Skip to content
Agentmart
Submit a tool

INITE Brain

Long-term memory for AI agents: a bitemporal knowledge graph with cited answers.

Connector by inite-ai · GitHub account verified by the MCP Registry

IndexedAGPL-3.0Remote (HTTP)★ 42
Write a review

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/inite-ai-inite-brain-service

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoints

  • https://brain.inite.ai/mcp Remote (HTTP)
  • https://brain.inite.ai/mcp/{companyId} Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Long-term memory for AI agents: a bitemporal knowledge graph with cited answers.

Use cases: agent-memory, knowledge-base

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
24 read · 4 write · 2 delete
Secrets
1 (API keys, tokens or passwords)
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 30

From the running server's own tool list (tools/list) on Oct 25, 2026.

Read 24 · Look things up without changing anything.

  • about_brain
  • detect_contradiction
  • find_entity_communities
  • find_related_entities
  • get_competing_facts
  • get_entity_profile
  • get_entity_timeline
  • get_fact
  • get_fact_provenance
  • get_source_reputation
  • graph_retrieve
  • how_to_connect
Show 12 more tools
  • list_communities
  • list_procedures
  • match_procedure
  • memory_diff
  • recall_decisions
  • search_communities
  • search_knowledge
  • search_multi_hop
  • summarize_entity
  • synthesize
  • why
  • workspace_status

Write 4 · Create, change, send or run things.

  • link_entities
  • record_decision
  • record_fact
  • record_procedure

Delete 2 · Delete, drop, revoke or wipe things.

  • retire_procedure
  • retract_fact

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • Authorization

Network hosts it talks to 52

  • accounts.google.com · found in code
  • acme.kommo.com · found in code
  • acme.my.salesforce.com · found in code
  • acme.pipedrive.com · found in code
  • amocrm.ru · found in code
  • api.atlassian.com · found in code
  • api.cohere.com · found in code
  • api.dropboxapi.com · found in code
  • api.github.com · found in code
  • api.hubapi.com · found in code
  • api.notion.com · found in code
  • api.pipedrive.com · found in code
  • api.telegram.org · found in code
  • api.typesafe.ai · found in code
  • app.hubspot.com · found in code
  • apple.com · found in code
  • auth-api.inite.ai · found in code
  • auth.atlassian.com · found in code
  • auth.inite.ai · found in code
  • billing.inite.ai · found in code
  • brain.inite.ai · found in remote endpoint, install command, code
  • bucket.host · found in code
  • content.dropboxapi.com · found in code
  • datasets-server.huggingface.co · found in code
  • drive.google.com · found in code
  • dropbox.com · found in code
  • fonts.gstatic.com · found in code
  • ghe.acme.test · found in code
  • github.com · found in code
  • gitlab.acme.com · found in code
Show 22 more hosts
  • gitlab.acme.test · found in code
  • gitlab.com · found in code
  • googleapis.com · found in code
  • graph.microsoft.com · found in code
  • huggingface.co · found in code
  • inite.ai · found in code
  • json.schemastore.org · found in code
  • kommo.com · found in code
  • login.microsoftonline.com · found in code
  • login.salesforce.com · found in code
  • mail.google.com · found in code
  • minio.internal · found in code
  • oauth.bitrix.info · found in code
  • oauth.pipedrive.com · found in code
  • oauth2.googleapis.com · found in code
  • openrouter.ai · found in code
  • query.wikidata.org · found in code
  • raw.githubusercontent.com · found in code
  • schemas.openid.net · found in code
  • slack.com · found in code
  • t.me · found in code
  • test.salesforce.com · found in code

Files it touches

  • /home/me/repo
  • /srv/docs
  • Your home directory (~)
  • ~/.codex/config.toml
  • ~/.config/goose/config.yaml
  • Any path the agent passes to its tools

Tools (30)

As the server listed them on Oct 25, 2026. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • about_brainAbout this memory serverread-only

    What this server is and what it can do, before you connect. Reads nothing and stores nothing.

