TypeScript
humanlayer/12-factor-agents
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
★ 27k
Stars
2k forks · 28 open issues
+10/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
33.1
Momentum / 100
see the breakdown below
19mo ago
Created
last push 13mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 20.2 | +10/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.79× the monthly pace |
| Freshness | 15 | 0.0 | last push 13mo ago; decays to zero at 180 days |
| Scale | 15 | 12.8 | 27k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 33.1 | sum of the above |
Detail
| Topics | 12-factor12-factor-agentsagentsaicontext-windowframeworkllmsmemoryorchestrationprompt-engineeringrag |
| Matched on | RAG (rag) |
| Short window | +73 stars over 7 days = 10.4/day |
| Long window | +343 stars over 26 days = 13.2/day |
| Lifetime average | 46.16 stars/day over 585 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |