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
FROM rust:1.96-slim AS build
WORKDIR /workspace
COPY . .
RUN cargo build --release -p headroom-simulators
FROM debian:bookworm-slim
RUN useradd --create-home --uid 10001 headroom
COPY --from=build /workspace/target/release/headroom-simulators /usr/local/bin/headroom-simulators
USER headroom
EXPOSE 8789
ENTRYPOINT ["headroom-simulators"]