# 
hyperhive
> a swarm of coding agents spread across NixOS hosts โ every agent in its
> own nspawn cage, every host a hive, one control plane over all of them.
> config changes flow as git commits, the operator approves them in a
> browser, every deploy is a tag. cyberpunk dashboard included. ๐โก
**[โ website](https://hyperhive.darkest.space)** ยท
**[โ docs](https://hyperhive.darkest.space/docs/)** ยท
**[โ options reference](https://hyperhive.darkest.space/options/)**
A coding agent is great in one window, _exponentielle_ across many โ as
long as the agents stay off each other's toes, keep a durable identity,
and leave production alone. hyperhive is the substrate for that, as a set
of NixOS modules:
- a **hive** is one host running `hive-c0re` and the agent containers it
owns;
- a **swarm** is any number of hives sharing one identity plane โ SSO,
forge, matrix, secret store, telemetry โ with a controller that places
agents on hives and tracks them across all of them.
Start with everything on one box; move services and add hives as the
swarm grows. Which host runs what is a per-host `deploy.*` toggle,
not an architecture change.
| concern | how hyperhive answers it |
| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **scale-out** | hives share one directory (`swarm.hives`, identical on every host); `swarmctl agent create --hive ` places an agent and the controller keeps the roster |
| **identity** | every agent gets swarm-wide accounts โ SSO subject, forge user, matrix account, secret-store cert identity โ and is addressable as `name@hive.domain` |
| **shared plane** | one forge, homeserver, secret store, SSO, queue and metrics/logs stack per swarm, each on whichever host you put it |
| **blast radius** | one `nixos-container` per agent; the host daemon runs unprivileged, and a tiny socket-activated helper does the few root ops |
| **config** | git: an agent proposes, the operator approves, the deploy lands as a `deployed/` tag |
| **runtime** | `claude --print` by default; any [ACP](https://agentclientprotocol.com) agent (e.g. opencode) per agent with `services.hyperhive.agent.runtime = "acp"` |
| **watching** | per-agent web UI with a live terminal, a per-hive dashboard, the swarm UI, Grafana over OTEL |
## Shape
```
every hive (NixOS host, deploy.hive-controller.enable)
โ
โโโ operator
โ โโโ browser โ :80/:443 (hive-gateway) dashboard + /agent// UIs
โ โโโ hivectl โ /run/hyperhive/host.sock admin protocol
โ
โโโ hive-c0re Rust daemon: lifecycle, broker, approvals, job queue,
โ auto-rebuild, dashboard โ runs as the unprivileged hive-core user
โโโ hive-priv root helper, socket-activated, does bind-mounts + nsenter
โโโ hive-gateway nginx + dnsmasq in front of c0re and every agent socket
โ
โโโ agent containers
โโโ h-ruth manager โ privileged MCP surface, spawns + configures agents
โโโ h- agent โ claude / ACP runtime, MCP tools, web UI, own socket
the swarm's shared services (one host each โ any hive, or a dedicated box)
โ
โโโ hive-forge Forgejo โ per-agent accounts, config mirror
โโโ hive-matrix tuwunel โ matrix homeserver, per-agent accounts
โโโ swarm-bao OpenBao โ the swarm's secret store, cert auth per agent
โโโ swarm-controller cross-hive state: hive directory, agent roster, jobs
โ (+ swarmctl, + swarm-ui served off the gateway)
โโโ swarm-authelia SSO in front of swarm-ui, forge, grafana, โฆ
โโโ swarm-nats message queue (JetStream KV: hive status, โฆ)
โโโ swarm-otel telemetry collector, sole holder of upstream creds
โโโ swarm-victoriametrics metrics store
โโโ swarm-victorialogs log store
โโโ swarm-grafana dashboards over both stores
โ
โโโ opt-in, not part of singleHostSwarm
โโโ hive-ci Forgejo Actions runner (deploy.forgejo.ci)
โโโ swarm-snapshot-store btrfs-receive endpoint for agent snapshots
โโโ wg-hive WireGuard mesh between hives (deploy.wireguard)
```
## Inside an agent
Every agent is a full NixOS container with its own unix user (passwordless
sudo inside the cage) and a durable, self-compacting session. Out of the
box it gets:
- **messaging** โ `send` / `recv` to other agents and the operator,
`remind` and recurring schedules to wake itself, and a todo list that
forge notifications and other producers feed. โ
[scheduling](docs/tools/scheduling.md)
- **background bash** โ long-running commands as tracked tasks
(`run` / `status` / `kill`), so a build doesn't block the turn. โ
[bash](docs/tools/bash.md)
- **subagents** โ nested sessions on the agent's own runtime, optionally
re-prompted toward a goal over several turns. โ
[subagent](docs/tools/subagent.md)
- **forge** โ its own Forgejo account, the `hive-forge` CLI, git
credentials, and notifications turned into todos. Optional linked
accounts on other forges, and GitHub (`gh` + push) via
`services.hyperhive.agent.github.enable`. โ
[forge](docs/integrations/forge.md) ยท [github](docs/integrations/github.md)
- **matrix** โ its own account(s) on the swarm homeserver, as MCP tools. โ
[matrix](docs/tools/matrix.md)
- **knowledge** โ the swarm's shared `internal/knowledge` repo, read-only
at `/knowledge`, plus hyperhive's own docs in the container. โ
[knowledge](docs/integrations/knowledge.md)
- **web UI** โ a per-agent page behind the gateway: live terminal of the
turn stream, model / effort switching, cancel, `/compact`.
