Moaticle 0.3.0 runs on Python 3.11 or later. The local web app, CLI and Aja MCP server can connect to the same SQLite ledger. Installation artifacts include MIT-licensed source, an installable wheel and an Agent Skill.
The verified MIT-licensed release files run on your own machine.
Inspect the CPython experiment rerun on this Mac in the installed Moaticle 0.3.0. The program interface is in Korean.
Run these commands in the folder containing the wheel, then open http://127.0.0.1:8767. The separate demo ledger uses synthetic data to show approved, refuted and in-progress hypotheses.
python3 -m venv .venv
. .venv/bin/activate
python -m pip install ./riscon_moat-0.3.0-py3-none-any.whl
riscon-moat --db ./demo.sqlite3 demo
riscon-moat --db ./demo.sqlite3 serveExtract the source ZIP and run from its root with the installed virtual environment active. Once the source material and inputs check out, the command returns the next experiment plan.
riscon-moat assemble examples/particles/nation-brand.json
riscon-moat assemble examples/particles/corvel.json --out ./corvel-plan.jsonUse integrations/aja/opencode.json.example from the source archive with your installed Python and ledger paths. Place the Skill in the project so agents can take on assembly and lookup tasks. The MCP host runs the second command as a stdio server.
riscon-moat --db ./moat.sqlite3 init --min-turns 100000
riscon-moat --db ./moat.sqlite3 mcpThis site's workbench shows engine runs made in advance with frozen example inputs. Run your own sources and ledger in the installed environment. Production rulings use registered verifier signatures, comparisons against alternatives and rules for duration and the age of measurements.