Skip to content

Releases: hbkdad/arc

Release list

v0.2.0

v0.2.0 Latest
Latest

Choose a tag to compare

View all tags
@hbkdad hbkdad released this 01 Aug 19:18
v0.2.0
286cbe3

Second release of acr-runtime. 45 commits since v0.1.0.

Highlights

  • Per-role tiered routing — spawn_agent_with_escalation(): start cheap, only pay for a higher quality tier if the cheap attempt fails review.
  • Paired trajectory auditing — acr skills audit-trajectory: a real LLM judge compares baseline vs. candidate skill on the same live objective before proposing a promotion.
  • Dashboard /settings page — configure Claude/OpenAI API keys from the browser, live in-process, no restart.
  • A third dashboard theme (Observatory) — designed by running ACR's own trial-and-error skill-evolution loop against a local Ollama model.
  • Two full audits (security, architecture, tests, dashboard, docs; the second added performance) with real fixes: a critical approve-flow crash, a judge false-positive risk, a CSRF gap, a skill-ID path-traversal risk, a prompt-injection surface in the trajectory judge, a .env test-isolation gap, and a SQL-side rewrite of usage aggregation for a route polled every 2 seconds.
  • Ko-fi support link + .github/FUNDING.yml.

Full details in docs/ARCHITECTURE.md.

pip install --upgrade acr-runtime
Assets 2
Loading

v0.1.0

v0.1.0

Choose a tag to compare

View all tags
@hbkdad hbkdad released this 29 Jul 00:34
v0.1.0
7a27cf9

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.

Loading