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: fix Kompress-base HuggingFace link
chopratejase4f3cf77c5f2
diff --git a/README.md b/README.mdindex 243e5be68..9b41a5e9a 100644--- a/README.md+++ b/README.md@@ -7,7 +7,7 @@[](https://github.com/chopratejas/headroom/actions/workflows/ci.yml)[](https://pypi.org/project/headroom-ai/)[](https://www.npmjs.com/package/headroom-ai)-[](https://huggingface.co/headroom-ai/Kompress-base)+[](https://huggingface.co/chopratejas/kompress-base)[](https://headroomlabs.ai/dashboard)[](LICENSE)[](https://chopratejas.github.io/headroom/)@@ -71,7 +71,7 @@ OPENAI_BASE_URL=http://localhost:8787/v1 your-app- **Accuracy-preserving.** GSM8K **0.870 → 0.870** (±0.000). TruthfulQA **+0.030**. SQuAD v2 and BFCL both **97%** accuracy after compression. Validated on public OSS benchmarks you can rerun yourself.- **Runs on your machine.** No cloud API, no data egress. Compression latency is milliseconds — faster end-to-end for Sonnet / Opus / GPT-4 class models than a hosted service round-trip.-- **[Kompress-base](https://huggingface.co/headroom-ai/Kompress-base) on HuggingFace.** Our open-source text compressor, fine-tuned on real agentic traces — tool outputs, logs, RAG chunks, code. Install with `pip install "headroom-ai[ml]"`.+- **[Kompress-base](https://huggingface.co/chopratejas/kompress-base) on HuggingFace.** Our open-source text compressor, fine-tuned on real agentic traces — tool outputs, logs, RAG chunks, code. Install with `pip install "headroom-ai[ml]"`.- **Cross-agent memory and learning.** Claude Code saves a fact, Codex reads it back. `headroom learn` mines failed sessions and writes corrections straight to `CLAUDE.md` / `AGENTS.md` / `GEMINI.md` — reliability compounds over time.- **Reversible (CCR).** Compression is not deletion. The model can always call `headroom_retrieve` to pull the original bytes. Nothing is thrown away.@@ -101,7 +101,7 @@ Bundles the [RTK](https://github.com/rtk-ai/rtk) binary for shell-output rewritiLLM provider (Anthropic · OpenAI · Bedrock · …)```-→ [Architecture](https://chopratejas.github.io/headroom/docs/architecture) · [CCR reversible compression](https://chopratejas.github.io/headroom/docs/ccr) · [Kompress-base model card](https://huggingface.co/headroom-ai/Kompress-base)+→ [Architecture](https://chopratejas.github.io/headroom/docs/architecture) · [CCR reversible compression](https://chopratejas.github.io/headroom/docs/ccr) · [Kompress-base model card](https://huggingface.co/chopratejas/kompress-base)---@@ -259,7 +259,7 @@ Devcontainers in `.devcontainer/` (default + `memory-stack` with Qdrant & Neo4j)- **[Live leaderboard](https://headroomlabs.ai/dashboard)** — 60B+ tokens saved and counting.- **[Discord](https://discord.gg/yRmaUNpsPJ)** — questions, feedback, war stories.-- **[Kompress-base on HuggingFace](https://huggingface.co/headroom-ai/Kompress-base)** — the model behind our text compression.+- **[Kompress-base on HuggingFace](https://huggingface.co/chopratejas/kompress-base)** — the model behind our text compression.## License