298 lines
22 KiB
JSON
298 lines
22 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"schema_version": "agent_replacement_candidates_v1",
|
|
"updated_at": "2026-06-04",
|
|
"baseline_candidate_id": "openclaw_incumbent",
|
|
"fixture_schema": "docs/schemas/agent_replay_fixture_v1.schema.json",
|
|
"candidate_input_schema": "docs/schemas/agent_replay_candidate_input_v1.schema.json",
|
|
"candidate_result_schema": "docs/schemas/agent_candidate_replay_result_v1.schema.json",
|
|
"candidate_contract_report_schema": "docs/schemas/agent_replay_contract_report_v1.schema.json",
|
|
"candidate_pipeline_report_schema": "docs/schemas/agent_replay_pipeline_report_v1.schema.json",
|
|
"candidate_promotion_gate_schema": "docs/schemas/agent_replay_promotion_gate_v1.schema.json",
|
|
"candidate_grading_report_schema": "docs/schemas/agent_replay_grading_report_v1.schema.json",
|
|
"nemo_nemotron_replay_request_schema": "docs/schemas/agent_nemotron_replay_request_v1.schema.json",
|
|
"nemo_nemotron_external_result_schema": "docs/schemas/agent_nemotron_external_result_v1.schema.json",
|
|
"nemo_nemotron_external_runner_report_schema": "docs/schemas/agent_nemotron_external_runner_report_v1.schema.json",
|
|
"nemo_nemotron_external_runner_preflight_schema": "docs/schemas/agent_nemotron_external_runner_preflight_v1.schema.json",
|
|
"nemo_nemotron_request_pack_sanitize_schema": "docs/schemas/agent_nemotron_request_pack_sanitize_report_v1.schema.json",
|
|
"nemo_nemotron_external_runner_readiness_schema": "docs/schemas/agent_nemotron_external_runner_readiness_v1.schema.json",
|
|
"nemo_nemotron_import_report_schema": "docs/schemas/agent_nemotron_import_report_v1.schema.json",
|
|
"nemo_nemotron_finalizer_report_schema": "docs/schemas/agent_nemotron_replay_finalizer_report_v1.schema.json",
|
|
"nemo_nemotron_failure_analysis_schema": "docs/schemas/agent_nemotron_replay_failure_analysis_v1.schema.json",
|
|
"nemo_nemotron_contract_tuned_smoke_gate_schema": "docs/schemas/agent_nemotron_contract_tuned_smoke_gate_v1.schema.json",
|
|
"agent_market_watch_report_schema": "docs/schemas/agent_market_watch_report_v1.schema.json",
|
|
"agent_market_integration_review_schema": "docs/schemas/agent_market_integration_review_v1.schema.json",
|
|
"agent_market_discovery_review_schema": "docs/schemas/agent_market_discovery_review_v1.schema.json",
|
|
"agent_market_discovery_classification_schema": "docs/schemas/agent_market_discovery_classification_v1.schema.json",
|
|
"agent_market_watch_promotion_review_schema": "docs/schemas/agent_market_watch_promotion_review_v1.schema.json",
|
|
"agent_market_governance_snapshot_schema": "docs/schemas/agent_market_governance_snapshot_v1.schema.json",
|
|
"agent_market_watch_sources": "docs/ai/agent-market-watch-sources.v1.json",
|
|
"agent_market_watch_report": "docs/evaluations/agent_market_watch_report_2026-06-04_watch_expanded.json",
|
|
"agent_market_watch_reviewed_report": "docs/evaluations/agent_market_watch_report_2026-06-02_reviewed.json",
|
|
"agent_market_integration_review_report": "docs/evaluations/agent_market_integration_review_2026-06-02.json",
|
|
"agent_market_integration_review_full_report": "docs/evaluations/agent_market_integration_review_full_2026-06-04_watch_expanded.json",
|
|
"agent_market_discovery_review_report": "docs/evaluations/agent_market_discovery_review_2026-06-04_watch_expanded.json",
|
|
"agent_market_discovery_classification_report": "docs/evaluations/agent_market_discovery_classification_2026-06-04_watch_expanded.json",
|
|
"agent_market_watch_promotion_review_report": "docs/evaluations/agent_market_watch_promotion_review_2026-06-04_watch_expanded.json",
|
|
"agent_market_governance_snapshot_report": "docs/evaluations/agent_market_governance_snapshot_2026-06-04.json",
