# Long-Term Memory _Last updated: 16.Apr.2026_ ## Current System (as of 16.Apr.2026) - **Host:** FreeBSD 15.0 bare-metal, ZFS, Bastille jails, 12 GB RAM - **Agent runtime:** TypeScript (Node.js 24), compiled via `tsc` to `dist/` - **Databases:** PostgreSQL 18 + pgvector on host (`DB_RUNTIME=host`), not in a jail - `{agent}_ops` — tasks, agents, activity, budgets, approvals - `{agent}_skills` — preloaded knowledge chunks (read-only) - `{agent}_memory` — user/agent dynamic memory with embeddings - **LLM:** Multiple providers via `PI_TUI_PROVIDER` (zai, openai, local llama-cpp) - **Control Plane:** Multi-agent orchestrator (port 3100) - Roles: Orchestrator (80% budget), Sysadmin (10%), DBA (5%), Git Admin (5%) - Identity files in `.agent/identities/` (SYSADMIN.md, DB_ADMIN.md, GIT_ADMIN.md, COORDINATOR.md) - 46+ operational skills in `.agent/skills/` - **Channels:** Telegram (grammy bot), HTTP REST API - **Jail isolation:** Phase 7 complete (behind `CONTROLPLANE_JAIL_ISOLATION` feature flag) - **Additive tenant path:** available for validating multi-agent + jail isolation without renaming the platform ## About Sam - **Name:** Samo Blatnik — call him Sam - **Location:** Near Ljubljana, Slovenia (Europe/Ljubljana, CET/CEST) - **Languages:** Slovenian (native), Croatian/Serbian, English (good) - **Background:** IT support (hardware, printers, general troubleshooting) - **Telegram ID:** 85126311 - **Dog:** Bucko - **CV:** https://samob.netlify.app/en/ ## Key Facts - SSH key authentication; ports 80, 443, 22 - Live host subnet: `192.168.72.0/24` (`AGENT_SUBNET_BASE` / `WARDEN_SUBNET_BASE`), bridge `warden0`, gateway `.1` - Live running jails on this host: `git` (thin, .2), `cms` (thick, .3), `worker` (thick, .101) - Live non-running defined roles on this host: optional `db` (.5), `ollama`/`llama-cpp` (.4), agent workers (.211-.213) - PostgreSQL runs on the host (`DB_RUNTIME=host`, `DB_HOST=127.0.0.1`), not in a db jail - Repo registry default for fresh installs is `10.0.1.0/24` in `infra/jails.yaml`, but env overrides change the live host network - Current intended repo policy: shared jails are thin by default; only the optional `db` jail is thick - Install: `just install` (20-step orchestrator), `just` CLI front door (35+ recipes) - Docs: markdown source in `docs/public/`, auto-compiled to HTML and deployed daily - Remotes: `git@codeberg.org:Clawdie/Clawdie-AI.git` (primary), Clawdie-ISO is cross-repo ## Open Work Items 1. **Dashboard** — Agent-generated dashboards (Phase C/D) need FreeBSD testing 2. **Skills artifact V1** — Bootstrap `artifact.sql` when docs stabilize 3. **CONTROLPLANE_JAIL_ISOLATION=YES** — validate Phase 7e end-to-end on a test tenant or staging install 4. **Deploy to ai.clawdie.si** — DNS + nginx vhost for public API ## Historical Context (Feb–Mar 2026, old system) The sessions below predate the FreeBSD migration. They ran on a Debian/Hostinger VPS using Docker, OpenClaw v1/v2, and cloud LLMs (GLM, OpenRouter). That infrastructure is retired. These memories are kept for continuity — treat infra references in them as historical, not current. - [24.02.] Major session: 3 skills created, cost optimisation, assistant renamed to Clawdie, Telegram integration - [14.02.] PRD updates v0.3: SSH, Tailscale VPN, user 'clawdie', GLM-5 model configured - [11.02.] Collaborative tmux + Claude Code workflow established - [10.02.] Strapi CMS deployment planning - [09.02.] Memory persistence explained — context files are the persistent layer - [06.02.] Initial setup: Sam configured Clawdie as AI assistant, sudo access, fail2ban, cron