v0.1.0

First release. ACR is a local-first, model-independent AI orchestration
and cognitive runtime: a real task engine, hybrid-retrieval memory store,
skill registry with routing/validation/evolution, model and tool routing
with safe-mode-aware permission checks, an agent planner/critic/topology
system, an operational dashboard with a real-telemetry visualization, an
MCP server (including a Claude Code project integration via .mcp.json),
web/browser/GitHub search tools, and controlled, approval-gated
self-improvement proposals.

Every phase in the master specification (ACR_MASTER_SYSTEM_PROMPT.md)
has at least a smallest-complete-vertical-slice implementation — see
docs/ARCHITECTURE.md
for exactly what's real versus deliberately deferred (a desktop app and a
few Phase 15 sub-bullets remain explicitly out of scope for now).

Runs entirely on SQLite with a zero-config mock model provider by
default — no cloud account or API key required to try it. Real local
(Ollama) or cloud routing is available via --min-quality-tier.

pip install acr-runtime
acr db upgrade
acr doctor
acr run "say hello"

Development status: Alpha. 305 tests passing, CI green, ruff/pyright
clean.