TypeScript
1173591564/memory-manage
LLM agent 的有界自纠错长期记忆层：把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamics + tension adjudication + causal-replay evals.
★ 182
Stars
1 forks · 12 open issues
−2.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
19.7
Momentum / 100
see the breakdown below
53d ago
Created
last push 24d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | −2.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran -0.41× the monthly pace |
| Freshness | 15 | 13.2 | last push 24d ago; decays to zero at 180 days |
| Scale | 15 | 6.6 | 182 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 19.7 | sum of the above |
Detail
| Topics | agent-memoryagentsllmllm-agentslong-term-memorymemorymemory-managementpythonragretrieval-augmented-generation |
| Matched on | RAG (rag, retrieval-augmented-generation) LLM & Inference (llm) |
| Short window | +-2 stars over 7 days = -0.3/day |
| Long window | +18 stars over 26 days = 0.7/day |
| Lifetime average | 3.57 stars/day over 51 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |