Turn a live Claude Code session into a Telegram agent — one interactive session, no per-message SDK billing. Replaces the claude -p gateway pattern. Multichat, media, voice transcription, terminal mirror.
Trust metadata for AI agents — a stamp costs ~15 tokens, re-verifying costs 15,000. Agents stamp what they verify; the next agent runs 'akf check' and builds on it. pip install akf
Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus a fixture-based eval suite.
For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI coding agent: your intent goes in before it writes, and the result is verified against your spec after, so those three are earned, not assumed. First L4 implementation of the Ironclad standard.