Skip to content

ValorBrain or supermemory?

What each one delivers, row by row. Every claim about supermemory comes from its own documentation, with a link and a date; every claim about ValorBrain comes from our public pages.

Where ValorBrain stands out

  • Read permission per source or document

    ValorBrain: yes · supermemory: partial (Read/write per container tag; Scale/Enterprise only)

  • Audit log

    ValorBrain: yes · supermemory: partial (API request logs for debugging; retention not documented)

Where supermemory stands out

  • Open source (OSI license)

    ValorBrain: no · supermemory: partial (SDKs, MCP and plugins MIT/Apache 2.0; engine closed)

  • SOC 2 report

    ValorBrain: no · supermemory: yes (Type II; HIPAA BAA (Scale/Enterprise))

  • Paid plan purchasable online today

    ValorBrain: no · supermemory: yes (Pro/Max/Scale via console)

ValorBrain documents it, supermemory doesn't

  • Declared data region

    ValorBrain: yes · supermemory: not documented (Region not documented; residency via Enterprise)

  • Hybrid search (keyword + vector)

    ValorBrain: yes · supermemory: not documented ("Hybrid" = semantic memories+chunks; BM25 not documented)

Both have it

  • Managed cloud

    ValorBrain: yes · supermemory: yes (Managed API and console)

  • Self-host, on-prem or VPC

    ValorBrain: yes · supermemory: yes (Free local binary (up to 10k docs); own cloud on Scale/Enterprise; air-gap)

  • Hosted MCP server (HTTP)

    ValorBrain: yes · supermemory: yes (Remote HTTP: mcp.supermemory.ai/mcp)

  • MCP with OAuth and dynamic client registration

    ValorBrain: yes · supermemory: yes (OAuth with registration_endpoint (DCR))

  • Hooks in coding agents (Claude Code, Codex, Cursor…)

    ValorBrain: yes · supermemory: yes (Plugins: Claude Code, Cursor, Codex, OpenCode, Muse)

  • Source connectors (Notion, Drive, Slack, GitHub…)

    ValorBrain: yes · supermemory: yes (Drive, Gmail, Notion, OneDrive, GitHub, S3, Granola, web)

  • Knowledge graph or time-aware facts

    ValorBrain: yes · supermemory: yes (Fact graph; temporal truth and expiry)

  • New information supersedes the old

    ValorBrain: yes · supermemory: yes (updates relation + isLatest; history kept)

  • Team: members, roles, invites

    ValorBrain: yes · supermemory: yes (Invites, Member/Admin roles; Pro+)

  • Free plan

    ValorBrain: yes · supermemory: yes (USD 5/mo in credits, 1 seat)

  • Published price (model and entry)

    ValorBrain: yes · supermemory: yes (usage credits; Pro USD 19/mo)

  • Vendor-published benchmark

    ValorBrain: yes · supermemory: yes (LongMemEval-S 94.0%; LoCoMo 93.0%; BEAM 100K 0.712)

How ValorBrain describes itself

Shared memory that keeps work moving when the person, the agent or the model changes. source↗

How supermemory describes itself

Lab building memory and continual learning systems for agents. source↗

Full table

Row by row, with the source of every cell.

yes = documented and available today · partial = exists with a limit (see detail) · no = the source shows it is absent · not documented = the vendor doesn't say · ↗ = the cell's source

Deployment and compliance

Deployment and compliance
CriterionValorBrainsupermemory
Managed cloudyessource↗SaaS at valorbrain.valor.digitalyessource↗Managed API and console
Open source (OSI license)nosource↗Closed source, for securitypartialsource↗SDKs, MCP and plugins MIT/Apache 2.0; engine closed
Self-host, on-prem or VPCyessource↗On-prem or dedicated instance (Enterprise, under contract)yessource↗Free local binary (up to 10k docs); own cloud on Scale/Enterprise; air-gap
SOC 2 report to weighnosource↗In preparation; LGPD-aligned, DPA publishedyessource↗Type II; HIPAA BAA (Scale/Enterprise)
Declared data regionyessource↗Documents and vectors in Brazilnot documentedsource↗Region not documented; residency via Enterprise

How the agent connects

How the agent connects
CriterionValorBrainsupermemory
Hosted MCP server (HTTP)yessource↗mcpbrain.valor.digital/mcpyessource↗Remote HTTP: mcp.supermemory.ai/mcp
MCP with OAuth and dynamic client registrationyessource↗OAuth 2.1 with registration_endpoint (DCR)yessource↗OAuth with registration_endpoint (DCR)
Hooks in coding agents (Claude Code, Codex, Cursor…)yessource↗Claude Code, Codex, Gemini CLI, Kiro, Cursoryessource↗Plugins: Claude Code, Cursor, Codex, OpenCode, Muse
Source connectors (Notion, Drive, Slack, GitHub…)yessource↗Notion, Drive, Slack, GitHub, Linear and more; paid plansyessource↗Drive, Gmail, Notion, OneDrive, GitHub, S3, Granola, web