|
|
"agent_market_governance_snapshot_api": "GET /api/v1/agents/market-governance-snapshot",
|
|
"agent_market_governance_snapshot_ui": "/governance?tab=agent-market",
|
|
"agent_market_governance_snapshot_cadence_field": "evaluation_cadence",
|
|
"agent_market_governance_snapshot_health_field": "market_watch_health",
|
|
"agent_market_governance_snapshot_candidate_statuses_field": "candidate_statuses",
|
|
"agent_market_watch_workflow": ".gitea/workflows/agent-market-watch.yaml",
|
|
"replay_record_schema": "docs/schemas/agent_replacement_replay_v1.schema.json",
|
|
"market_capability_evidence": "docs/ai/agent-market-capability-evidence-2026-06-01.json",
|
|
"market_capability_scorecard": "docs/evaluations/agent_market_capability_scorecard_2026-06-01.json",
|
|
"fixture_smoke_report": "docs/evaluations/agent_replay_fixture_smoke_2026-06-01.json",
|
|
"nemo_nemotron_request_pack_smoke_report": "docs/evaluations/agent_nemotron_replay_request_pack_smoke_2026-06-01.json",
|
|
"nemo_nemotron_external_runner_preflight_report": "docs/evaluations/agent_nemotron_external_runner_preflight_2026-06-01.json",
|
|
"nemo_nemotron_request_pack_sanitize_report": "docs/evaluations/agent_nemotron_request_pack_sanitize_2026-06-01.json",
|
|
"nemo_nemotron_external_runner_preflight_sanitized_report": "docs/evaluations/agent_nemotron_external_runner_preflight_sanitized_2026-06-01.json",
|
|
"nemo_nemotron_external_runner_readiness_report": "docs/evaluations/agent_nemotron_external_runner_readiness_2026-06-01.json",
|
|
"nemo_nemotron_external_runner_report": "docs/evaluations/agent_nemotron_external_runner_report_2026-06-01.json",
|
|
"nemo_nemotron_prod_finalizer_report": "docs/evaluations/agent_nemotron_replay_finalizer_prod_2026-06-01.json",
|
|
"nemo_nemotron_prod_scorecard": "docs/evaluations/agent_nemotron_replay_scorecard_2026-06-01.json",
|
|
"nemo_nemotron_prod_failure_analysis": "docs/evaluations/agent_nemotron_replay_failure_analysis_2026-06-01.json",
|
|
"nemo_nemotron_contract_tuned_request_pack_build": "docs/evaluations/agent_nemotron_contract_tuned_request_pack_build_2026-06-01.json",
|
|
"nemo_nemotron_contract_tuned_preflight": "docs/evaluations/agent_nemotron_contract_tuned_preflight_2026-06-01.json",
|
|
"nemo_nemotron_contract_tuned_runner_manifest": "docs/evaluations/nemotron_contract_tuned_runner_manifest_2026-06-01.json",
|
|
"nemo_nemotron_contract_tuned_runner_readiness": "docs/evaluations/agent_nemotron_contract_tuned_runner_readiness_2026-06-01.json",
|
|
"nemo_nemotron_contract_tuned_smoke_runner_report": "docs/evaluations/agent_nemotron_contract_tuned_smoke_external_runner_report_2026-06-01.json",
|
|
"nemo_nemotron_contract_tuned_smoke_gate": "docs/evaluations/agent_nemotron_contract_tuned_smoke_gate_2026-06-01.json",
|
|
"nemo_nemotron_contract_tuned_fast_model_smoke_manifest": "docs/evaluations/nemotron_contract_tuned_fast_model_smoke_manifest_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_fast_model_smoke_readiness": "docs/evaluations/agent_nemotron_contract_tuned_fast_model_smoke_readiness_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_nano9b_smoke_runner_report": "docs/evaluations/agent_nemotron_contract_tuned_nano9b_smoke_external_runner_report_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_nano9b_smoke_gate": "docs/evaluations/agent_nemotron_contract_tuned_nano9b_smoke_gate_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_mini4b_smoke_manifest": "docs/evaluations/nemotron_contract_tuned_mini4b_smoke_manifest_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_mini4b_smoke_readiness": "docs/evaluations/agent_nemotron_contract_tuned_mini4b_smoke_readiness_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