# cogitator-02: an Apple Silicon Mac on the tailnet. Ansible manages it as # phil; only tasks that set `become: true` use sudo. ansible_python_interpreter: /usr/bin/python3 ansible_become_password: "{{ vault_cogitator02.become_password }}" homebrew_taps: - beeper/tap homebrew_formulae: - beeper/tap/bbctl homebrew_casks: - beeper - claude-code # Power settings (pmset, AC power). The Mac had `sleep 1` and only stayed up # because BlueBubbles runs caffeinate; this keeps it up on its own. mac_pmset: sleep: 0 # never sleep disksleep: 0 # never spin down disks autorestart: 1 # power back on after a power cut womp: 1 # wake on network access # Hermes's web dashboard: a launchd service listening on 127.0.0.1 only, # published to the tailnet over HTTPS by Tailscale Serve. hermes_dashboard_port: 9119 hermes_dashboard_url: "https://{{ ansible_host }}" hermes_dashboard_username: admin # Individual Hermes settings, set with `hermes config set`. The rest of # ~/.hermes/config.yaml stays Hermes's own (its updates migrate that file). hermes_settings: updates.pre_update_backup: full # zip of ~/.hermes before every update timezone: America/Denver # cron schedules and the time in the prompt # Never borrow Claude Code's login: subscription use outside Anthropic's own # apps breaks its terms, and refreshing it can break Claude Code's login. auth.adopt_external_logins: false # Hermes's default. /workspace (a container path) made the host log a # warning every few seconds (hermes-agent #140527); with the docker backend # a host cwd never becomes the container's working directory anyway. terminal.cwd: . terminal.container_memory: 3072 # MB; must fit in the Podman VM (podman_machine_memory) # Kanban is for multi-agent boards (unused here) and its 14 tools were 25 KB # of the 65 KB of tool definitions sent with every message. agent.disabled_toolsets: [kanban] skills.write_approval: true # skills Hermes writes wait for your approval # Never run these, even in the sandbox and even under /yolo (examples from # Hermes's hardening guide). Case-insensitive globs over the whole command. approvals.deny: - "git push --force*" - "*curl*|*sh*" - "dd if=* of=/dev/*" streaming.enabled: true # replies stream into Telegram as they're written stt.local.model: small # voice notes: more accurate than base # Models (OpenRouter), from the Nov 2026 review of Nous's Hermes Index # (portal.nousresearch.com/bench): chat on GPT-6.1 Sol (best value of the # premium models there), background work on cheap models. model.default: openai/gpt-6.1-sol agent.reasoning_effort: high # the level Nous benchmarks at (was ultra) # /model deepseek or /model haiku in Telegram; add --once for one reply. model_aliases.deepseek: {model: deepseek/deepseek-v4.1-flash, provider: openrouter} model_aliases.haiku: {model: anthropic/claude-haiku-5.5, provider: openrouter} # Side tasks would otherwise run on the chat model ("auto"). GLM-5.3 Flash # is the cheapest model with credible Hermes scores; its slow first token # doesn't matter here. Vision, voice and /review stay on the chat model. auxiliary.compression.provider: openrouter auxiliary.compression.model: z-ai/glm-5.3-flash auxiliary.approval.provider: openrouter auxiliary.approval.model: z-ai/glm-5.3-flash auxiliary.title_generation.provider: openrouter auxiliary.title_generation.model: z-ai/glm-5.3-flash auxiliary.mcp.provider: openrouter auxiliary.mcp.model: z-ai/glm-5.3-flash auxiliary.memory_query_rewrite.provider: openrouter auxiliary.memory_query_rewrite.model: z-ai/glm-5.3-flash auxiliary.curator.provider: openrouter auxiliary.curator.model: z-ai/glm-5.3-flash auxiliary.monitor.provider: openrouter auxiliary.monitor.model: z-ai/glm-5.3-flash # Unpinned cron jobs. Per-job reasoning effort: set --reasoning-effort low # when creating agent jobs (there's no global cron setting for it). cron.model_provider: openrouter cron.model: z-ai/glm-5.3-flash # Subagents: DeepSeek V4.1 Flash does