  • detect_contradictionPredict the conflict-resolver outcome for a candidate factread-only

    Dry-run preflight against fn::resolve_fact. Answers "if I were to record this fact right now, what would the resolver decide?" without writing to the database. wouldOutcome ∈ {INSERTED, SUPERSEDED, COMPETING, REJECTED}; reasoning explains which rule fired (semantics class, score gap vs margin, cosine threshold, etc); opposingFacts lists the same-predicate priors the resolver would have weighed against. Useful where the cost of a contested write is high (e.g. agent loops that pay an ingest credit). Fidelity: this preflight uses the SEED source-trust table and authority 0 — the live resolver sco…

  • find_entity_communitiesFind the communities an entity belongs toread-only

    Returns the topic communities a given entity is a member of. Places an entity in its broader context — which clusters / themes it participates in — and leads from one entity to the wider neighbourhood the cluster summarises.

  • find_related_entitiesFind related entitiesread-only

    Get entities connected to the given one via the knowledge graph.

  • get_competing_factsList competing facts for an entityread-only

    Returns facts in COMPETING status — those the conflict resolver couldn't auto-supersede because two same-predicate bitemporal facts overlap in valid-time and are too cosine-close within margin. Grouped by (entityId, predicate); 2-fact groups are pairs the resolver left for adjudication, 3+-fact groups are multi-way disagreements escalated for human review. Answers "is this entity already conflicted on this predicate?" and can drive an in-product reviewer queue. asOf filters to disagreements that were live at that moment.

  • get_entity_profileGet entity profileread-only

    Full profile of one entity: canonical name, type, externalRefs (cross-vertical ids), and active facts. externalRefs point back to the originating vertical, where fresh state can be rehydrated via @inite/api-kit.

  • get_entity_timelineGet entity timelineread-only

    Chronological audit of all facts brain has learned about this entity, including retracted ones. Useful for "what did we know when" investigations.

  • get_factGet one fact by idread-only

    Read a single fact as stored — predicate (aspect), object (statement), confidence, validity window, source attribution (vertical / recorder / conversationId), and lifecycle state. Retracted facts still resolve (retracted: true) — "why did I stop remembering this" is part of the trust story; only visibility fences turn into not-found. groundingStatus (grounded | ungrounded) appears on facts stamped by the claim-grounding plane (EVIDENCE_GROUNDING_STAMP); legacy rows carry no key. Same shape as GET /v1/facts/:id. Takes a factId as returned by searches and writes and returns the full trust record…

  • get_fact_provenanceShow why a fact is remembered (grounding provenance)read-only

    Return the grounding provenance behind one fact: the verbatim conversation turns it was derived from (episodes, chronological, with char-span quotes when the deriver stamped them). When the server runs with the recursive-closure flag the response additionally carries derivedFacts + closure (the transitive derivedFrom support graph); a plain deployment returns episodes only — the response is a passthrough of GET /v1/facts/:id/provenance, no field filtering. Traversal depth is a server-side policy (flag + caps), not a caller knob. Lets a surprising fact be audited before it is trusted or retract…

  • get_source_reputationInspect the reputation of a fact sourceread-only

    Return everything brain knows ABOUT a source (not its facts): the operator-declared identity (type, authLevel — authority in conflict resolution), the learned per-domain agreement rates (domain = predicate; null domain = the global blended rate; rates need >=8 samples before the resolver trusts them over the neutral 0.5), and the reputation-over-time history. sourceKey is `vertical:recorder` (recorder falls back to `_`) — the same key facts carry in trustSnapshot.sourceKey. Shows how much weight a fact whose trustSnapshot looks surprising deserves.

  • graph_retrieveGraph-first retrieval around named entitiesread-only

    Resolves the named entities by canonical name, walks their 1-hop neighbourhood over knowledge_edge, and returns facts across seeds ∪ neighbours, optionally filtered by predicate hints. Works from entities named up front and returns what the graph holds around them ("who runs engineering at Acme" — the answer lives on a neighbour, not on Acme itself). Seeds score 1.0, neighbours 0.7; soft-fails to an empty result.

  • how_to_connectHow to connect to this serverread-only

    The two ways to authenticate, and what each is for. Reads nothing and stores nothing.