- **GUI** (opt-in, `services.hyperhive.agent.gui.enable`) โ a Wayland
desktop with screenshot / keyboard / mouse tools, viewable over VNC in
the web UI.
- **your own tools** โ any extra MCP server (stdio or http) via
`services.hyperhive.agent.extraMcpServers`, and any NixOS config you'd
put on a machine.
## Quick start: an all-local swarm
The whole swarm on one box โ a hive plus every shared service. Good for a
dev box or a single-host deployment; [`docs/swarm/`](docs/swarm/README.md)
covers spreading a swarm across hosts.
```nix
{
inputs = {
nixpkgs.url = "github:NixOS/nixpkgs/nixos-26.05";
hyperhive.url = "git+https://forge.darkest.space/hyperhive/hyperhive";
hyperhive.inputs.nixpkgs.follows = "nixpkgs"; # see "Overriding nixpkgs"
};
outputs = { nixpkgs, hyperhive, ... }: {
nixosConfigurations.my-host = nixpkgs.lib.nixosSystem {
system = "x86_64-linux";
modules = [
hyperhive.nixosModules.default # the whole host stack, one import
{
services.hyperhive = {
deploy.singleHostSwarm = true; # run everything on one machine
swarm.domain = "hive.example"; # the swarm's DNS domain
hiveName = "pr1ma"; # this hive's label in it
swarm.hives.pr1ma = { }; # the directory: just us
# c0re.operatorPronouns = "they/them"; # default "she/her"
};
# ... the rest of your host config
system.stateVersion = "25.11";
}
];
};
};
}
```
`singleHostSwarm` turns on everything an all-on-one-box swarm implies:
the shared services above, the swarm CA, the swarm controller, and
`/etc/hosts` entries so the hive's names resolve on the box itself.
`claude-code` is unfree โ hyperhive scopes the allowance to itself, so
there's nothing to set.
After `nixos-rebuild switch`, hive-c0re creates the manager (`ruth`) and
keeps every container rebuilt whenever its hyperhive rev goes stale. A few
steps stay deliberately human โ initialising the secret store, giving ruth
her store identity, adding a gateway login, SSO. Walk through
**[`docs/getting-started/setup.md`](docs/getting-started/setup.md)**
once, top to bottom.
### Overriding nixpkgs
hyperhive pins its own `nixpkgs` so it builds standalone in CI. The
`follows` line above builds it against your host's `nixpkgs` instead: one
evaluation, no version drift. It works as long as your channel is close to
the `nixos-26.05` hyperhive develops against โ drop it if a much older or
newer channel breaks in ways hyperhive's CI doesn't catch.
## Operating it
- **`hivectl`** โ the hive's operator CLI, on every hive host: agents,
approvals, gateway logins, container shells. Talks to hive-c0re over
`/run/hyperhive/host.sock`. โ [guide](docs/tools/hivectl.md) ยท
[full reference](docs/tools/hivectl-cli.md)
- **`swarmctl`** โ the swarm's operator CLI, on the swarm-controller host:
creating agents with their identities, SSO users, forge admins.
โ [reference](docs/tools/swarmctl-cli.md)
- **Dashboard** โ approvals, agent state, the job graph, per-agent
terminals. โ [`docs/web-ui/`](docs/web-ui/README.md)
Human accounts come from SSO: a first login through authelia creates your
forge and matrix accounts; `swarmctl forge make-admin ` promotes the
forge one.
## Where to read next
[`docs/README.md`](docs/README.md) is the index, grouped by question โ
pick the page for your task rather than reading front to back. Some
common entry points:
- how config changes flow โ [`agent-lifecycle/approvals.md`](docs/agent-lifecycle/approvals.md)
- trust boundary + threat model โ [`trust-boundary/`](docs/trust-boundary/boundary.md)
- what an agent's turn looks like โ [`turn-loop/`](docs/turn-loop/README.md)
- connecting hives into a swarm โ [`swarm/`](docs/swarm/README.md)
- every `services.hyperhive.*` option โ [options reference](https://hyperhive.darkest.space/options/)
## Hacking on it
```sh
nix develop -c cargo check
nix flake check # rust + nix + toml fmt, clippy, module-eval tests
# in your host flake:
nix flake update hyperhive
sudo nixos-rebuild switch --flake .#
```
Conventions (commit style, no `#[allow(clippy::โฆ)]`, the pre-push hook)
live in [`docs/process/conventions.md`](docs/process/conventions.md).
Issues + backlog are on the
[forge](https://forge.darkest.space/hyperhive/hyperhive/issues).