Headroom: vendor claims and pricing, captured before any test
Sources: GitHub repo description and README.md of github.com/headroomlabs-ai/headroom, fetched 2026-10-20 11:17 UTC+8 (76,311 stars then; repo created 2026-01-08 UTC+8). Version tested: headroom-ai 0.41.0 from PyPI (pip install 'headroom-ai[all]'), repo tag v0.41.0 commit 76133cf for the benchmark scripts.

--- Repo description (verbatim) ---
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.

--- README lines 36-39 (verbatim) ---
Headroom compresses everything your AI agent reads — tool outputs, logs, RAG
chunks, files, and conversation history — before it reaches the LLM. Same
answers, fraction of the tokens. Compression runs on your machine; no prompt or
file content is sent anywhere to be compressed.

--- README lines 146-161 (proof table, savings caveat, latency claim; verbatim) ---
```

| Scenario | Before | After | Saved |
|---|---:|---:|---:|
| Code search (100 results) | 17,199 | 13,597 | **21%** |
| SRE incident debugging | 55,957 | 24,340 | **57%** |
| Codebase exploration | 58,801 | 33,895 | **42%** |
| GitHub issue triage | 46,067 | 32,429 | **30%** |

Savings scale with how repetitive the payload is. Repeated JSON arrays and log
lines clear 90% in `benchmarks/bench_latency.py`; prose and already-dense output
compress very little. Run `headroom savings` against your own traffic for the
number that applies to you.

Compression costs **well under a millisecond** — 0.21 ms p50 on a 10K-token JSON
search result, 1.4 ms at 100K tokens — so it does not show up in agent latency.

--- README lines 619-628 (telemetry; verbatim) ---
## Telemetry

An anonymous beacon is **on by default**. It reports how compression behaved:
ratios, counters, provider and model IDs, OS and architecture. It never sends
prompts, completions, code or file paths. It exists so we can see when a release
regresses a compression ratio across real workloads rather than only our own test
corpus.

Turn it off with `HEADROOM_BEACON=off`, `HEADROOM_TELEMETRY=off`, the
`DO_NOT_TRACK=1` convention, or `HEADROOM_OFFLINE=1`. The full field list is in

--- Pricing ---
Open source, Apache-2.0, free (README line 701). 'Headroom Enterprise' for teams with no public price; README lines 644-646: 'Companies that sign a 12-month Enterprise plan get their first 3 months free.' No account or key is needed for the library.