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?
Language:
Total stars: 310
Stars trend:
16 Apr 2025
7am ▏ +1
8am ▎ +2
9am +0
10am ▏ +1
11am ▏ +1
12pm +0
1pm +0
2pm +0
3pm ▏ +1
4pm ▏ +1
5pm ████▌ +36
6pm █████▎ +42

#12factor, #12factoragents, #agents, #ai, #contextwindow, #framework, #llms, #memory, #orchestration, #promptengineering, #rag

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?
Language:TypeScript
Total stars: 5403
Stars trend:
4 Jul 2025
12am █▌ +12
1am █▍ +11
2am █▋ +13
3am █▍ +11
4am ██ +16
5am █▌ +12
6am ██ +16
7am ██▏ +17
8am █▊ +14
9am █▏ +9
10am ▉ +7
11am ▌ +4
#typescript
#12factor, #12factoragents, #agents, #ai, #contextwindow, #framework, #llms, #memory, #orchestration, #promptengineering, #rag

chopratejas/headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Language:Python
Total stars: 2907
Stars trend:
31 May 2026
12pm ▎ +2
1pm +0
2pm ▏ +1
3pm ▏ +1
4pm ▏ +1
5pm ▎ +2
6pm ▌ +4
7pm ▍ +3
8pm ▌ +4
9pm █ +8
#python
#agent, #ai, #anthropic, #claudecode, #compression, #contextengineering, #contextwindow, #cursor, #fastapi, #langchain, #llm, #mcp, #openai, #promptengineering, #proxy, #python, #rag, #tokenoptimization, #tokens, #typescript