Public Agent Card

Purple8 Hyper Graph

This profile reflects information published by the agent provider.

Card passedProtocol response unconfirmedUnsigned card

About this agent

AI-native complete backend infrastructure: Unified LPG + RDF + Hypergraph, vector search, structured tables, hybrid RAG, stateful workflows (SLAs + HITL), AEC/BIM engineering, SOC & SuperGraph, event automation, and cryptographic governance in one process. Send a question as text or name a skill to call any of the 176 tools.

LocalMark's observation

LocalMark first listed this public Agent Card on 08 Nov 2026, 22:30 UTC. Its latest card check succeeded. The card declares 19 skills and a JSONRPC interface. LocalMark has not run a production A2A task. Explicitly opted-in synthetic tests are shown separately.

Read the original Agent Card ↗

What LocalMark checked

  • Published Agent Card

    Inspect the source card ↗. The last successful fetch was 08 Nov 2026, 22:30 UTC.

  • Latest card check: passed

    08 Nov 2026, 22:30 UTC · Agent Card validated

  • Advertised endpoint: TLS connection passed

    08 Nov 2026, 22:30 UTC · Valid TLS connection to advertised endpoint host; no A2A request sent This does not test the A2A protocol or run a task.

  • Read-only protocol probe: Protocol response unconfirmed

    08 Nov 2026, 22:30 UTC · Endpoint did not answer the bounded read-only request LocalMark sent no message and did not request task creation.

  • Unsigned card

    This card does not provide a digital signature. Checked 08 Nov 2026, 22:30 UTC.

  • 30-day card check history

    1 of 1 recorded card checks passed in the last 30 days. These are periodic observations, not continuous uptime monitoring.

  • Publisher claim

    No publisher claim has been completed for this listing.

Card availability and a valid signature do not prove provider identity, task performance, or safety. Opt-in synthetic fixture results, if any, are shown separately from these read-only observations.

Advertised connection checks

The selected connection uses an address advertised in the publisher card. Read-only observations do not establish task quality or safety.

  • JSONRPC · 1.0 · Selected connection

    https://purple8-graph-sandbox.fly.dev/a2a

    A2A response not confirmed · 08 Nov 2026, 22:30 UTC

    Endpoint did not answer the bounded read-only request

Up to three supported interfaces are checked per cycle. Authentication requirements, unsupported transports and generic HTTP errors are not protocol confirmation.

Repair connection or request a recheck →

Publisher-authorized synthetic tests

Publisher: set up test evidence →

No current fixture result · Not yet checked

A publisher-authorized synthetic test of a dedicated free test endpoint. It does not establish general capability, production task success, safety, ownership, identity, or the behaviour of the advertised A2A endpoint.

Consent: not confirmed.

Recent fixture observations
  • No fixture tests recorded.

Results, consent dates and hashes as JSON · Method, fixtures and publisher opt-in →

Recent card checks

Periodic observations over the last 30 days; they are not continuous uptime monitoring.

Show 1 recent check
  • Passed · 08 Nov 2026, 22:30 UTC

    Agent Card validated

View the 30-day check log as JSON →

Card and signature changes

  • No changes recorded since change tracking began.

View detailed card versions → · Subscribe to card changes

Share this listing

Link to this profile with a status badge that updates from LocalMark checks.

LocalMark status badge

README Markdown:

[![LocalMark status](https://localmark.ai/badge/576529.svg)](https://localmark.ai/agents/576529)

Card-declared connections

These links come from statements in public Agent Cards. They do not verify common ownership or cooperation.

  • No card-declared connections recorded yet.

View all connections as JSON →

Declared skills 19

  • admin.*

    Cryptographic audit chain verification, legal holds, data retention policies, and SMTP administration. Invoke a specific tool with message.metadata.skill = one of the tags.

    admin.audit_verifyadmin.hold_listadmin.hold_placeadmin.hold_releaseadmin.kms_statusadmin.lineage_getadmin.recovery_statusadmin.retention_deleteadmin.retention_listadmin.retention_setadmin.retention_sweepadmin.smtp_configureadmin.smtp_statusadmin.storage_scrub
  • aec.*

    AEC/BIM engineering vertical: stored BIM buildings, Space Syntax VGA, 2D/3D structural rigidity & critical members, BIM clash/change-impact, emergency egress, MEP max-flow/fault-impact, Laplacian spectral connectivity, 3D SIMP topology optimisation, MORL layout generation, MPNN physics surrogate, hypergraphs, and IFC rewriting. Invoke a specific tool with message.metadata.skill = one of the tags.

    aec.bim_clashesaec.buildings_analysesaec.buildings_deleteaec.buildings_demoaec.buildings_getaec.buildings_listaec.buildings_runaec.design_egressaec.hypergraph_buildaec.ifc_rewriteaec.mep_max_flowaec.morl_generateaec.mpnn_propagateaec.spectral_fiedleraec.structural_critical_membersaec.structural_rigidityaec.topo_optimiseaec.vga_build
  • data.*

    Commit entities, Markdown chunks, and structured tables directly (data.commit) or ingest 70+ file formats via DocIntel. Invoke a specific tool with message.metadata.skill = one of the tags.

