Initial Phase A intelligence core

2026-03-21 07:34:09 +00:00 · 2026-03-21 07:34:09 +00:00 · 94eae8ceba
commit 94eae8ceba
11 changed files with 4261 additions and 0 deletions
--- a/docs/ARCHITECTURE_BOARD.md
+++ b/docs/ARCHITECTURE_BOARD.md
@ -0,0 +1,25 @@
+# Architecture Board
+
+## Goal
+Build a local-first Openclaw agent that becomes more intelligent over time through:
+- typed memory
+- typed tool graph
+- trajectory logging
+- reward signals
+- shadow meta-controller
+- offline policy learning
+- sacred eval gates
+
+## Hosts
+- Mac Studio: hot-path inference
+- openclaw: orchestration and live logging
+- Unraid: offline learning, retrieval, replay, eval batch jobs
+- Kimi: offline teacher only
+
+## Phase A
+1. Typed trajectory schema
+2. Reward signals
+3. Replay buffer + policy stats
+4. Tool graph
+5. Uncertainty model
+6. Shadow meta-controller