Python · MIT
vectorize-io/hindsight
Hindsight: Agent Memory That Learns
★ 59k
Stars
7.3k forks · 208 open issues
+441/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
80.3
Momentum / 100
see the breakdown below
12mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 50.6 | +441/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.9 | last week ran 1.06× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 13.8 | 59k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 80.3 | sum of the above |
Detail
| Topics | agentic-aiagentsai-memorymemory |
| Matched on | AI Agents (agentic-ai) |
| Short window | +3.1k stars over 7 days = 441.4/day |
| Long window | +10.8k stars over 26 days = 416.3/day |
| Lifetime average | 158.96 stars/day over 371 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |