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
chore: add .git-blame-ignore-revs
Garm570a365dc491
diff --git a/.git-blame-ignore-revs b/.git-blame-ignore-revsnew file mode 100644index 000000000..b9450e26a--- /dev/null+++ b/.git-blame-ignore-revs@@ -0,0 +1,10 @@+# Revisions listed here are skipped by `git blame --ignore-revs-file`+# and by GitHub's blame UI. Use for mechanical, repo-wide changes that+# touch every line of a file but don't change semantics (formatter runs,+# line-ending normalization, bulk renames applied by codemod, etc.).+#+# Configure your local git to auto-pick this up:+# git config blame.ignoreRevsFile .git-blame-ignore-revs++# chore: renormalize line endings to LF+efd2ac1ca4d88d8f5990259c98b673c603902896