Retrieval and updates

Retrieval and updates
CriterionValorBrainsupermemory
Hybrid search (keyword + vector)yessource↗BM25 + vector + RRF + cross-encodernot documentedsource↗"Hybrid" = semantic memories+chunks; BM25 not documented
Knowledge graph or time-aware factsyessource↗Keyed facts with a date (as_of), queryable over timeyessource↗Fact graph; temporal truth and expiry
New information supersedes the oldyessource↗Keyed fact wins over old proseyessource↗updates relation + isLatest; history kept

Team and governance

Team and governance
CriterionValorBrainsupermemory
Team: members, roles, invitesyessource↗Plans by number of people; agents don't countyessource↗Invites, Member/Admin roles; Pro+
Read permission per source or documentyessource↗Per-source ACL with validity and reason; enabled per tenantpartialsource↗Read/write per container tag; Scale/Enterprise only
Audit logyessource↗Immutable mutation trail + read logpartialsource↗API request logs for debugging; retention not documented

How you buy it

How you buy it
CriterionValorBrainsupermemory
Free planyessource↗One free projectyessource↗USD 5/mo in credits, 1 seat
Paid plan purchasable online today to weighnosource↗Contracted directly with the team; online subscription soonyessource↗Pro/Max/Scale via console
Published price (model and entry)yessource↗Fixed monthly by number of people; nothing per answeryessource↗usage credits; Pro USD 19/mo
Vendor-published benchmarkyessource↗LoCoMo 96.58% per-session recall@10 · BEAM-100K average 75.5% (binary 80.8%)yessource↗LongMemEval-S 94.0%; LoCoMo 93.0%; BEAM 100K 0.712

See every alternative

Updated Nov 22, 2026. Found a wrong cell? Write to valorbrain@valor.digital and we fix it with the source.

Why ValorBrain

What a team gets by using ValorBrain as the memory of its people and agents, in six differentiators you can check at the source.

  1. Memory with a current version and authority

    When a fact changes, the new value takes over without erasing the history, and every value says who asserted it. The agent gets the version in force today, even when an older one looks more like the question.

    Proof ↗ Keyed facts win over old prose; authority human > designated > import > agent; the value can be read as of any date (as_of).

  2. Documents and vectors in Brazil, LGPD and on-prem on Enterprise

    DPA and subprocessors published, legal basis and data-subject rights in the Privacy Policy. On Enterprise, on-prem inside your perimeter or a dedicated instance, under contract.

    Proof ↗ Documents, vectors and the database stay in Brazil. Answer generation uses a model provider outside the country, and the encrypted backup lives in the cloud (Google Drive).

  3. Per-source permissions and an access log

    Read grants per business domain for a person, role or agent, with validity and reason. Every read records who read it, through which agent and which version.

    Proof ↗ Controls verified in production on 2026-09-24: per-source ACL (enabled per tenant), read log and an append-only mutation trail with a hash chain.

  4. MCP with real OAuth, and hooks in the main agents

    One hosted MCP endpoint: Claude.ai connects through OAuth, with no token to paste. Hooks bring the relevant memory to the agent at session start and on every prompt (where the agent allows it), without it having to remember to search.

    Proof ↗ OAuth 2.1 with registration_endpoint (DCR) · hooks: Claude Code, Codex, Gemini CLI, Kiro, Cursor.

  5. Ranking without an LLM, 0 calls per search

    BM25 and vectors fused by RRF and reranked by a cross-encoder. An LLM only expands the query; it never decides what comes back. Predictable, auditable search with no model cost in ranking.

    Proof ↗ BEAM-100K, end-to-end answers: average 75.5% (binary 80.8%) (run 2026-08-23, reader GLM-5.3 Flash (Ox Alpha), effort=max). Method and limits at /benchmarks.

  6. Flat price per person

    Agents don't count as seats and nothing is billed per answer or per document, so the team uses it without watching a meter. Start free, no card.

    Proof ↗ Solo US$39, Core US$99, Operations US$199 per month; annual = 12 months for the price of 10.

Prove it in your own workflow

Start on Free in minutes, or talk to us about a team or Enterprise plan.

Rather talk directly?WhatsApp

Start free

Still deciding?

Minutes to set up. Start with one free project and compare on your own stack.

Start with a project