shell work better than the other # cheap models (TerminalBench 17.5 vs GPT-6 Luna 6.3). delegation.provider: openrouter delegation.model: deepseek/deepseek-v4.1-flash mcp_servers.karakeep: "{{ hermes_mcp_karakeep }}" # MCP servers. Each stdio server runs in a throwaway Podman container (not on # the Mac itself); secrets come from ~/.hermes/.env (hermes_env_secrets) and # are passed to the container by name, never on the command line. hermes_mcp_podman_args: [run, -i, --rm] # Karakeep (bookmarks): search/read, create, tag, add to list. No update or # delete tools are registered. trust: full because Karakeep doesn't mark its # search tools read-only, so "untrusted" would ask before every search. # github.com/karakeep-app/karakeep/tree/main/apps/mcp hermes_karakeep_mcp_image: ghcr.io/karakeep-app/karakeep-mcp:0.34.1 hermes_mcp_karakeep: command: /opt/podman/bin/podman args: "{{ hermes_mcp_podman_args + ['-e', 'KARAKEEP_API_ADDR', '-e', 'KARAKEEP_API_KEY', hermes_karakeep_mcp_image] }}" env: KARAKEEP_API_ADDR: "https://{{ subdomains.bookmarks }}" KARAKEEP_API_KEY: "${KARAKEEP_API_KEY}" lazy: true # start the container on first use idle_timeout_seconds: 600 # and stop it after 10 idle minutes tools: include: - search-bookmarks - get-bookmark - get-bookmark-content - get-bookmark-lists - get-lists - get-list - get-list-bookmarks - get-tags - get-tag - get-tag-bookmarks - create-bookmark - attach-tag-to-bookmark - add-bookmark-to-list resources: false prompts: false # Secrets written to ~/.hermes/.env (single-quoted), from the vault. hermes_env_secrets: KARAKEEP_API_KEY: "{{ vault_cogitator02.karakeep_api_key }}" # Keys `hermes config set` refuses without --force although Hermes reads them # (agent.reasoning_effort: hermes-agent #140221). hermes_settings_force: [agent.reasoning_effort] # Podman VM that runs Hermes's sandbox containers. podman_machine_memory: 4096 # MB # Hermes cron jobs. `script` is a file in roles/mac/files/hermes-scripts/, # copied to ~/.hermes/scripts/ (with an agent job its output is injected into # the prompt). Optional: model + provider (pin), reasoning_effort, continuity. # Jobs are created when missing; to change one, remove it in Hermes # (`hermes cron remove `) and redeploy. hermes_cron_jobs: - name: hermes-update-notice schedule: "7 9 * * 1" # Mondays 09:07 script: hermes-update-notice.sh no_agent: true # just the script's output, no model deliver: telegram - name: hermes-model-review schedule: "7 9 1 * *" # 1st of the month, 09:07 script: hermes-model-context.sh # current setup + usage, injected into the prompt model: openai/gpt-6.1-sol # a report you act on: strong model, pinned provider: openrouter reasoning_effort: high continuity: true # sees last month's report, says what changed deliver: telegram prompt: >- Monthly review of which AI models this Hermes install should use. The current setup and last month's usage are above. Research what changed since last month, using primary sources where possible: (1) Nous Research's Hermes Index, https://portal.nousresearch.com/bench (agent tasks run inside Hermes; note it is run by Nous, who also sell model access); (2) OpenRouter's Hermes Agent app rankings, https://openrouter.ai/apps/hermes-agent, remembering that token volume mostly reflects cheap automated workloads, not chat quality; (3) current prices from https://openrouter.ai/api/v1/models; (4) notable model releases and Hermes release notes from the past month that affect model choice. Then, for each slot (chat model and reasoning effort, side tasks, cron, subagents, /model aliases), say keep or change, with the evidence, a link, and the rough monthly cost difference at the current usage. Only recommend a change when the evidence is clearly better, not just newer. Don't change any settings: they are managed with Ansible, so end with the exact keys and values to change, if any. Keep it under 300 words. If nothing should change, say so in two sentences.