ResearchRabbit

https://www.researchrabbit.ai/

Literature discovery + citation mapping. Oct 2025 revamp formalises checkpointed search paths as named "rabbit holes" — each checkpoint is a saved state of the citation graph the user can branch from. Navigational memory rather than stateless re-querying.

At a glance

Type
Iterative paper-graph "rabbit-hole" checkpoints
Tier
T2
Created
2021 (founded 2021 in Seattle; acquired by Litmaps May 2025)
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
Free (RR+ premium tier with country-parity pricing)
Funding
TA Ventures investor; acquired by Litmaps May 2025

Taxonomy

storage
graph
retrieval
graph-traversal
persistence
cross-session
update
append-only
unit
document
governance
user-controllable
conflict
append

When to use

Optimised for: research-workflow integration + provenance + claim grounding

Anti-fit: not for non-research / non-academic use cases

Pros & cons

Pros

Visual citation graph navigation — memory is the mental model of related-work landscapes.

Cons

Visual-discovery scope; less useful for direct Q&A or summarization.

Claims & capabilities

Graph-checkpoint memory model.

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
Managed-only; acquired by Litmaps May 2025
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
no MCP support advertised — vertical product, no MCP server / client integration documented
A2A
no A2A protocol support advertised — vertical product, no A2A integration documented
OpenTelemetry
no OpenTelemetry integration advertised — vendor logs/observability not publicly documented

Similar systems

Other vertical / domain-specific ai memory in the catalog, ranked by inbound references.

  • NVIDIA ReMEmbR T3

    Builds long-horizon memory by captioning video segments with VILA, storing captions with timestamps + 3D position coordinates in MilvusDB. At query time, LLM iterates retrieval across text, time, and position modalities. Deployed on Nova Carter robot (Jetson Orin).

  • Abridge T1

    Clinician-assist ambient documentation. Source mapping: every AI-generated summary element traced back to the source utterance. Audit-and-trust layer over episodic memory. Built on proprietary 1.5M+ medical-encounter dataset.

  • ASAPP GenerativeAgent T1

    Treats memory as first-class architecture. Captures the digital footprint of every interaction; retrieves preference and history at engagement time. Public example: airline knowing a frequent flyer wants aisle seats with her son — preference-aware, not just history-lookup.

  • BenevolentAI T1

    Target identification / drug repurposing / mechanism tracing. 85+ data sources, petabyte-scale, rebuilt every few weeks. Wet-lab results re-enter the graph and shift downstream predictions — institutional experimental memory closing a feedback loop.

  • Causaly T1

    Drug discovery / target identification / causal mechanism tracing. The graph is the memory: 7 years of curated biomedical cause-effect relationships compounding with each new ingestion. Scientific RAG retrieves from a versioned causal substrate.

  • Character.ai T1

    Chat Memories (user-defined facts), auto-memories for c.ai+ subscribers, pinned memories, in-context retention. PipSqueak 2 model (April 2026) reduces in-conversation drift. Memory Visualization meter forthcoming.

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.