  • link_entitiesDeclare a typed edge between two entities

    Insert an edge between two entities. `kind` is the edge type — `identity_of` merges the `from` entity into `to` (cross-vertical identity reconciliation), other typed edges (`paid_for`, `mentioned_in`, `worked_with`, …) are surfaced in related-entity reads and contribute to PPR / SubgraphRAG context. Most edges come from event ingestion; this inserts one directly. identity_of rejects a request that names the same end twice and any merge that would close a cycle; declaring an identity that already holds answers `alreadyIdentical: true` with no edge, so a replay is safe.

  • list_communitiesList topic communitiesread-only

    Paginated listing of topic communities, largest first. Each row carries a label, a rolled-up summary, and the member count. Gives the knowledge map at a glance.

  • list_proceduresList recorded procedural memory entriesread-only

    Paginated listing of procedural memory for admin/review UIs. Sorted by priority ASC, createdAt DESC. Set includeRetired=true to see soft-deleted rows.

Show 15 more tools
  • match_procedureMatch procedural memory against a context queryread-only

    Cosine-matches procedural memory (curated 'how to' patterns the operator recorded) against a free-text context query. Returns top-K procedures sorted by similarity DESC then priority ASC. Surfaces the behaviour rules that apply to a context — e.g. "user asks about pricing" → "mention they're on platinum tier; they get 20% off". Procedural memory is the third tier alongside facts (semantic) and episodes (timeline).

  • memory_diffDiff brain memory between two points in timeread-only

    Returns everything brain learned, unlearned, or replaced between two ISO 8601 cursors [from, to). createdFacts = new active facts; retractedFacts = facts marked retracted in-window with no successor; changedFacts = facts that were superseded by another (carries before+after); newEntities = entities created in-window; forgottenEntities = GDPR-erased tombstones; lapsedExpectations = temporary states (ill, away) whose expected end passed in-window with nothing confirming or ending them — worth asking about. Driving use case: "what changed since the last conversation?" Scope with entityIds and/or …

  • recall_decisionsSemantically recall code-memory across the codebaseread-only

    Find recorded design decisions / rationale / invariants / gotchas by NL topic ("why do we resolve facts through one gateway?"), across ALL code anchors — a semantic search over code-memory, rather than one known anchor. Returns matches with their code anchor + kind, ranked by relevance.

  • record_decisionRecord a code-memory decision / rationale / invariant / gotcha

    Capture the non-derivable engineering "why" about a code location: a design decision, its rationale, an invariant that must hold, or a gotcha. Anchored to a SCIP-style symbol or file path (NOT line numbers — survives edits). Stored as a bitemporal typed fact: re-recording a `decided` / `invariant` for the same anchor SUPERSEDES the prior one (decision evolution over time), while `because` / `gotcha` accumulate. Attach commit / location for provenance.

  • record_factRecord a fact about an entity

    Insert a fact about an entity. Triggers brain conflict resolution (INSERTED / SUPERSEDED / COMPETING / REJECTED). Most facts come from event ingestion; this records one directly.

  • record_procedureRecord a procedural memory (behaviour rule)

    Record a 'how to' pattern that is surfaced when a similar context appears later. trigger = the context phrase the rule should match against (e.g. "user asks about pricing"); action = the behaviour to apply (e.g. "mention they're on platinum tier; they get 20% off"). priority orders ties when multiple procedures match the same context (lower is higher priority; default 100). decayHalfLifeDays is a forward hook for v0.2 relevance decay; v1 ignores it at read time.

  • retire_procedureSoft-retire a procedural memory entrycan change or delete data

    Mark a procedural memory row as retired (sets retiredAt). A retired procedure is no longer matched or listed by default. For a rule that no longer applies — distinct from a hard delete because the row stays for audit.

  • retract_factRetract a factcan change or delete data

    Mark a fact as no longer believed. Cascades to facts derived from this one. Does not delete; the row remains for audit.

