Python · MIT
FuRongJun-1999/dsh-memory
白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。
★ 601
Stars
62 forks · 12 open issues
+9.6/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
42.7
Momentum / 100
see the breakdown below
2mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 19.6 | +9.6/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 8.1 | 601 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 42.7 | sum of the above |
Detail
| Topics | agent-safetyagentic-aiagiai-agent-frameworkdeepseekdsh-pluginexplainable-aiguardrailsknowledge-graphmcpmulti-agentpersistent-memoryragspatiotemporal-graph-neural-network |
| Matched on | RAG (rag) |
| Short window | +48 stars over 5 days = 9.6/day |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 7.25 stars/day over 83 days |
| First seen here | 2026-10-31 |
| Last read | 2d ago |