min-min

Auto-generated from project docs

North Star

Booklet Status

BookletStatusBranchAppetiteDeadlineNotes
B0-B7.1COMPLETEN/AOpenClaw era. Telegram, Discord, skills, autonomy, chat redesign
B8BLOCKEDbooklet/min-min-b82 weeks2026-04-26Runtime migration: ZeroClaw live but webhook doesn't pass tools (INCIDENT-052). Decision needed: expand proxy / adopt nanobot / fork ZeroClaw
B9DONE1 week2026-04-21RESCOPED + COMPLETE Memory architecture (L0+L1+L2 injection + tool exec proxy). RESEARCH-250.
B9.5QUEUED3 daysFix remaining broken capabilities (deferred from B9)
B9.6DECISION DONE, EXEC PENDING8 hrs exec2026-04-21RESEARCH-273 (2026-04-18): Expand minmin-proxy into full runtime (Option A). 11 deliverables A1-A11. Awaiting Mister go-ahead to execute.
B10QUEUED2 weeks2026-05-17Life Intelligence (morning briefing)
B11QUEUED2 weeks2026-05-31Client delivery automation

Recent Decisions

DateDecisionRationale
---------------------------
2026-04-12Project kickstarted (rescope from OpenClaw workspace)Never had proper project structure despite being core product
2026-04-12Migrate OpenClaw → ZeroClawRESEARCH-226: 99% less RAM, 0 CVEs, native LiteLLM/Discord, migration tool exists
2026-04-12Discord as primary channel (not Telegram)Mister preference. Own full stack long-term (Chatii)
2026-04-12OpenRouter as primary model (not Gemini)Gemini too unreliable for agent tool calling. OpenRouter auto-top-up
2026-04-12Monthly landscape review (QUICKREF-003)AI agent space moving too fast to review annually
2026-04-14Rescope B9: memory architecture replaces "fix broken things"INCIDENT-052: tool-based memory fails with non-Claude models. RESEARCH-250: industry consensus is hybrid injection. Old B9 deliverables moved to B9.5
2026-04-14Switch default model: openrouter-auto → gemini-2.5-proOpenRouter auto-routing picked models bad at tool calling. Gemini Pro better but still doesn't call tools — confirms need for injection pattern
2026-04-14Hybrid memory injection (L0+L1+L2) over tool-based memoryRESEARCH-250: every production agent system (MemPalace, Letta, Zep, GBrain) converged on this. Model-agnostic, 8 cents/day overhead
2026-04-14Switch model: gemini-2.5-pro → gpt-4.1-miniGemini tool calling unreliable (documented Google forum issues, 5 LiteLLM bugs). GPT-4.1-mini: $0.40/1M input, 97-99% tool accuracy

Source: /root/projects/min-min/