--- title: Nanobot type: agent status: active created: 2026-07-22 updated: 2026-10-11 verified_on: 2026-10-11 confidence: high tags: [agent, nanobot, homelab] sources: [live-probe, runtime-config] --- # Nanobot ## Purpose Primary homelab AI agent running on `clawtest` (CT333). Handles agent orchestration, memory, tool execution, and cross-channel messaging for Anthony. ## Location - **Host:** LXC 333, hostname `clawtest`, Tailscale IP `100.122.189.81`. - **User:** `nano` - **Workspace:** `/home/nano/.nanobot/workspace` ## Current state - **Status: ACTIVE.** Verified 2026-10-11: gateway process `nanobot-gateway` (PID 2259048) running and listening. - **Gateway:** port `8765` (HTTP API + chat completions) — `LISTEN 0.0.0.0:8765` - **WebSocket bridge:** port `8766` — `LISTEN 0.0.0.0:8766` - **Serve API:** port `8900` was recorded as the Serve API; **not listening** in the 2026-10-11 `ss -ltn` check. Treat as unverified/possibly removed. - **Service unit names:** earlier notes listed `whatsapp-bridge.service` — `systemctl is-active nanobot gateway` and `is-active gateway` are NOT valid here (both returned `inactive`). Nanobot runs as a user service under the `nanobot` user (`systemd --user`, PID 166) plus the `nanobot-gateway` process; it is **not** a system-level `nanobot.service`. Check the gateway port/process, not the systemd unit. ## Confirmed running on CT333 (2026-10-11) | Process | Owner | Port(s) | Notes | |---|---|---|---| | `nanobot-gateway` (PID 2259048) | — | 8765, 8766 | The gateway | | `mnemosyne` MCP (`mnemosyne mcp --transport std…`) | nano | — | `venvs/mnemosyne-mcp` venv | | `chroma_query_api.py` | nano | — | started Sep 23 | | `agentmail-daemon.py` | nano | — | started Sep 23 | | `readlater` Next dev server | nano | 3210 | started Sep 23 | Other listeners on CT333 include 8787, 8880, 8899, 8999, 3000, 5050, 8080 and the Tailscale 443. ## Docker on CT333 (verified 2026-10-11) `steel-browser`, `gotify`, `readlater`, `readlater-extraction-worker`, `kokoro-tts`, `edge-tts`, `onecli-postgres-1`, `tender_brattain`, plus healthy `community-spark` and `quirky_darwin`. ## Cron jobs Unverified against live Nanobot scheduler on 2026-10-11. Previously recorded: - `auto-upgrade-freellmapi-safeguard` — daily at 03:30 AWST - `morning-quota-report` — daily at 07:30 AWST - `daily-quota-730am` — daily at 07:30 AWST - `vault-daily-seed` — daily at 08:00 AWST - `daily-agent-briefing` — daily at 08:15 AWST - `rss-check-proxmox-selfhst` — Mon/Thu at 09:00 AWST - `daily-quota-7pm` — daily at 19:00 AWST - `evening-quota-report` — daily at 21:00 AWST - `heartbeat` — every 30m - `dream` — every 2h (memory consolidation) ## Skills Active skills include: `agent-reach`, `verify-nanobot-config-against-docs`, `cli-app-exa`, `playwright`, `system-prompts-collection`, `agent-skill-retrieval`, `enhanced-search`, `api-gateway`, `debugging-and-error-recovery`, `mnemosyne-memory-hooks`, `proxmox-shell-fallback`, `agentmail`, `langfuse`, `install-and-verify-agent-skills`, `verify-system-claims`, `skill-interceptor`, `tool-call-failure-recovery`, `using-agent-skills`, `api-vault`, `repair-memory`, `patch-config-relative-paths`, `long-task-management`, `nanobot-full-restore-backup`, `context-diet`, `frontend-design`. ## Connected systems - [[systems/hermes-agent]] - [[systems/omniroute]] - [[systems/gitea]] - [[systems/chromadb]] ## Known issues - Context window management requires periodic skill audits; baseline skill catalog + MCP schemas consume ~38–51K tokens per turn. - Model preset `freellmapi-auto` may route through fallback models depending on provider availability. - See [[incidents/nanobot-degraded-2026-08-07]] for prior outage. ## Relevant runbooks - [[runbooks/restart-hermes]] - [[runbooks/nanobot-restart]] ## Related - [[comparisons/hermes-vs-nanobot]]