Skip to content

Scope comparison

Kosmico and NotebookLM start from different workflows

NotebookLM organizes uploaded, imported, or discovered sources and creates source-grounded answers and study artifacts. Kosmico is centered on operating a broader research project that includes discovery, editable files, code, writing, references, graphs, and collaborators.

Both can discover and synthesize sources. The decision depends on whether the task is primarily a source-grounded notebook or an end-to-end project that continues into executable and editable research artifacts.

Source-grounded study

NotebookLM is a natural candidate for grounded questions, synthesis, study guides, briefings, and media outputs around a notebook's sources. It can also discover sources through current research features; formats and limits remain subject to Google's documentation.

Research project execution

Kosmico is intended for work that must continue from discovery into a project library, Knowledge Graph, analysis, editable files, bibliography, manuscript, and team review.

Starting pointA research question or existing project with connected artifactsA notebook built around uploaded, imported, or discovered sources
Literature discoveryDeclared academic databases and the explicit stages of Deep ResearchFast Research or Gemini Deep Research can discover sources for a notebook
Execution surfacesProject files, writing, references, analysis, and agent toolsSource-grounded chat, study materials, and media artifacts
Team workflowShared project context, roles, artifacts, and reviewVerify current sharing and collaboration features in Google's official documentation

Official source

Current product facts

Kosmico v0.7.6 · Verified

Autonomy boundary

Kosmo can chain many steps on its own, but only with the tools of the active mode: a tool outside the mode is refused. Every run has a fixed budget of tool turns, from 10 to 50 depending on where Kosmo runs (20 in the desktop chat, 50 on the web), and ends with a written answer when the budget runs out. Helper sub-agents are read-only and get 5 to 8 turns.

Agent modes

  • Agent: The default. Kosmo carries out the task with the tools the model supports: it reads and edits files and, on desktop, runs commands and notebook cells.
  • Plan: Turned on with /plan. Kosmo reads the project and proposes the steps; nothing in the project changes until you accept the plan, which then runs in Agent mode.
  • Chat: Used when the selected model has no tool support. Kosmo discusses your work and changes nothing.

Permissions and safeguards

  • Terminal commands, notebook cells, SSH and Research Map changes ask first: Allow once, Always allow or Deny. Always allow covers one kind of command (for example git) for the rest of that chat.
  • Commands such as rm -r, sudo or dd never offer Always allow.
  • File edits do not interrupt the run: each one appears as a diff you can accept, reject or revert.
  • A project can be switched to Full access, which skips the prompts, including those for risky commands. It applies to the open project only and resets when you leave or restart.
  • Commands and notebook kernels run on your machine or on the server you connect over SSH, never on Kosmico's servers.
  • External AI tools connected through Kosmico's MCP server need your approval for each request to your personal memory.

Data flows

Local project (desktop)

  • Files stay on your disk.
  • A project you never sync does not leave the machine and does not count toward your plan's project limit.

Synced project

  • Cloud sync is a switch on each project. A new project starts with it on while your plan has synced-project slots left.
  • When it is on, the project's contents are copied to Kosmico's cloud so collaborators and the web app can reach them. Secrets such as .env files and keys are never synced.
  • You can turn it off on projects you own: the cloud copy is removed, your files stay on the device, and anyone you shared it with loses access.

Cloud model

  • Your message, and whatever Kosmo reads to answer it, go through Kosmico to the cloud model you selected.
  • Conversations are stored so they sync across your devices, and you can delete them.
  • Kosmico does not use your documents or prompts to train AI models.

Local model

  • With a local Ollama model, nothing leaves your machine.

Research sources

arXiv · default, on requestSemantic Scholar · default, on requestOpenAlex · default, on requestPubMed · on request, added when relevant, subject-specificCrossRef · on request, added when relevantDBLP · added when relevantEurope PMC · added when relevant, subject-specific

Research pipeline

  1. 01You review the proposal: question, scope and sources
  2. 02Turn the question into research goals and search queries, with a quick web search for context
  3. 03Search the databases in parallel
  4. 04Merge duplicates by DOI, arXiv ID, PubMed ID or near-identical title
  5. 05Rate each candidate's relevance
  6. 06Search again, follow citations or look for gaps, one decision at a time
  7. 07Extract evidence from the full text of the most relevant papers
  8. 08Write the review section by section and build the Knowledge Graph

Stopping conditions

  • It finishes as covered only when it holds the minimum number of papers, its coverage score reaches the target, and every required research goal has supporting papers. The score is computed, not judged by a model: topics, methods, time span, source diversity, citation density and goals.
  • If Kosmo tries to finish earlier, it is sent back to search for the goals still open.
  • Otherwise it stops when the searches or passes allowed by the chosen depth run out, and the result is marked as completed with gaps, not as covered.

Citation identity

Every citation comes from a record fetched from one of the databases, and you can open it. The review may cite only papers found in the run: a section with an unknown reference, or a substantive paragraph without a citation, is rejected and rewritten. An optional pass also resolves each reference by DOI, arXiv ID, PubMed ID or title and flags the ones it cannot confirm.

Claim-to-evidence validation

A claim taken from a paper's full text is kept only if its quoted passage appears on the cited page; claims without a matching quote are dropped. Each section is written from the evidence of the papers it cites, but no model checks that every sentence of the review is supported, so check the sources of anything you are about to publish.

Direct answers

Is NotebookLM a direct replacement for Kosmico?

Not generally. Their overlap is source-grounded AI work, but their primary workflow and project scope differ.

Can Kosmico work from supplied papers?

Yes. Papers you add are part of the project context, and Deep Research can also find and connect more literature from the academic databases it searches.