NousResearch/hermes-agent

• CAI 54 → 56 (+2.0)
• Rubric changed (rubric-2026.08.17 → rubric-2026.08.18) — scores are not directly comparable.

• Code Health 62 → 66 (+3.9)
• Architecture 88 → 84 (-3.4)
• Maturity 72 → 75 (+2.5)
• Readiness 50 → 53 (+2.9)
• Security 53 → 58 (+5.5)
• Domain Modelling 100 → 100 (+0.0)
• Event Sourcing 100 → 100 (+0.0)
• Accessibility 49 → 49 (+0.4)

• (anonymous) (cognitive 89) (plugins/platforms/photon/sidecar/index.mjs)
• (anonymous) (cyclomatic 59) (plugins/platforms/photon/sidecar/index.mjs)
• AIAgent._capture_credits (cognitive 26) (run_agent.py)
• AIAgent._capture_credits (cyclomatic 19) (run_agent.py)
• AIAgent._coerce_api_error_detail (cognitive 23) (run_agent.py)
• AIAgent._extract_codex_interim_visible_parts (cognitive 28) (run_agent.py)
• AIAgent._extract_codex_interim_visible_parts (cyclomatic 16) (run_agent.py)
• AIAgent._fire_stream_delta (cognitive 22) (run_agent.py)
• AIAgent._fire_stream_delta (cyclomatic 16) (run_agent.py)
• AIAgent._flush_messages_to_session_db_unlocked (cognitive 72) (run_agent.py)
• AIAgent._flush_messages_to_session_db_unlocked (cyclomatic 45) (run_agent.py)
• AIAgent._hook_jsonable (cognitive 32) (run_agent.py)
• AIAgent._hook_jsonable (cyclomatic 22) (run_agent.py)
• AIAgent._hydrate_todo_store (cognitive 20) (run_agent.py)
• AIAgent._is_thinking_only_assistant (cognitive 35) (run_agent.py)
• AIAgent._is_thinking_only_assistant (cyclomatic 24) (run_agent.py)
• AIAgent._preprocess_anthropic_content (cognitive 34) (run_agent.py)
• AIAgent._preprocess_anthropic_content (cyclomatic 21) (run_agent.py)
• AIAgent._qwen_prepare_chat_messages (cognitive 24) (run_agent.py)
• AIAgent._qwen_prepare_chat_messages_inplace (cognitive 24) (run_agent.py)
• …and 3800 more

• Dependency hygiene not measured — dependency manifest found but not parsed for hygiene
• No artifact signing
• No build provenance
• Off-boarding risk: anonymized user #2
• Off-boarding risk: anonymized user #4
• Off-boarding risk: anonymized user #3
• Off-boarding risk: anonymized user #1
• Secret passed as a command-line argument

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

NousResearch/hermes-agent was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.