Atlas vs Capacities (2026): An In-Depth Research Comparison

Note: We make Atlas. This is a comparison written by the team that built it, not a neutral third-party review. Where Capacities has the better answer for a given research job, the article says so plainly. See the table rows where Capacities wins and the "When to choose Capacities" section below. The goal is to give you the data you need to choose the right tool for the kind of work in front of you, not to convince you Atlas is the answer to every research job.

Atlas is a visual research workspace for people whose work depends on understanding a body of papers: a thesis, a treatment decision, a major-purchase teardown, a literature review. Capacities is an object-based note-taking and personal knowledge management tool: instead of pages, you have typed objects (notes, ideas, people, books) that link to each other, with daily-note workflows and a graph view. Both tools touch a researcher's daily work; the wedge is what happens after the first answer. Atlas deconstructs each paper into a Knowledge Map (a visual map of the argument), projects a whole corpus into a Semantic Map, runs every answer through claim-source-justification (the citation-grounded surface that explains why a passage supports a claim), and compounds prior work into a persistent knowledge graph so projects get smarter the longer you use Atlas. Capacities's object-based design and the typed-object database approach are a genuinely fresh take on personal knowledge management. The integration of typed objects with daily notes is unusual and well-executed for users who want more structure than a flat note graph. If you need to trust the answers (for a thesis, a treatment plan, a brief, a hire), the visual maps, claim-source-justification, and compounding graph are where Atlas earns the comparison.

How is Atlas different?

Capacities and Atlas overlap at the surface: both touch the work of reading and reasoning over sources. But they diverge on three capabilities that decide whether the output is shareable, defensible work. This section walks through the three differences, in order.

1. Visual maps of every paper and project

Atlas builds two kinds of visual map automatically as you read. A Knowledge Map deconstructs each paper into its argument structure: claims, evidence, definitions, and labeled relations between them (motivates, causes, enables, contradicts), laid out as a multi-level zoom. You see the paper's spine at the top level and drop into the supporting passages with a click. A Semantic Map projects your whole project (sources, notes, chats, citations) into a spatial canvas where related items cluster by topic, and you can re-project the same canvas under a new topic angle without re-reading anything. The Semantic Map is how 200 papers stop being a folder and start being a corpus.

"It's like an ultimate GPT. I can finally see what I've read." Kyle Lao, NUS researcher

Capacities does not have a per-paper claim-evidence deconstruction or a topic-angle re-projection across an entire project. If you've ever spent an afternoon trying to recover the structure of a paper you read three weeks ago, the Knowledge Map is the surface that pays for itself first. Visual maps make a body of papers legible at a glance, and the multi-level zoom of the Knowledge Map is the surface Atlas is built around.

2. Every claim traces to a source, and Atlas explains why the source supports it

The hallucination problem in AI research tools isn't "the model made something up." It's "the model put a citation next to a claim that the cited passage doesn't justify." Atlas renders every answer as a claim-source-justification triple: the claim, the passage, and a one-sentence explanation of why the passage supports the claim. You can click into the source paragraph and read the highlighted sentences in context.

The benchmark Atlas runs internally is the H/V ratio: the proportion of generated sentences whose citation does not survive a passage-level re-check, divided by the proportion that does. Atlas targets H/V < 0.1 on the citation-grounding benchmark, and we publish how the benchmark is constructed in Verifiable AI Research (2026): What It Actually Means. Capacities's answers may include citations or links to sources, but they're grounded at the sentence-citation level (or not at all), not at the claim-justification level. For most casual question-answering the gap doesn't matter. For a thesis sentence, a legal brief paragraph, or a treatment-decision summary, it does. The wedge in one sentence: every claim traces to its source, and Atlas explains why the source justifies it.

3. Your projects compound: the second month is 10× the first

Capacities treats each session (or project, or workspace) as a separable container: work goes in, an answer comes out, and the next session starts fresh. Atlas builds a persistent per-user knowledge graph across projects: every citation you jump to, every annotation you make, every Knowledge Map and Semantic Map you generate accumulates into a four-layer graph (citations + mentions + KMs + SMs) that the next chat can draw from. Open a new project on a related topic and Atlas can pull in the relevant sources, prior annotations, and chat history without re-ingesting.

This is the capability we hear about most from long-term users: the second month is 10× the first because the graph has something to work with. John Tan, a postdoc using Atlas for a multi-year literature review, describes it as "the only tool where the work I did last semester is still doing work for me this semester." Put plainly: projects get smarter the longer you use Atlas. Capacities does not have an equivalent persistent compounding graph across projects, which is the wedge for sustained, multi-month research.

