| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 138.197.113.180 | 10.11.1.4 |
| 2 | agent | ai:bob | 165.227.65.116 | 10.11.1.2 |
| 3 | agent | ai:charlie | 104.131.100.128 | 10.11.1.3 |
| 4 | memory-only | — | 138.197.82.179 | 10.11.1.5 |
Per the authoritative baseline spec, every agent node must emit a self-attestation before any scenario is permitted to run. This run's attestation:
Spec version: 1.4.0 — see authoritative baseline.
| Node | Agent | Framework | Authentic | MCP ai-memory | xAI cfg | xAI default | Agent ID | Federation | UFW off | iptables | dead-man | F1 xAI | F2a substrate | F2b agent (non-gating) | Config SHA | Pass |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| node-1 | ai:alice | hermes Hermes Agent v0.10.0 (2026.4.16) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | fa358f9a9059 | PASS |
| node-2 | ai:bob | hermes Hermes Agent v0.10.0 (2026.4.16) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 21635cf63640 | PASS |
| node-3 | ai:charlie | hermes Hermes Agent v0.10.0 (2026.4.16) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | ce52d772ef5a | PASS |
{
"baseline_pass": true,
"per_node": [
{
"spec_version": "1.4.0",
"agent_type": "hermes",
"agent_id": "ai:alice",
"node_index": "1",
"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
"ai_memory_version": "0.6.2-rc.0",
"peer_urls": "https://10.11.1.2:9077,https://10.11.1.3:9077,https://10.11.1.5:9077",
"config_file_sha256": "fa358f9a90597243fb96224babd541399bd7b1e972f364605308ab1e2d9dd2c7",
"config_attestation": {
"framework_is_authentic": true,
"mcp_server_ai_memory_registered": true,
"llm_backend_is_xai_grok": true,
"llm_is_default_provider": true,
"mcp_command_is_ai_memory": true,
"agent_id_stamped": true,
"federation_live": true,
"ufw_disabled": true,
"iptables_flushed": true,
"dead_man_switch_scheduled": true
},
"negative_invariants": {
"_description": "Alternative A2A channels must be OFF so a passing scenario is only passing via ai-memory shared memory. Any true here = thesis-preserving.",
"a2a_protocol_off": true,
"sub_agent_or_sessions_spawn_off": true,
"alternative_channels_off": true,
"tool_allowlist_is_memory_only": true,
"a2a_gate_profile_locked": true
},
"functional_probes": {
"xai_grok_chat_reachable": true,
"xai_grok_sample_reply": "READY",
"substrate_http_canary_f2a": true,
"substrate_http_canary_uuid": "daa4e21c-196e-461f-a5c9-3e1953afe4ae",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "faa51cd7-446e-4849-b79c-1f5624f58ca5",
"agent_canary_response_head": "Traceback (most recent call last): File \"/usr/local/bin/hermes\", line 11, in <module> main() File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 8813, in main args.func(args) File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1145, in cmd_chat from cli import main as cli_main File \"/root/.hermes/hermes-agent/cli.py\", line 43, in <module> from prompt_toolkit.history import FileHistory ModuleNotFoundError: No module named 'prompt_toolkit' ",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"mesh_connectivity_f4": true,
"mesh_edges_ok": 3,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.11.1.2:9077:OK,10.11.1.3:9077:OK,10.11.1.5:9077:OK",
"_f4_note": "F4 verifies this local nodes N-1 OUTBOUND mesh edges to every peer via both GET health and POST sync_push dry_run. Aggregator ANDs across N nodes to confirm full N*(N-1) bidirectional reachability. Gates baseline_pass.",
"ai_memory_mcp_stdio_f5": true,
"ai_memory_mcp_stdio_init_ok": true,
"ai_memory_mcp_stdio_tools_ok": true,