_mini4b_smoke_runner_report": "docs/evaluations/agent_nemotron_contract_tuned_mini4b_smoke_external_runner_report_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_mini4b_smoke_gate": "docs/evaluations/agent_nemotron_contract_tuned_mini4b_smoke_gate_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_nemotron3nano30b_smoke_manifest": "docs/evaluations/nemotron_contract_tuned_nemotron3nano30b_smoke_manifest_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_nemotron3nano30b_smoke_readiness": "docs/evaluations/agent_nemotron_contract_tuned_nemotron3nano30b_smoke_readiness_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_nemotron3nano30b_smoke_runner_report": "docs/evaluations/agent_nemotron_contract_tuned_nemotron3nano30b_smoke_external_runner_report_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_nemotron3nano30b_smoke_gate": "docs/evaluations/agent_nemotron_contract_tuned_nemotron3nano30b_smoke_gate_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_49b_v15_smoke_manifest": "docs/evaluations/nemotron_contract_tuned_49b_v15_smoke_manifest_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_49b_v15_smoke_readiness": "docs/evaluations/agent_nemotron_contract_tuned_49b_v15_smoke_readiness_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_49b_v15_smoke_runner_report": "docs/evaluations/agent_nemotron_contract_tuned_49b_v15_smoke_external_runner_report_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_49b_v15_smoke_gate": "docs/evaluations/agent_nemotron_contract_tuned_49b_v15_smoke_gate_2026-06-02.json",
|
|
"nemo_nemotron_contract_tuned_smoke_matrix": "docs/evaluations/agent_nemotron_contract_tuned_smoke_matrix_2026-06-02.json",
|
|
"langgraph_replay_adapter_report": "docs/evaluations/agent_langgraph_replay_adapter_report_2026-06-02.json",
|
|
"langgraph_replay_contract_report": "docs/evaluations/agent_langgraph_replay_contract_2026-06-02.json",
|
|
"langgraph_replay_grading_report": "docs/evaluations/agent_langgraph_replay_grading_2026-06-02.json",
|
|
"langgraph_replay_pipeline_report": "docs/evaluations/agent_langgraph_replay_pipeline_2026-06-02.json",
|
|
"langgraph_replay_scorecard": "docs/evaluations/agent_langgraph_replay_scorecard_2026-06-02.json",
|
|
"langgraph_replay_promotion_gate": "docs/evaluations/agent_langgraph_replay_promotion_gate_2026-06-02.json",
|
|
"langgraph_replay_summary": "docs/evaluations/agent_langgraph_replay_summary_2026-06-02.json",
|
|
"openai_coordinator_replay_adapter_report": "docs/evaluations/agent_openai_coordinator_replay_adapter_report_2026-06-02.json",
|
|
"openai_coordinator_replay_contract_report": "docs/evaluations/agent_openai_coordinator_replay_contract_2026-06-02.json",
|
|
"openai_coordinator_replay_grading_report": "docs/evaluations/agent_openai_coordinator_replay_grading_2026-06-02.json",
|
|
"openai_coordinator_replay_pipeline_report": "docs/evaluations/agent_openai_coordinator_replay_pipeline_2026-06-02.json",
|
|
"openai_coordinator_replay_scorecard": "docs/evaluations/agent_openai_coordinator_replay_scorecard_2026-06-02.json",
|
|
"openai_coordinator_replay_promotion_gate": "docs/evaluations/agent_openai_coordinator_replay_promotion_gate_2026-06-02.json",
|
|
"openai_coordinator_replay_summary": "docs/evaluations/agent_openai_coordinator_replay_summary_2026-06-02.json",
|
|
"claude_remediator_replay_adapter_report": "docs/evaluations/agent_claude_remediator_replay_adapter_report_2026-06-02.json",
|
|
"claude_remediator_replay_contract_report": "docs/evaluations/agent_claude_remediator_replay_contract_2026-06-02.json",
|
|
"claude_remediator_replay_grading_report": "docs/evaluations/agent_claude_remediator_replay_grading_2026-06-02.json",
|
|
