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
Select Headroom context engine on install
JerrettDavis746a1737c1a9
diff --git a/plugins/openclaw/README.md b/plugins/openclaw/README.mdindex 032bceb9d..a0e1e369e 100644--- a/plugins/openclaw/README.md+++ b/plugins/openclaw/README.md@@ -45,6 +45,8 @@ Why this matters:## Configure+Install automatically selects the `contextEngine` slot for `headroom` on current OpenClaw releases. If you need to switch back manually, set `plugins.slots.contextEngine` to `"legacy"` or another engine id.+```json{"plugins": {diff --git a/plugins/openclaw/openclaw.plugin.json b/plugins/openclaw/openclaw.plugin.jsonindex 5c54599c7..e5b8bb865 100644--- a/plugins/openclaw/openclaw.plugin.json+++ b/plugins/openclaw/openclaw.plugin.json@@ -1,5 +1,6 @@{"id": "headroom",+ "kind": "context-engine","uiHints": {"proxyUrl": {"label": "Proxy URL",