AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.
-
Updated
Jul 12, 2026 - TypeScript
AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.
VeriClaw 爪印: Apple-native AI agent correction and OpenClaw companion workflow for LLM supervision, hallucination remediation, and role-drift diagnosis.
A Claude Code plugin that turns one natural-language goal into parallel tmux sessions — decompose, plan, implement, verify (independent test-quality audit), and merge through a methodology-grounded loop (TDD / PDCA / Reflexion). Gated where it matters: task-split approval + pre-merge review. Pluggable capability roles.
Claude Code plugin — a wiki-grounded implementation loop: planning is fixed to a semantic-layer wiki (wiki-plan), execution runs one TDD/PDCA/Reflexion verification loop citing the exact wiki pages it applies, and an auto-harvesting knowledge loop turns verified insights into reviewed wiki PRs. Merges loop-orchestrator + dev-llm-wiki.
A dashboard watching itself being built - every feature shipped by a maker-checker loop (Claude + Codex + TestSprite), rendered as the app itself. TestSprite S3 hackathon.
Add a description, image, and links to the verification-loop topic page so that developers can more easily learn about it.
To associate your repository with the verification-loop topic, visit your repo's landing page and select "manage topics."