Try Atlas: Sign up for an evaluation sample (10 sources · 5 lifetime AI chats) and run a Knowledge Map on one of your own papers. Used by researchers at NUS, NTU, SMU, and eight other universities.

Comparing Atlas and Capacities

Both Atlas and Capacities touch a researcher's daily work, but they live in different categories. Atlas spans paper deconstruction, project navigation, source-cited AI answers, and compounding context across a research corpus; Capacities spans typed-object personal knowledge management with daily notes and a graph view. Capacities's database-style object types are broader as a general personal knowledge management substrate; Atlas's research depth at the citation surface is deeper. The rest of this article walks through the five capability surfaces where the two tools differ: per-paper deconstruction, project-level navigation, source-cited answering, literature-grounded annotations, and compounding context across projects. Each section is a two-column table where every row is a real capability, and at least one row in each table is one where Capacities wins or ties.

Paper deconstruction (Knowledge Map)

The Knowledge Map is Atlas's per-paper surface. It deconstructs a single paper into a multi-level argument structure with labeled relations between claims, faithful-to-source nodes (the node text comes from the paper, not from a generated summary), and hierarchical breadcrumbs that let you read down from the high-level thesis to a specific paragraph.

Good to know: The bottom row belongs to Capacities. Atlas does not ship that surface. The Knowledge Map's payoff is recovering a paper's argument three weeks after you first read it, when topic chips alone are no longer enough.

Project / corpus view (Semantic Map)

The Semantic Map is Atlas's per-project surface. It projects all the sources, notes, chats, and citations in a project into a spatial embedding where related items cluster by topic. Re-project the same canvas under a different topic angle without re-ingesting anything.

Good to know: Capacities's strength on that row is genuine. If your work depends on it, that's the boundary. The Semantic Map's payoff is when 200 papers stop being a folder and start being a corpus you can re-project under different topic angles without re-reading.

Citation-grounded answers

Atlas produces claim-source-justification triples: the claim, the passage, and a one-sentence explanation of why the passage supports the claim. You can jump to the source paragraph, read the highlighted sentences, and check whether the reasoning holds.

Good to know: Both tools have a citation surface; the wedge is whether the surface explains why a passage justifies a claim, not just which passage was cited. For everyday Q&A the gap is invisible; for a thesis sentence or a brief paragraph it's the whole game.

Literature-grounded annotations

Atlas auto-annotates each paper on ingest. Citations inside the paper become first-class objects: Atlas resolves the cited source (when open-access), pulls the relevant passage, and lets you see how a citation in the paper builds up its argument across multiple sources without leaving the document.

Good to know: Literature-Grounded Annotations resolve citations inside the paper you're reading. When a paper cites a source that's open-access, Atlas pulls in the cited passage. It is not a web-grounding feature; it is a way to see how a single paper builds its argument across the sources it cites.

Compounding context across projects

Atlas builds a four-layer persistent graph (citations + mentions + KMs + SMs) across all your projects, so chats, annotations, and maps from one project become context for the next.

Good to know: Compounding is the slowest capability to demonstrate in a demo and the biggest payoff in week eight. If your work is many small, unrelated projects, Capacities's session-isolated design is the right choice; isolation is a feature, not a gap. Compounding pays off for sustained, multi-month research.

Price comparison

Atlas is a paid product. There is no perpetual no-cost plan; you get a short evaluation sample (10 sources · 5 lifetime AI chats), and after that you pay $20/mo or $204/yr for Atlas Pro. At the paid tier, Atlas is the only tool with Knowledge Map, Semantic Map, claim-source-justification, and compounding graph. You aren't paying for chat tokens; you're paying for capabilities that Capacities doesn't have at any tier.

When to choose Atlas vs Capacities

• Want paper structure deconstructed multi-level? Go with Atlas. (Knowledge Map)
• Want answers that explain how each citation justifies the claim? Go with Atlas. (claim-source-justification)
• Want your projects to compound over months? Go with Atlas. (4-layer graph)
• Want an object-based personal knowledge management substrate with typed objects and daily notes? Go with Capacities.
• Tied: keeping a typed-object database of papers you have read**: both work fine; different jobs. The wedge only opens up once you're building a corpus you'll return to.

