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
docs: use headroom-ai package name in install commands (#1014) (#1257)
Parideboy8cc5354f510e
diff --git a/SECURITY.md b/SECURITY.mdindex c44a9237a..c308f5cf1 100644--- a/SECURITY.md+++ b/SECURITY.md@@ -44,7 +44,7 @@ When using Headroom:### ScopeThe following are in scope for security reports:-- Headroom Python package (`pip install headroom`)+- Headroom Python package (`pip install headroom-ai`)- Headroom proxy server- Official integrations (LangChain, MCP)diff --git a/docs/content/docs/claude-code-vertex.mdx b/docs/content/docs/claude-code-vertex.mdxindex 779721efd..b41773a9f 100644--- a/docs/content/docs/claude-code-vertex.mdx+++ b/docs/content/docs/claude-code-vertex.mdx@@ -34,7 +34,7 @@ No `ANTHROPIC_API_KEY` is needed — Vertex mode uses your Google login.## Run it (one command)```bash-pip install headroom+pip install headroom-aiheadroom wrap claude```diff --git a/wiki/getting-started.md b/wiki/getting-started.mdindex 7fc9f9e3a..098a83ffe 100644--- a/wiki/getting-started.md+++ b/wiki/getting-started.md@@ -8,16 +8,16 @@ This guide will help you get up and running with Headroom in under 5 minutes.```bash# Core package (minimal dependencies)-pip install headroom+pip install headroom-ai# With proxy server-pip install headroom[proxy]+pip install headroom-ai[proxy]# With semantic relevance (for smarter compression)-pip install headroom[relevance]+pip install headroom-ai[relevance]# Everything-pip install headroom[all]+pip install headroom-ai[all]```**TypeScript / Node.js:**