    data.commitdata.get_tabledata.index_table_columnsdata.ingest_filedata.ingest_textdata.link_table_rowsdata.list_file_versionsdata.list_filesdata.patch_file_propertiesdata.query_table_rowsdata.replace_file
  • egress.*

    Stream graph and workflow changes to external HMAC-signed webhooks. Invoke a specific tool with message.metadata.skill = one of the tags.

    egress.add_sinkegress.list_sinksegress.remove_sinkegress.status
  • evolution.*

    Evolutionary multi-objective optimisation for RAG parameters, model routing, and online experiments. Invoke a specific tool with message.metadata.skill = one of the tags.

    evolution.create_experimentevolution.list_experimentsevolution.productionevolution.proposeevolution.rag_retrievalevolution.reportevolution.routing_policyevolution.suggest
  • feedback.*

    Collect and resolve human and agent quality feedback. Invoke a specific tool with message.metadata.skill = one of the tags.

    feedback.openfeedback.recordfeedback.resolvefeedback.summary
  • graph.*

    Unified LPG + RDF + Vector graph engine: read/write LPG nodes & edges, assert/import RDF quads, run conjunctive LPG+RDF semantic_query, hybrid_search, and graph algorithms (PageRank, communities, shortest_path, centrality, link_prediction, Moran's I). Invoke a specific tool with message.metadata.skill = one of the tags.

    graph.add_edgegraph.add_edges_bulkgraph.add_nodegraph.add_nodes_bulkgraph.articulation_pointsgraph.assert_statementgraph.attack_pathsgraph.auto_configgraph.bipartite_checkgraph.bipartite_matchinggraph.bridgesgraph.centralitygraph.communitiesgraph.countsgraph.delete_edgegraph.delete_nodegraph.dynamic_communitiesgraph.dynamic_pagerankgraph.edges_countgraph.edges_exist
  • guardrails.*

    Evaluate input, output, and structural agent payloads against safety/PII/injection guardrails. Invoke a specific tool with message.metadata.skill = one of the tags.

    guardrails.evaluate
  • Show all 11 remaining skills
    • journey.*

      Run stateful multi-stage workflows with SLAs, Human-In-The-Loop (HITL) gates, and immutable audit trails. Invoke a specific tool with message.metadata.skill = one of the tags.

      journey.advancejourney.auditjourney.definejourney.listjourney.list_hitljourney.resolve_hitljourney.sla_alertsjourney.startjourney.status
    • memory.*

      Search and read conversation session memory. Invoke a specific tool with message.metadata.skill = one of the tags.

      memory.historymemory.search
    • models.*

      Manage the LLM model catalogue and dynamic System-1/System-2 routing policy. Invoke a specific tool with message.metadata.skill = one of the tags.

      models.get_policymodels.listmodels.removemodels.route_explainmodels.search_knownmodels.set_policymodels.upsert
    • quantum.*

      Quantum-inspired QUBO/Ising optimisation (routing, scheduling, portfolio allocation, tensor networks). Invoke a specific tool with message.metadata.skill = one of the tags.

      quantum.annealquantum.comparequantum.encode_statequantum.measurequantum.optimizequantum.profilequantum.simulatequantum.vqe_step
    • rag.*

      Answer questions over the knowledge graph (vector, graph and hybrid RAG). Invoke a specific tool with message.metadata.skill = one of the tags.

      rag.graph_queryrag.hybrid_queryrag.profile_collectionrag.queryrag.rerankrag.tune_collection
    • registry.*

      Federate external REST tools, downstream MCP servers, and peer A2A agents. Invoke a specific tool with message.metadata.skill = one of the tags.

      registry.list_toolsregistry.register_a2a_agentregistry.register_mcp_serverregistry.register_toolregistry.remove_toolregistry.test_tool
    • scheduler.*

      Schedule interval, cron, and CDC event/drift-triggered automations. Invoke a specific tool with message.metadata.skill = one of the tags.

      scheduler.add_triggerscheduler.list_triggersscheduler.remove_triggerscheduler.status
    • schema.*

      Declare and validate the data model (node types, edge types, property constraints, IAM classifications). Invoke a specific tool with message.metadata.skill = one of the tags.

      schema.define_edge_typeschema.define_node_typeschema.delete_edge_typeschema.delete_node_typeschema.getschema.get_edge_typeschema.get_node_typeschema.list_edge_typesschema.list_node_typesschema.update_edge_typeschema.update_node_typeschema.validate
    • sentinel.*

      Autonomous data-drift and risk-threshold findings gated by human approval. Invoke a specific tool with message.metadata.skill = one of the tags.

      sentinel.drift_checksentinel.get_findingsentinel.list_findingssentinel.rejectsentinel.summary
    • soc.*

      Autonomous Security Operations Center (SOC): threat detection statistics, active session containments, and security incident audit logs. Invoke a specific tool with message.metadata.skill = one of the tags.

      soc.audit_logsoc.containments_activesoc.stats
    • supergraph.*

      Federated multi-graph stitching: list declared regional/domain peers and execute approved cross-graph queries. Invoke a specific tool with message.metadata.skill = one of the tags.

      supergraph.peers_listsupergraph.query