Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
ci: run relevance tests offline so fastembed doesn't 429 on cache HEAD
Tejas Chopra2ea548a86dc2
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.ymlindex 1cde45243..a2767c556 100644--- a/.github/workflows/ci.yml+++ b/.github/workflows/ci.yml@@ -233,6 +233,11 @@ jobs:doneecho "::error::could not fetch fastembed model from HuggingFace"; exit 1- name: Run relevance tests+ # Offline so fastembed reads the cache the prefetch step just warmed,+ # without an unauthenticated cache-validation HEAD that could 429.+ env:+ HF_HUB_OFFLINE: "1"+ TRANSFORMERS_OFFLINE: "1"run: pytest tests/test_relevance.py -vtest-agno: