Jun 3, 2026 · Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. - 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. - Pull requests · 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. - chopratejas/headroom

Jan 7, 2026 · Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. - chopratejas/headroom

May 30, 2026 · Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. - Pulse · chopratejas/headroom

6 days ago · Summary This PR improves CodeAwareCompressor's function-body compression by replacing simple prefix truncation with a lightweight statement-level selection strategy. Previously, …

Very cool project! I lean on Claude Code pretty hard for real coding work — not chat, actual edits. Exact diffs, line numbers, file paths, even line-ending normalization that breaks if a single cha...

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. - Watchers · chopratejas/headroom

Jan 14, 2026 · Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. - Workflow runs · chopratejas/headroom

Explore the GitHub Discussions forum for chopratejas headroom. Discuss code, ask questions & collaborate with the developer community.