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
# Example local act configuration.
# Copy this file to .actrc.local and edit for your local environment.
#
# cp .actrc.local.example .actrc.local
#
# .actrc.local is NOT committed — it overrides .actrc for your machine only.
# Use a specific runner image (uncomment if you have issues with the default)
# --platform=ubuntu-latest=ghcr.io/catthehacker/ubuntu:runner-latest
# Or use act with a specific container runtime
# --container-args="--runtime=runc"
# Extra verbose output for debugging (uncomment to see all steps)
# --verbose