docs: security-first positioning + organic discoverability

docs: add Hugging Face mirror link + model-card metadata

feat(devices): multi-device task claiming — only the winning device executes a task

chore: bump device-reported version to 1.5.0

feat(brain): all-science reasoning upgrade — persistent memory injection, few-shot exemplars, actor-critic verification, uncertainty rule

docs: enterprise documentation suite — compliance mappings (CRA, ISO 27001, IEC 62443), threat model, data flow, audit & deployment guides, SBOM, use cases, security.txt

feat(brain): auto smart/cheap mode — per-task brain profiles with provider routing (simple/standard/complex heuristics, quality-first vs cost-first key ordering)

fix(parser): lenient answer salvage — no raw JSON leaks when the brain breaks JSON with unescaped quotes (e.g. German „..." quotes); 3 new tests

feat(reasoning): deep reasoning engine — plan, act, reflect, verify

feat(trace): deep insight — live run traces with per-step usage, tokens, timing and cost

feat(tools): persistent memory + web research tools for the agent

fix(cloud): WAF-safe transport — base64 bodies for agent API payloads

feat: enterprise capability expansion — app control, browser control, background execution

docs: README rewrite — story-driven, sharper, more readable

feat(agent): self-healing loop — auto-debug, auto-reasoning, iteration

fix(agent): robust tool-call parsing — prose, fences and nested braces

docs: compliance & trust — CRA, NIS2, EU AI Act, GDPR, SBOM

polish: community touchpoints — star/share links, CLI + installer CTAs

fix(cli): login crash on failed verify — readline used after close

feat(agent): agentic execution loop — the agent that acts

docs: examples and integrations — boot units, health check, automation recipes

docs: project documentation — guides, FAQ, architecture, security policy and contribution workflow

refactor: public repo = client agent only — control plane + server packages moved off GitHub

fix(installer): point dashboard URL at /dashboard

feat: desktop app packaging + engine/protocol/gateway packages, HTTP metrics pipeline

feat: merged enterprise monorepo — mona-expert 2.0

feat(dashboard): single-key enterprise UI — mona.expert only

feat: control plane platform + dashboard (dark glass UI)

refactor: agent never names an LLM provider or model

fix(tui): log panel cut off the two newest entries + auto-follow

feat: docker platform protocol — register, chat RPC, LLM proxy

feat: extended device metrics (cpu/mem/disk percent)

feat: versioned WS envelope (v:1) + capabilities in hello

feat: stop reconnect loop on credential rejection (4001/4003)

mo: rework terminal GUI — live connect flow, inline login, setup guide, v1.2.0

mo: installer — auto-add ~/.local/bin to PATH (fix 'command not found' after install)

mo: fix Authorization header case for Apache/PHP compatibility

mo: platform-aware API client, sngine integration, Docker support

mo: multi-OS support, API client, enhanced CLI and TUI

docs: add README with architecture, tools, and open-source model

test: add unit tests for tools, registry, and configuration

feat: add CLI with login, gui, start, status, and help commands

feat: add terminal dashboard with live system metrics

feat: add network operations tool with HTTP-only guard

feat: add file operations tool with workspace sandboxing

feat: add sandboxed shell execution with allowlist and pattern blocking

feat: add read-only system information tool

feat: introduce modular tool registry pattern

feat: add agent daemon with cloud-brain reasoning loop

feat: add WebSocket control channel with auto-reconnect