hyperhive/docs/tools
Repository files (latest commit first)
Filename Latest commit message Latest commit date
2026-08-18 13:53:27 +02:00
..
bash.md feat(#2659): serve hive-bash-mcp over persistent streamable-http, drop stdio bridge 2026-07-23 18:01:20 +02:00
forge.md docs: cover the reaction verb and comments --show-reactions 2026-08-18 13:53:27 +02:00
hivectl-cli.md hive-c0re/hivectl/hive-agent: pause as a job-queue DAG node (closes #3056) 2026-08-11 23:47:09 +02:00
hivectl.md fix(3179): the gateway's config files get their own state dir 2026-08-12 10:29:27 +02:00
lifecycle.md refactor(#2416): remove the non-pr config-change flow (request_apply_commit / applycommit) 2026-07-15 21:03:52 +02:00
matrix.md docs(matrix): fix invite-wake mechanism and todo message format 2026-08-15 12:45:22 +02:00
README.md swarmctl: add CLI reference docs, same pattern as hivectl 2026-08-11 21:55:56 +02:00
scheduling.md feat(3088): move the gateway's nginx + dnsmasq onto the host 2026-08-11 18:01:03 +02:00
swarmctl-cli.md docs(#3422): the user store is one file, not two 2026-08-18 10:34:00 +02:00

Tools

hivectl is your tool — the operator's own host CLI. Everything else here documents the tool surface your agents get inside their containers (the MCP tools an agent's own claude session can call). You never call these directly, but they're the reference for what an agent can actually do — useful when you're trying to understand or debug agent behavior.

For the operator

  • hivectl — the curated guide: provisioning forge and matrix accounts, gateway htpasswd management, container lifecycle shortcuts, interactive agent shell access.
  • hivectl-cli — the exhaustive, auto-generated flag-by-flag reference, kept in lockstep with the binary by CI.

For the swarm operator

  • swarmctl-cli — the exhaustive, auto-generated flag-by-flag reference for swarmctl, kept in lockstep with the binary by CI the same way hivectl-cli.md is. swarmctl itself runs as root on the swarm-controller host, not through hivectl — see swarmctl/README.md for why. No curated guide yet (one verb, user add, doesn't need one); add one here if/when that grows.

What your agents can do

  • bash — background shell execution (mcp__bash__*), available on every agent unconditionally.
  • forge — the hive-forge Forgejo CLI every agent has for issues, PRs, and comments. Not an MCP tool — a binary agents shell out to instead of ad-hoc curl.
  • lifecycle — kill/start/restart/update for an agent's own direct children, plus the approval-gated config-change tools.
  • matrix — the matrix MCP tool surface (mcp__matrix__*) for agents with a matrix account, multiple accounts per agent, and declaring extra MCP servers generally.
  • scheduling — scheduled prompts (operator approval required) and the diagnostics tools (get_logs, get_host_journal).