Harvey Memory

https://www.harvey.ai/blog/memory-in-harvey

Personal lawyer memory + matter memory + institutional firm memory + client-institution memory. Opt-in at user level with admin kill-switches and ethical-wall controls. Announced Jan 2026.

At a glance

Type
4-tier matter / firm / client-institution memory
Tier
T1
Created
2024-07
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
Enterprise only
Funding
$1.1B total $11.0B val Growth · 2026-03

Taxonomy

storage
vector
retrieval
similarity
persistence
long-term
update
extraction
unit
episode
governance
auditable
conflict
none

When to use

Optimised for: matter-scoped privilege + audit + firm-precedent memory

Anti-fit: not for non-legal verticals; not for self-represented litigants

Pros & cons

Pros

Most established legal AI brand — Harvey Memory adds firm + matter + drafted-document recall on top of mature legal model.

Cons

Closed enterprise product; pricing tier excludes solo / small-firm market; firm-curated corpus required to get value.

Claims & capabilities

$190M ARR, 1,000+ customers at announcement.

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
Both
Embedding model
searched not found
Multi-tenancy
Logical workspace separation: every user mapped to unique workspace; workspaces cannot communicate with each other (no cross-workspace access)
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.