MunHQ

Infrastructure, AI and tech solutions.

We focus on solving problems and delivering finished products.

The products.

  1. 01
    chat-recall

    One searchable history for every AI coding tool on the machine.

    • Temporal knowledge graph
    • MCP server
    • Secret alerts
    chatrecall.dev
  2. 02
    gpuscale

    Buys the cheapest spot GPU it can find, then gives it back.

    • Seven providers
    • Scales to zero
    • vLLM
    gpuscale.cc
  3. 03
    axon

    One gateway for every LLM call, with the real cost attached to each one.

    • Routes by cost and request type
    • Response cache
    • Per-tenant budgets
    • Spend alerts
    • Cost dashboards
    Ask us
  4. 04
    codeindex

    An agent calls a tool instead of reading the whole file.

    • 40+ languages
    • Dependency graph
    • MCP server
    github.com/munhq/codeindex
  5. 05
    cloud-tools

    Reads your cloud bill and says where the money goes.

    • Four clouds
    • Read-only access
    • MCP + HTTP
    github.com/munhq/cloud-tools
  6. 06
    distil

    Measures what compressing a session actually costs.

    • Benchmark harness
    • Prompt-cache accounting
    • MCP server
    github.com/munhq/distil
  7. 07
    CoolCode

    Runs coding agents as a team, with work that outlives a session.

    • Desktop app
    • Role-pinned models
    • Every change snapshotted
    coolcode.hotmun.com
  8. 08
    munbot

    A team of agents that runs a business, one isolated pod each.

    • One pod per tenant
    • Per-tenant spend ceilings
    • Scheduled agent turns
    Ask us
  9. 09
    agentfetch

    Gets clean markdown out of pages that resist it.

    • Three-layer escalation
    • Markdown output
    Ask us

Write to us.

General
hello@munhq.com

Send this and we may email you back at the address above. Nothing else.