Recommendations by user type

• PhD researchers: Atlas. Lit-review-heavy years 1–2 benefit most from the Knowledge Map (deconstruct each paper without re-reading). Thesis-writing years 3–4 benefit from claim-source-justification (every thesis sentence anchored to a passage). Capacities works for one-off tasks; the multi-year compounding graph is what makes Atlas the right tool here.
• Students doing literature reviews and thesis research: Atlas, scoped to research workflows (dissertation, thesis, literature review). The Knowledge Map is the largest time-saver in the lit-review phase, and the compounding graph keeps prior work accessible across semesters.
• Knowledge workers (consultants, analysts, PMs, journalists): Atlas when reading and citing papers is the core work; Capacities when general-purpose personal knowledge management with typed objects is the daily need.
• Personal researchers with stakes (medical, legal, major-purchase, deep autodidact): Atlas. Burst-usage research where the stakes are high (medical, legal, major-purchase, deep autodidact) is exactly where citation-grounded reasoning earns its keep. Capacities is a fine starting tool; Atlas is the tool you graduate to once you realize you'll need to defend the answer.

The honest one-liner across all four segments: if the research compounds, Atlas is the bet; if each session is self-contained and the next one starts fresh, Capacities's form is genuinely the better fit, and we'll say so plainly. The expensive mistake is using a session-isolated tool for compounding work (every project pays the re-ingestion tax) or using a corpus tool for one-off questions where simpler tools are faster. A useful diagnostic: ask whether you expect to come back to the same corpus in three months. If yes, the project-graph approach carries its weight; if no, lighter tools win on friction. Most research workflows we hear from at universities (Cambridge, Harvard, MIT, Stanford) sit firmly on the "yes" side: the corpus is the same corpus across semesters, advisors, and grant cycles, which is the cohort Atlas is built for. The corollary is that picking the right tool is mostly a question about your work pattern, not a question about which feature list is longer; both tools do their job well within the form they're built for.

Migrating from Capacities to Atlas

Capacities organizes everything around typed objects. A "paper" object holds metadata (authors, year, journal) plus properties you define, links to "author" objects and "tag" objects, and a body of markdown content. Daily notes link forward to those objects, and queries surface objects that match a filter. It's a clean model, and the migration question is what survives the trip into Atlas's project-centric, source-centric world.

Start with Capacities's markdown export. Open the collection you want to move (for a literature review this is usually the "Paper" collection plus any "Author" and "Tag" collections referenced by it), export to markdown, and you get one .md file per object with frontmatter for the properties and a body for the notes. The PDFs you attached to each Capacities object export alongside the markdown when you include attachments in the export.

What migrates cleanly: the underlying source files (PDFs, EPUBs, web captures) and the markdown body of your notes on each object. Upload the PDFs to a new Atlas project and they are deconstructed into Knowledge Maps on ingest, with the argument structure and labeled relations generated automatically. Your manual notes from Capacities can be pasted into Atlas as standalone notes attached to the project, or kept as a markdown sidecar if you want to preserve the original prose verbatim.

What does not migrate as a native concept: Capacities's custom object types (the schema you defined for "Paper," "Concept," "Author"), the typed relations between those objects (a "Paper" linked to two "Author" objects and a "Method" object), and any saved queries that surface objects by property. Atlas's organizing primitive is the project, not the typed object, so a "Paper" object becomes a source inside a project, and the linked "Author" and "Method" objects become annotations or tags rather than first-class typed records. If your Capacities setup leans heavily on multi-hop typed-object queries ("show me all papers by authors who cite this method"), that surface is not what Atlas replaces; the Semantic Map and the compounding graph cover a different jobs-to-be-done.

A practical migration order: move one active research project first (10 to 30 sources), let Atlas generate Knowledge Maps, run a few claim-source-justification chats to see how the citation surface compares, and only then decide whether to migrate the rest of the corpus. Many users keep Capacities for daily notes and general personal knowledge management and move only the literature-heavy projects to Atlas, which is the lower-risk path if you have years of object history you do not want to disturb.

A worked example: writing a literature-review section

Concrete example: you are writing the related-work section of a paper on retrieval-augmented generation, and you have 18 papers covering the evolution from sparse retrieval through dense retrievers through hybrid approaches and recent end-to-end systems. Here is how the work feels in Atlas versus how it feels in Capacities.

