Skip to content
@headroomlabs-ai

Headroom Labs

Make every token count

Popular repositories Loading

  1. headroom headroom Public

    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 72k 5.5k

  2. tokview tokview Public

    See where your LLM tokens actually go — down to the individual tool call. A small, local, zero-config proxy + dashboard for token/cost tracking across Claude, OpenAI, Gemini.

    Python 76 13

  3. strands-headroom strands-headroom Public

    Headroom context compression for AWS Strands Agents

    Python 1

  4. headroom-switchyard headroom-switchyard Public

    Forked from NVIDIA-NeMo/Switchyard

    Rust

Repositories

Showing 4 of 4 repositories
  • headroom Public

    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.

    headroomlabs-ai/headroom's past year of commit activity
    Python 71,954 Apache-2.0 5,512 313 322 Updated Sep 13, 2026
  • headroom-switchyard Public Forked from NVIDIA-NeMo/Switchyard
    headroomlabs-ai/headroom-switchyard's past year of commit activity
    Rust 0 Apache-2.0 273 0 0 Updated Aug 13, 2026
  • strands-headroom Public

    Headroom context compression for AWS Strands Agents

    headroomlabs-ai/strands-headroom's past year of commit activity
    Python 1 Apache-2.0 0 0 0 Updated Aug 2, 2026
  • tokview Public

    See where your LLM tokens actually go — down to the individual tool call. A small, local, zero-config proxy + dashboard for token/cost tracking across Claude, OpenAI, Gemini.

    headroomlabs-ai/tokview's past year of commit activity
    Python 76 MIT 13 0 0 Updated Jul 9, 2026

Top languages

Python Rust

Most used topics

Loading…