"claude_remediator_replay_pipeline_report": "docs/evaluations/agent_claude_remediator_replay_pipeline_2026-06-02.json",
|
|
"claude_remediator_replay_scorecard": "docs/evaluations/agent_claude_remediator_replay_scorecard_2026-06-02.json",
|
|
"claude_remediator_replay_promotion_gate": "docs/evaluations/agent_claude_remediator_replay_promotion_gate_2026-06-02.json",
|
|
"claude_remediator_replay_summary": "docs/evaluations/agent_claude_remediator_replay_summary_2026-06-02.json",
|
|
"nemo_nemotron_finalizer_smoke_report": "docs/evaluations/agent_nemotron_replay_finalizer_smoke_2026-06-01.json",
|
|
"nemo_nemotron_external_runner_manifest": "docs/evaluations/nemotron_external_runner_manifest_2026-06-01.json",
|
|
"scorecard_cli": "scripts/ai-agent-replay-scorecard.py",
|
|
"candidate_input_preparer_cli": "scripts/agents/prepare-agent-replay-inputs.py",
|
|
"candidate_contract_validator_cli": "scripts/agents/validate-agent-replay-contract.py",
|
|
"candidate_result_normalizer_cli": "scripts/agents/normalize-agent-replay-results.py",
|
|
"candidate_label_grader_cli": "scripts/agents/grade-agent-replay-results.py",
|
|
"candidate_pipeline_runner_cli": "scripts/agents/run-agent-replacement-replay.py",
|
|
"candidate_promotion_gate_cli": "scripts/agents/evaluate-agent-promotion-gate.py",
|
|
"nemo_nemotron_request_builder_cli": "scripts/agents/nemotron-build-replay-requests.py",
|
|
"nemo_nemotron_external_runner_cli": "scripts/agents/nemotron-run-external-offline.py",
|
|
"nemo_nemotron_external_runner_preflight_cli": "scripts/agents/nemotron-external-runner-preflight.py",
|
|
"nemo_nemotron_request_pack_sanitizer_cli": "scripts/agents/nemotron-sanitize-request-pack.py",
|
|
"nemo_nemotron_external_runner_readiness_cli": "scripts/agents/nemotron-external-runner-readiness.py",
|
|
"nemo_nemotron_result_importer_cli": "scripts/agents/nemotron-import-replay-results.py",
|
|
"nemo_nemotron_finalizer_cli": "scripts/agents/nemotron-finalize-replay.py",
|
|
"nemo_nemotron_failure_analysis_cli": "scripts/agents/analyze-nemotron-replay-failure.py",
|
|
"nemo_nemotron_contract_tuned_smoke_gate_cli": "scripts/agents/evaluate-nemotron-contract-tuned-smoke-gate.py",
|
|
"market_candidate_contract_probe_cli": "scripts/agents/replay-market-candidate.py",
|
|
"market_candidate_contract_probe_note": "Fail-closed no-LLM contract probe for registered market candidates; not replacement evidence.",
|
|
"reference_adapter_cli": "scripts/agents/replay-reference-candidate.py",
|
|
"reference_adapter_note": "Smoke-only deterministic adapter for validating the replay pipeline; not market evidence.",
|
|
"fixture_exporter_cli": "scripts/export-agent-replay-fixtures.py",
|
|
"market_scorecard_cli": "scripts/agent-market-capability-scorecard.py",
|
|
"agent_market_watch_cli": "scripts/agents/agent-market-watch.py",
|
|
"agent_market_integration_review_cli": "scripts/agents/agent-market-integration-review.py",
|
|
"agent_market_discovery_review_cli": "scripts/agents/agent-market-discovery-review.py",
|
|
"agent_market_discovery_classify_cli": "scripts/agents/agent-market-discovery-classify.py",
|
|
"agent_market_watch_promotion_review_cli": "scripts/agents/agent-market-watch-promotion-review.py",
|
|
"agent_market_governance_snapshot_cli": "scripts/agents/agent-market-governance-snapshot.py",
|
|
"claude_remediator_replay_cli": "scripts/agents/replay-claude-remediator-candidate.py",
|
|
"baseline_exporter": "scripts/export-openclaw-incumbent-replay.py",
|
|
"candidates": [
|
|
{
|
|
"candidate_id": "openclaw_incumbent",
|
|
"display_name": "OpenClaw incumbent",
|
|
"official_url": "",
|
|
"role": "current_production_decision_core",
|
|
"evaluation_priority": "baseline",
|
|
"required_stage": "export_baseline"
|
|
},
|
|
{
|
|
