Hexum documentation
Last updated 29 August 2026
This overview is the activity of a Hexum session: what you put in the repo, what the agent calls, what comes back, what you review. It does not describe how Hexum compresses or checks internally.
Read in this order
- A session — billing, key, paste MCP, architecture file, turn loop.
- Connect — Bearer header, AUTH vs BILLING.
- architecture.hexum — layers and rules.
- Tools — five tools from tools/list.
| Tool | When |
|---|---|
hexum_skill | First Hexum use this session if SKILL.md is missing, or when intensity changes. |
hexum_shrink | Before reading a repo or a wide file set. |
hexum_expand | When one folded function, class, or method is the thing to patch. |
hexum_splice | When applying the patch. |
hexum_check | Before claiming the turn is done. |
What Hexum is not
- Not an IDE. Not a customer CLI. Not a model.
- Not a store of your repo. ZDR.
- Not a spend cap. Usage billing.
FAQ
What is Hexum?
Hexum is an MCP server for Cursor, Claude Code, and other coding agents. It sits between the agent and the model: hexum_shrink sends this turn instead of the repository, hexum_check fails the turn when architecture.hexum is broken, and you keep your editor. On MBPP, context dropped about 85% with the same tests passing.
Does Hexum replace Cursor or Claude Code?
No. Hexum is a hosted MCP server. You keep Cursor, Claude Code, Antigravity, Codex, or Grok. Hexum is not an IDE and not a model.
How does Hexum reduce tokens?
The agent calls hexum_shrink before it reads widely. The model is sent this turn, not the repository. On MBPP, measured context dropped about 85% with the same tests passing. Example turn: 18.2k → 3.1k tokens, 41 files → 6. See /benchmarks and /methodology.
Is hexum_check an LLM?
No. hexum_check is deterministic. It maps files to layers in architecture.hexum and reports forbidden imports. It does not call a model.
How is Hexum billed?
Hexum bills tokens saved: input minus what still goes to the model. Cache hits are free. No monthly cap. No seat tax. Usage early access from €0.30 per million. Teams from €0.35 per million. See /pricing.
What is tokens saved?
Tokens in minus tokens out, when that is positive. Stripe is billed on tokens saved. Calls that do not save tokens still increment calls and the in/out counters.
Does Hexum store my repo?
No. Zero Data Retention is on Usage and Teams. MCP payloads are not stored. Hexum does not train on your code. Policy: /zdr.
How do I add Hexum to Cursor?
Turn on usage billing at /app, mint a hexum_live_ key, paste the mcpServers JSON into Cursor Settings → MCP or ~/.cursor/mcp.json, then reload. Details: /cursor.