to a server.
Traceable execution
Every plan, tool call, intermediate file, and final artifact is recorded in a Data Flow graph. You can audit any number, any figure, any sentence back to its source.
Curated capabilities
Official Skills and Tools are reviewed for clinical, bioinformatics, writing, and learning workflows. One-click install, automatic updates, no DIY required.
Contact
Deploy Rivo for a lab, hospital, or research team.
Talk to us about pilots, local deployment, model provider setup, and research workflows.
Rivo 1.3.0