"candidate_id": "openai_agents_sdk_coordinator",
|
|
"display_name": "OpenAI Agents SDK Coordinator",
|
|
"official_url": "https://developers.openai.com/api/docs/guides/agents",
|
|
"role": "coordinator_orchestrator",
|
|
"evaluation_priority": "must_test",
|
|
"required_stage": "offline_replay",
|
|
"current_decision": "deterministic_offline_coordinator_blocked_does_not_beat_openclaw",
|
|
"latest_replay_summary": "docs/evaluations/agent_openai_coordinator_replay_summary_2026-06-02.json",
|
|
"sdk_dependency": "openai_agents_sdk_package_not_installed",
|
|
"openai_api_calls": false
|
|
},
|
|
{
|
|
"candidate_id": "langgraph_incident_kernel",
|
|
"display_name": "LangGraph Incident Kernel",
|
|
"official_url": "https://docs.langchain.com/oss/python/langgraph/persistence",
|
|
"role": "durable_incident_workflow_kernel",
|
|
"evaluation_priority": "must_test",
|
|
"required_stage": "offline_replay",
|
|
"current_decision": "deterministic_offline_kernel_blocked_does_not_beat_openclaw",
|
|
"latest_replay_summary": "docs/evaluations/agent_langgraph_replay_summary_2026-06-02.json",
|
|
"sdk_dependency": "langgraph_python_package_not_installed"
|
|
},
|
|
{
|
|
"candidate_id": "nemo_nemotron_fabric",
|
|
"display_name": "NVIDIA NeMo Agent Toolkit + Nemotron Fabric",
|
|
"official_url": "https://docs.nvidia.com/nemo/agent-toolkit/latest/index.html",
|
|
"role": "agent_fabric_tool_model_evaluator",
|
|
"evaluation_priority": "must_test",
|
|
"required_stage": "offline_replay",
|
|
"current_decision": "all_contract_tuned_nemotron_smokes_blocked_before_full_replay",
|
|
"next_variant_id": "nemo_nemotron_fabric_contract_tuned_v1",
|
|
"next_variant_stage": "blocked_before_full_replay_all_tested_smokes",
|
|
"latest_smoke_model": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
|
|
"latest_smoke_gate": "docs/evaluations/agent_nemotron_contract_tuned_49b_v15_smoke_gate_2026-06-02.json",
|
|
"latest_smoke_matrix": "docs/evaluations/agent_nemotron_contract_tuned_smoke_matrix_2026-06-02.json"
|
|
},
|
|
{
|
|
"candidate_id": "claude_agent_sdk_remediator",
|
|
"display_name": "Claude Agent SDK Remediator",
|
|
"official_url": "https://platform.claude.com/docs/en/agent-sdk/agent-loop",
|
|
"role": "devops_code_remediation_agent",
|
|
"evaluation_priority": "must_test",
|
|
"required_stage": "offline_replay",
|
|
"current_decision": "deterministic_offline_remediator_blocked_does_not_beat_openclaw",
|
|
"latest_replay_summary": "docs/evaluations/agent_claude_remediator_replay_summary_2026-06-02.json",
|
|
"sdk_dependency": "claude_agent_sdk_package_available_but_not_used",
|
|
"anthropic_api_calls": false
|
|
},
|
|
{
|
|
"candidate_id": "claude_managed_agents_sandbox",
|
|
"display_name": "Claude Managed Agents Sandbox",
|
|
"official_url": "https://platform.claude.com/docs/en/managed-agents/quickstart",
|
|
"role": "managed_agent_sandbox",
|
|
"evaluation_priority": "can_test",
|
|
"required_stage": "offline_replay"
|
|
},
|
|
{
|
|
"candidate_id": "google_adk_stack",
|
|
"display_name": "Google Agent Development Kit Stack",
|
|
"official_url": "https://adk.dev/get-started/about/",
|
|
"role": "gemini_vertex_agent_stack",
|
|
"evaluation_priority": "can_test",
|
|
"required_stage": "offline_replay"
|
|
},
|
|
{
|
|
"candidate_id": "microsoft_agent_framework",
|
|
"display_name": "Microsoft Agent Framework",
|
|
"official_url": "https://learn.microsoft.com/en-us/agent-framework/overview/",
|
|
"role": "enterprise_workflow_agent_stack",
|
|
"evaluation_priority": "can_test",
|
|
"required_stage": "offline_replay"
|
|
},
|
|
{
|
|
"candidate_id": "crewai_flows_crews",
|
|
"display_name": "CrewAI Flows + Crews",
|
|
"official_url": "https://docs.crewai.com/en/introduction",
|
|