"ai_memory_mcp_stdio_tools_found": "memory_agent_list,memory_agent_register,memory_archive_list,memory_archive_purge,memory_archive_restore,memory_archive_stats,memory_auto_tag,memory_capabilities,memory_consolidate,memory_delete,memory_detect_contradiction,memory_expand_query,memory_forget,memory_gc,memory_get,memory_get_links,memory_inbox,memory_link,memory_list,memory_list_subscriptions,memory_namespace_clear_standard,memory_namespace_get_standard,memory_namespace_set_standard,memory_notify,memory_pending_approve,memory_pending_list,memory_pending_reject,memory_promote,memory_recall,memory_search,memory_session_start,memory_stats,memory_store,memory_subscribe,memory_unsubscribe,memory_update",
"_f5_note": "F5 spawns the ai-memory stdio MCP subprocess using the framework-configured invocation and verifies initialize + tools/list return memory_store, memory_recall, memory_list. Deterministic (no LLM). Gates baseline_pass.",
"tls_mode": "tls",
"tls_handshake_f6": true,
"tls_handshake_f6_reason": "",
"mtls_enforcement_f7": true,
"mtls_enforcement_f7_reason": "",
"_f6_f7_note": "F6 verifies the TLS 1.3 handshake against the local serve + CA chain. F7 verifies mTLS enforcement — anonymous client rejected, whitelisted client accepted. Both gate baseline_pass when tls_mode != off / mtls respectively.",
"agent_mcp_ai_memory_canary": true,
"canary_uuid": "daa4e21c-196e-461f-a5c9-3e1953afe4ae",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
},
{
"spec_version": "1.4.0",
"agent_type": "hermes",
"agent_id": "ai:bob",
"node_index": "2",
"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
"ai_memory_version": "0.6.2-rc.0",
"peer_urls": "https://10.11.1.4:9077,https://10.11.1.3:9077,https://10.11.1.5:9077",
"config_file_sha256": "21635cf6364057fd2a004d28aac89abf8438671d85f9fd2ed1e654d812d23ff1",
"config_attestation": {
"framework_is_authentic": true,
"mcp_server_ai_memory_registered": true,
"llm_backend_is_xai_grok": true,
"llm_is_default_provider": true,
"mcp_command_is_ai_memory": true,
"agent_id_stamped": true,
"federation_live": true,
"ufw_disabled": true,
"iptables_flushed": true,
"dead_man_switch_scheduled": true
},
"negative_invariants": {
"_description": "Alternative A2A channels must be OFF so a passing scenario is only passing via ai-memory shared memory. Any true here = thesis-preserving.",
"a2a_protocol_off": true,
"sub_agent_or_sessions_spawn_off": true,
"alternative_channels_off": true,
"tool_allowlist_is_memory_only": true,
"a2a_gate_profile_locked": true
},
"functional_probes": {
"xai_grok_chat_reachable": true,
"xai_grok_sample_reply": "READY",
"substrate_http_canary_f2a": true,
"substrate_http_canary_uuid": "63876d14-e37c-4777-af4e-6da8650b84d8",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "de416a37-53e7-478b-b3c4-89f2bafe2ff1",
"agent_canary_response_head": "Traceback (most recent call last): File \"/usr/local/bin/hermes\", line 11, in <module> main() File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 8813, in main args.func(args) File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1145, in cmd_chat from cli import main as cli_main File \"/root/.hermes/hermes-agent/cli.py\", line 43, in <module> from prompt_toolkit.history import FileHistory ModuleNotFoundError: No module named 'prompt_toolkit' ",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"mesh_connectivity_f4": true,
"mesh_edges_ok": 3,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.11.1.4:9077:OK,10.11.1.3:9077:OK,10.11.1.5:9077:OK",
"_f4_note": "F4 verifies this local nodes N-1 OUTBOUND mesh edges to every peer via both GET health and POST sync_push dry_run. Aggregator ANDs across N nodes to confirm full N*(N-1) bidirectional reachability. Gates baseline_pass.",
"ai_memory_mcp_stdio_f5": true,
"ai_memory_mcp_stdio_init_ok": true,
"ai_memory_mcp_stdio_tools_ok": true,