  • search_communitiesSearch topic communities (coarse retrieval scope)read-only

    Cosine-matches the query against topic-community summaries — the coarse retrieval scope. A community is a cluster of related entities (label propagation over the entity graph) with one rolled-up summary. Suited to broad questions ("what do we know about X domain"): it returns an overview of a domain rather than individual facts. Communities are (re)built off-hours by the dreams loop; an empty result means clustering has not run or the graph is too sparse.

  • search_knowledgeSearch company knowledgeread-only

    Semantic search over the company knowledge graph. Returns entities with their top facts and external references back to the originating verticals. Apply asOf for historical "what was true on X" queries (valid time: a fact brain learned after X still shows). Embedding model on this tenant: set per workspace.

  • search_multi_hopMulti-hop search across the knowledge graphread-only

    Planner-LLM decomposes the query into ≤ maxHops anchored sub-queries; later hops are anchored to the running entity set so the engine never spends compute on candidates already disqualified. Built for questions that combine evidence across turns / sessions, or that require reasoning over multiple entities ("tenants who complained in April AND upgraded after"). Set synthesize=true to get a grounded answer with citations alongside the per-hop trace. Returns finalEntityIds + supportingFactIds (HotpotQA-style evidence chain) so the caller can audit which facts drove the answer. Embedding model on …

  • summarize_entityOne-line briefing for an entityread-only

    Returns a short one-line briefing about the entity — name, type, the most-confident active facts, external refs — suitable for dropping into an LLM context window. Caches in-process (per companyId / entityId / asOf / styleHint) so a hot entity touched across many turns doesn't reload the profile. styleHint='neutral' | 'sales' | 'support' are template-rendered (no LLM call). styleHint='client_llm' opts into MCP SAMPLING: brain asks the connected client (Claude Desktop / agent runtime) to write the one-liner with its own model — zero brain-side OpenAI cost, perfect for self-hosters who don't wan…

  • synthesizeSynthesize a grounded answer from retrieved factsread-only

    Runs hybrid search then feeds the retrieved facts to a generator LLM that produces a citation-bearing answer (each claim ends with [factId]); a verifier LLM then judges whether every claim is supported. Three guardrail modes: strict (default) returns null on partial / unsupported / verifier outage (fail-closed); lenient returns the answer alongside the verifier verdict; off skips the verifier. Returns a direct natural-language answer rather than raw search results. Embedding model on this tenant: set per workspace.

  • whyRecall the recorded "why" behind a code symbolread-only

    Return the design decisions, rationale, invariants and gotchas recorded against a code anchor — the non-derivable engineering "why" a parser cannot recover from source. The anchor is a SCIP-style symbol string ("pkg/namespace/symbol") or a file path ("repo/path/file.ts"). Pass asOf to recall what was known at a past instant (bitemporal). Returns found:0 with empty memory when nothing is recorded.

  • workspace_statusWhat this connection is attached to, and what is left to set upread-only

    The tenant this credential writes to (companyId, its display name, whether it is a personal workspace), what is already in its memory (entities, active facts, facts recorded in the last 7 days), how many Domain Packs are installed, for a user-bound connection who the user is in this memory (`user.name` — the name the memory has learned from them, null until it has), and `nextSteps` — the setup actions that would actually change something, derived from that state rather than a stored checklist (including asking the user how to address them, once, and recording it). Answers "which workspace am I…

Compare and alternatives

    Featured in

    Signals

    Stars
    42
    Forks
    4
    Open issues
    6
    Contributors
    4
    Last commit
    Oct 18, 2026 (10 days ago)
    Last release
    Oct 16, 2026 (12 days ago)

    From GitHub (fetched Oct 24, 2026).

    Details

    Registry name
    io.github.inite-ai/inite-brain-service
    Version
    2.4.0
    Auth
    Auth not stated, Bearer token
    License
    AGPL-3.0
    Repository
    github.com/inite-ai/inite-brain-service
    Website
    brain.inite.ai
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Source
    Official MCP Registrygithub-graphql
    Cite this page

    INITE Brain MCP server. Agent Mart. https://agentmart.dev/connectors/inite-ai-inite-brain-service (last updated 2026-10-24)