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
fix(cli): default wrap openclaw spec to headroom-ai/openclaw
JerrettDavis61dacc94a139
diff --git a/headroom/cli/wrap.py b/headroom/cli/wrap.pyindex 1cd115349..adf1f4351 100644--- a/headroom/cli/wrap.py+++ b/headroom/cli/wrap.py@@ -829,7 +829,7 @@ def cursor(port: int, no_rtk: bool, no_proxy: bool, learn: bool, verbose: bool))@click.option("--plugin-spec",- default="headroom-openclaw",+ default="headroom-ai/openclaw",show_default=True,help="NPM plugin spec for OpenClaw install (used when --plugin-path is omitted)",)diff --git a/tests/test_cli/test_wrap_openclaw.py b/tests/test_cli/test_wrap_openclaw.pyindex f8947bd06..fc6c6a5b5 100644--- a/tests/test_cli/test_wrap_openclaw.py+++ b/tests/test_cli/test_wrap_openclaw.py@@ -57,7 +57,7 @@ def test_wrap_openclaw_default_installs_from_npm_and_restarts(runner: CliRunner)"plugins","install","--dangerously-force-unsafe-install",- "headroom-openclaw",+ "headroom-ai/openclaw",] in cmdsassert ["openclaw", "config", "validate"] in cmdsassert ["openclaw", "gateway", "restart"] in cmds