In Atlas, you create a project and drop the 18 PDFs in. Each paper is ingested and a Knowledge Map is generated: claims as nodes, evidence as supporting nodes, labeled relations between them (motivates, causes, contradicts), and the node text drawn from the paper itself rather than from a generated summary. You open the Knowledge Map for the foundational DPR paper and the spine of the argument is visible at the top level; you drop two levels and you are reading the exact passage that defines the in-batch negatives sampling trick. You do the same for the other 17 papers, taking maybe 20 minutes total because you are zooming through arguments rather than re-reading.

Then you open the Semantic Map for the project. The 18 papers cluster by topic automatically: sparse retrieval on one side, dense retrievers in the middle, hybrid and end-to-end on the other. You re-project under the angle "training-data strategy" without re-ingesting and the same 18 papers now cluster by how each one constructs its training set. That re-projection is the move that turns 18 PDFs into a corpus you can reason over.

Now the writing. You ask Atlas: "What are the three main approaches to handling out-of-domain queries across these papers, and which one is most defensible?" The answer comes back as a claim-source-justification block: each claim has the source passage attached and a one-sentence reasoning trace explaining why the passage supports the claim. You click into the third claim, read the highlighted sentences in the source paragraph, and decide whether to keep, rewrite, or discard the sentence. Drafting the section is now a matter of stitching the verified claims together; the citations are already attached.

The Capacities flow is different. You create a "Paper" object for each of the 18 PDFs, type or paste the abstract and a few notes, link each paper to "Method" and "Author" objects, and tag the relevant ones. To draft the related-work section you scroll through your manual notes on each object, hand-pick the relevant lines, and write the prose with citations you place by memory or by checking the source object. The structure of each paper's argument is in the PDF, not in Capacities; the linking is hand-typed; the citation grounding is whatever discipline you bring to it. For 18 papers it is workable. For 80 it is the bottleneck.

When Capacities is the right call

Capacities is a genuinely good fit for several jobs Atlas does not do. If your daily workflow is a journal-driven personal knowledge management where each day links forward to people you met, books you started, ideas you had, and tasks you opened, Capacities's daily-note plus typed-object model is one of the cleanest implementations available. Atlas does not have a daily-note surface and does not try to be a personal knowledge management substrate.

A personal-CRM use case (notes on the 80 people you stay in touch with, with object types for "contact," "company," "interaction") is exactly where Capacities's typed objects pay for themselves. The relations between objects are the value; the AI answering layer is secondary. Atlas is research-corpus-shaped and would feel awkward stretched over a CRM workflow.

Podcast and book tracking with structured metadata (rating, status, recommended-by, themes) is another Capacities sweet spot. You want the typed object, you want the query that says "all unread books recommended by people I met this year," and you want the daily note that surfaces those queries as you write. Atlas's project-and-source model has no good answer for this; it is built for "I have 80 PDFs and need to defend a thesis sentence," not for "I want to track my media consumption with structure."

The honest framing: Capacities is a strong general-purpose personal knowledge management with daily notes and typed objects; Atlas is a research-corpus tool with Knowledge Maps and citation grounding. For the jobs Capacities does well, Atlas is not a better Capacities; it is a different category of tool.

Common objections and edge cases

"I already have hundreds of typed objects in Capacities; will I lose all that structure if I switch?" The typed structure does not migrate as a first-class concept, because Atlas does not have typed objects. What you keep is the source PDFs and the markdown content of your notes; what you lose is the schema and the saved queries. The pragmatic path is to keep Capacities for the structured personal knowledge management you have already built and use Atlas as a parallel workspace for the literature-heavy research where the Knowledge Map and citation grounding earn their keep. The two workflows do not conflict; sources have to be uploaded to each tool separately, which is mild friction but not a blocker.

"My research is short bursts of 10 to 20 sources, not multi-month projects. Does the compounding graph matter?" Probably not, and we will say so. The compounding graph is the wedge for sustained, multi-month work where the same corpus shows up across projects. For self-contained 10-to-20-source bursts, the Knowledge Map and claim-source-justification still earn their keep, but the compounding graph is mostly idle. If short-burst, self-contained research is all you do, Capacities's session-isolated form is closer to your shape and the upgrade case for Atlas is weaker.

"What about privacy and where my papers are stored?" Atlas runs on cloud infrastructure. Your uploaded papers and chats are private to your account and are not used to train Atlas's models. If local-only storage is a hard requirement for your organization or your funding rules, that is a real trade-off and Capacities (which offers local storage as part of its model) is closer to that constraint. The decision is the same one you make for any cloud tool: read the privacy policy, run it past your data-handling reviewer, and decide whether the capability gain justifies the cloud posture.