26 lines
585 B
Markdown
26 lines
585 B
Markdown
|
# 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
|