"ai_memory_mcp_stdio_tools_found": "memory_agent_list,memory_agent_register,memory_archive_list,memory_archive_purge,memory_archive_restore,memory_archive_stats,memory_auto_tag,memory_capabilities,memory_consolidate,memory_delete,memory_detect_contradiction,memory_expand_query,memory_forget,memory_gc,memory_get,memory_get_links,memory_inbox,memory_link,memory_list,memory_list_subscriptions,memory_namespace_clear_standard,memory_namespace_get_standard,memory_namespace_set_standard,memory_notify,memory_pending_approve,memory_pending_list,memory_pending_reject,memory_promote,memory_recall,memory_search,memory_session_start,memory_stats,memory_store,memory_subscribe,memory_unsubscribe,memory_update",
"_f5_note": "F5 spawns the ai-memory stdio MCP subprocess using the framework-configured invocation and verifies initialize + tools/list return memory_store, memory_recall, memory_list. Deterministic (no LLM). Gates baseline_pass.",
"tls_mode": "tls",
"tls_handshake_f6": true,
"tls_handshake_f6_reason": "",
"mtls_enforcement_f7": true,
"mtls_enforcement_f7_reason": "",
"_f6_f7_note": "F6 verifies the TLS 1.3 handshake against the local serve + CA chain. F7 verifies mTLS enforcement — anonymous client rejected, whitelisted client accepted. Both gate baseline_pass when tls_mode != off / mtls respectively.",
"agent_mcp_ai_memory_canary": true,
"canary_uuid": "63876d14-e37c-4777-af4e-6da8650b84d8",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
},
{
"spec_version": "1.4.0",
"agent_type": "hermes",
"agent_id": "ai:charlie",
"node_index": "3",
"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
"ai_memory_version": "0.6.2-rc.0",
"peer_urls": "https://10.11.1.4:9077,https://10.11.1.2:9077,https://10.11.1.5:9077",
"config_file_sha256": "ce52d772ef5a00968db29fb80eea7a14206b0a258a00ff2165db725405474618",
"config_attestation": {
"framework_is_authentic": true,
"mcp_server_ai_memory_registered": true,
"llm_backend_is_xai_grok": true,
"llm_is_default_provider": true,
"mcp_command_is_ai_memory": true,
"agent_id_stamped": true,
"federation_live": true,
"ufw_disabled": true,
"iptables_flushed": true,
"dead_man_switch_scheduled": true
},
"negative_invariants": {
"_description": "Alternative A2A channels must be OFF so a passing scenario is only passing via ai-memory shared memory. Any true here = thesis-preserving.",
"a2a_protocol_off": true,
"sub_agent_or_sessions_spawn_off": true,
"alternative_channels_off": true,
"tool_allowlist_is_memory_only": true,
"a2a_gate_profile_locked": true
},
"functional_probes": {
"xai_grok_chat_reachable": true,
"xai_grok_sample_reply": "Icannotcomplywiththisrequestasitappearsto",
"substrate_http_canary_f2a": true,
"substrate_http_canary_uuid": "9322fffe-6afe-4740-b499-646fff36f6c0",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "43b47496-ccd7-480b-b6f8-9472014f5b43",
"agent_canary_response_head": "Traceback (most recent call last): File \"/usr/local/bin/hermes\", line 11, in <module> main() File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 8813, in main args.func(args) File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1145, in cmd_chat from cli import main as cli_main File \"/root/.hermes/hermes-agent/cli.py\", line 43, in <module> from prompt_toolkit.history import FileHistory ModuleNotFoundError: No module named 'prompt_toolkit' ",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"mesh_connectivity_f4": true,
"mesh_edges_ok": 3,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.11.1.4:9077:OK,10.11.1.2:9077:OK,10.11.1.5:9077:OK",
"_f4_note": "F4 verifies this local nodes N-1 OUTBOUND mesh edges to every peer via both GET health and POST sync_push dry_run. Aggregator ANDs across N nodes to confirm full N*(N-1) bidirectional reachability. Gates baseline_pass.",