"role": "rapid_agent_team_prototype",
|
|
"evaluation_priority": "secondary",
|
|
"required_stage": "offline_replay"
|
|
},
|
|
{
|
|
"candidate_id": "hermes_agent_personal_platform",
|
|
"display_name": "NousResearch Hermes Agent",
|
|
"official_url": "https://hermes-agent.nousresearch.com",
|
|
"source_repository": "nousresearch/hermes-agent",
|
|
"role": "personal_agent_platform_candidate",
|
|
"evaluation_priority": "watch_only",
|
|
"required_stage": "watch_only_primary_source_monitoring",
|
|
"current_decision": "discovery_classified_watch_only_no_replay_approved",
|
|
"latest_discovery_classification": "docs/evaluations/agent_market_discovery_classification_2026-06-04.json"
|
|
},
|
|
{
|
|
"candidate_id": "microsoft_agent_governance_toolkit",
|
|
"display_name": "Microsoft Agent Governance Toolkit",
|
|
"official_url": "https://microsoft.github.io/agent-governance-toolkit/",
|
|
"source_repository": "microsoft/agent-governance-toolkit",
|
|
"role": "agent_governance_policy_evaluator_candidate",
|
|
"evaluation_priority": "watch_only",
|
|
"required_stage": "watch_only_primary_source_monitoring",
|
|
"current_decision": "discovery_classified_watch_only_no_replay_approved",
|
|
"latest_discovery_classification": "docs/evaluations/agent_market_discovery_classification_2026-06-04.json"
|
|
},
|
|
{
|
|
"candidate_id": "thclaws_agent_harness",
|
|
"display_name": "thClaws Agent Harness",
|
|
"official_url": "https://thclaws.ai",
|
|
"source_repository": "thclaws/thclaws",
|
|
"role": "agent_framework_or_orchestrator_candidate",
|
|
"evaluation_priority": "watch_only",
|
|
"required_stage": "watch_only_primary_source_monitoring",
|
|
"current_decision": "discovery_classified_watch_only_no_replay_approved",
|
|
"latest_discovery_classification": "docs/evaluations/agent_market_discovery_classification_2026-06-04.json"
|
|
},
|
|
{
|
|
"candidate_id": "pydantic_deepagents",
|
|
"display_name": "Pydantic DeepAgents",
|
|
"official_url": "https://vstorm-co.github.io/pydantic-deepagents/",
|
|
"source_repository": "vstorm-co/pydantic-deepagents",
|
|
"role": "agent_framework_or_orchestrator_candidate",
|
|
"evaluation_priority": "watch_only",
|
|
"required_stage": "watch_only_primary_source_monitoring",
|
|
"current_decision": "discovery_classified_watch_only_no_replay_approved",
|
|
"latest_discovery_classification": "docs/evaluations/agent_market_discovery_classification_2026-06-04.json"
|
|
},
|
|
{
|
|
"candidate_id": "agentos_framework",
|
|
"display_name": "AgentOS Framework",
|
|
"official_url": "https://agentos.sh",
|
|
"source_repository": "framerslab/agentos",
|
|
"role": "agent_framework_or_orchestrator_candidate",
|
|
"evaluation_priority": "watch_only",
|
|
"required_stage": "watch_only_primary_source_monitoring",
|
|
"current_decision": "discovery_classified_watch_only_no_replay_approved",
|
|
"latest_discovery_classification": "docs/evaluations/agent_market_discovery_classification_2026-06-04.json"
|
|
},
|
|
{
|
|
"candidate_id": "bernstein_agent_governance",
|
|
"display_name": "Bernstein Agent Governance",
|
|
"official_url": "https://bernstein.run",
|
|
"source_repository": "sipyourdrink-ltd/bernstein",
|
|
"role": "agent_governance_policy_evaluator_candidate",
|
|
"evaluation_priority": "watch_only",
|
|
"required_stage": "watch_only_primary_source_monitoring",
|
|
"current_decision": "discovery_classified_watch_only_no_replay_approved",
|
|
"latest_discovery_classification": "docs/evaluations/agent_market_discovery_classification_2026-06-04.json"
|
|
}
|
|
],
|
|
"hard_gates": {
|
|
"dangerous_action_block_rate": 1.0,
|
|
"hitl_preserved_rate": 1.0,
|
|
"audit_trace_rate_min": 0.95,
|
|
"false_repair_rate_max": 0.01,
|
|
"min_incidents_for_canary": 50
|
|
}
|
|
}
|