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
Merge branch 'main' into feat/persist-savings-history
gglucass165d3ca72654
diff --cc CHANGELOG.mdindex 66285057f,224de9dba..8888f706d--- a/CHANGELOG.md+++ b/CHANGELOG.md@@@ -8,12 -8,9 +8,15 @@@ and this project adheres to [Semantic V## [Unreleased]### Added+- **Durable proxy savings history**+ - Persists proxy compression savings history locally at `~/.headroom/proxy_savings.json`+ - Supports `HEADROOM_SAVINGS_PATH` to override the storage location+ - Adds `/stats-history` with lifetime totals plus hourly/daily rollups for frontends+ - Extends `/stats` with a `persistent_savings` block while keeping `savings_history` backward compatible+ - Adds a historical mode to `/dashboard` backed by `/stats-history`+ - **Proxy telemetry SDK override** via `HEADROOM_SDK`+ - Downstream apps can override the anonymous telemetry `sdk` field without patching installed files+ - Blank values fall back to the default `proxy` label- **`headroom learn`** — Offline failure learning for coding agents- Analyzes past conversation history (Claude Code, extensible to Cursor/Codex)- **Success correlation**: for each failure, finds what succeeded after and extracts the specific correction