llm-agents 3

Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — FOUR agent presets in one install: vibe-math-v2 (probability-driven, classic: qs.json + Propos knowledge base + explorer→solver→review/debate verdict), vibe-math-v3

Cairn — long-term memory for the DeepSeek Harness: persistent cross-session memory (store, tools, auto-extraction, context injection) as one installable profile bundle

Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.