"ai_memory_mcp_stdio_f5": true,
"ai_memory_mcp_stdio_init_ok": true,
"ai_memory_mcp_stdio_tools_ok": true,
"ai_memory_mcp_stdio_tools_found": "memory_agent_list,memory_agent_register,memory_archive_list,memory_archive_purge,memory_archive_restore,memory_archive_stats,memory_auto_tag,memory_capabilities,memory_consolidate,memory_delete,memory_detect_contradiction,memory_expand_query,memory_forget,memory_gc,memory_get,memory_get_links,memory_inbox,memory_link,memory_list,memory_list_subscriptions,memory_namespace_clear_standard,memory_namespace_get_standard,memory_namespace_set_standard,memory_notify,memory_pending_approve,memory_pending_list,memory_pending_reject,memory_promote,memory_recall,memory_search,memory_session_start,memory_stats,memory_store,memory_subscribe,memory_unsubscribe,memory_update",
"_f5_note": "F5 spawns the ai-memory stdio MCP subprocess using the framework-configured invocation and verifies initialize + tools/list return memory_store, memory_recall, memory_list. Deterministic (no LLM). Gates baseline_pass.",
"tls_mode": "tls",
"tls_handshake_f6": true,
"tls_handshake_f6_reason": "",
"mtls_enforcement_f7": true,
"mtls_enforcement_f7_reason": "",
"_f6_f7_note": "F6 verifies the TLS 1.3 handshake against the local serve + CA chain. F7 verifies mTLS enforcement — anonymous client rejected, whitelisted client accepted. Both gate baseline_pass when tls_mode != off / mtls respectively.",
"agent_mcp_ai_memory_canary": true,
"canary_uuid": "9322fffe-6afe-4740-b499-646fff36f6c0",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
}
]
}
Workflow-level probe answering "can agents communicate through ai-memory?". Writer ai:alice posted canary UUID 310721a6-c0a1-43ae-9f90-061bceb90f22 to namespace _baseline_peer_canary via node-1's local ai-memory serve HTTP. After W=2 fanout settle, probe confirmed the canary on each of the 3 peer nodes via their local GET /api/v1/memories.
{
"probe": "F3",
"name": "peer-a2a-via-shared-memory",
"description": "Writer agent posts a canary via local ai-memory HTTP on node-1; verifies the row propagates to the 3 peer nodes (W=2/N=4 quorum) before scenarios run.",
"canary_uuid": "310721a6-c0a1-43ae-9f90-061bceb90f22",
"canary_namespace": "_baseline_peer_canary",
"writer_agent": "ai:alice",
"pass": false
}
Run focus
What this campaign tested: No scenarios were exercised, despite requesting 35 covering various transport, framework, and primitive axes, due to missing reports.
What it demonstrated: The results demonstrated a critical failure in the testing harness or infrastructure, preventing any data collection or validation.
AI NHI analysis · Claude Opus 4.7
FAIL — no scenarios executed or reported.
This test run didn't work at all because no results were collected from the planned scenarios. We can't tell if AI agents can reliably share memories with each other. It looks like there was a problem in setting up or running the tests.
High risk posture from complete campaign failure, indicating unresolved issues in the testing pipeline; production readiness remains unassessed. Customer-facing claims on agent memory sharing are unsupported by this run. No changes detected vs. prior runs as nothing was tested.
No per-scenario results available, with overall failure due to 'no scenario reports recovered'; all 35 requested scenarios (S1, S1b, S2, etc.) effectively skipped. Probable root cause in harness report aggregation or CI workflow (harness_sha: 9d280e8e7ad5debcdfa38e38b86fdf12be9f99fe). Impacts all primitives and frameworks under test.
Debug and resolve report recovery failures in the harness before retrying.