{"slug":"the-h-ai-k-u-method","title":"the-h-ai-k-u-method","description":"H·AI·K·U (Human + AI Knowledge Unification) is a lifecycle orchestrator for structured AI-assisted work. Instead of loading instructions into the agent's context, H·AI·K·U drip-feeds one action at a time from a plan kept on disk — so runs survive context compaction, /clear, crashes, and even handoffs between humans. 24 built-in studios cover software, marketing, security, compliance, incident response, data pipelines, and more. Each stage has configurable autonomy (auto-advance, human review, or external sign-off), parallel adversarial review agents, and deterministic quality gates. The agent stays simple; the orchestrator holds the structure.","developer":"GigSmart","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T12:07:05.061Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/gigsmart/haiku-method.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"the-h-ai-k-u-method","source":{"ref":"main","sha":"42451f546de75e0c4f38d5d3bb0999e54661bf32","url":"https://github.com/gigsmart/haiku-method.git","path":"plugin","source":"git-subdir"},"homepage":"https://haikumethod.ai","description":"H·AI·K·U (Human + AI Knowledge Unification) is a lifecycle orchestrator for structured AI-assisted work. Instead of loading instructions into the agent's context, H·AI·K·U drip-feeds one action at a time from a plan kept on disk — so runs survive context compaction, /clear, crashes, and even handoffs between humans. 24 built-in studios cover software, marketing, security, compliance, incident response, data pipelines, and more. Each stage has configurable autonomy (auto-advance, human review, or external sign-off), parallel adversarial review agents, and deterministic quality gates. The agent stays simple; the orchestrator holds the structure."}]},"manifest":{"url":"https://raw.githubusercontent.com/gigsmart/haiku-method/42451f546de75e0c4f38d5d3bb0999e54661bf32/plugin/.claude-plugin/plugin.json","payload":{"name":"haiku","author":{"url":"https://gigsmart.com","name":"GigSmart"},"license":"Apache-2.0","version":"10.3.0","homepage":"https://haikumethod.ai","keywords":["haiku","haiku-method","lifecycle","orchestration","methodology","workflow","iteration","completion-criteria","hat-switching","context-preservation","human-ai-collaboration"],"repository":"https://github.com/gigsmart/haiku-method","description":"H·AI·K·U methodology — universal lifecycle orchestration with hat-based workflows, completion criteria, and automatic context preservation."},"observed_at":"2026-11-06T10:50:07Z"}}