a swarm o agents, each in its own nspawn cage, gossiping over unix sockets. config changes flow as git commits, the operator approves them in a browser, every deploy is a tag. cyberpunk-themed dashboard included. 💜
  • Rust 68.8%
  • Nix 15.7%
  • JavaScript 8.4%
  • CSS 3.6%
  • TypeScript 1.9%
  • Other 1.6%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
iris cce85a6c1b fix(#540): use systemd.globalEnvironment instead of environment.variables
environment.variables writes to /etc/environment (PAM sessions only)
and is not visible to systemd service units. The correct path for
env vars that need to reach all systemd services is
systemd.globalEnvironment (sets DefaultEnvironment in systemd.conf),
which is the pattern established by #608 for HYPERHIVE_STATE_DIR.

Also update the inline comment reference from environment.variables
to systemd.globalEnvironment.
2026-05-31 22:59:46 +02:00
branding forge: auto-set agent-configs org avatar on core start (#424) 2026-05-26 00:10:52 +02:00
docs fix(#540): pin weston socket + inject WAYLAND_DISPLAY globally 2026-05-31 22:59:46 +02:00
frontend fix(#888): use gateway forge URL in dashboard links 2026-05-31 22:04:52 +02:00
hive-ag3nt fix(#888): use gateway forge URL in dashboard links 2026-05-31 22:04:52 +02:00
hive-c0re gateway_nginx: fix stale module doc + clarify reload log (argus nits) 2026-05-31 22:42:52 +02:00
hive-forge hive-forge: drop boilerplate # Errors from pure-GET verbs (mara on #827, option A) 2026-05-31 16:22:05 +02:00
hive-matrix-mcp docs: catch up post-#658/#604/#660 + add operator hivectl section (#124) 2026-05-31 10:13:33 +02:00
hive-sh4re feat(#704): add <children> recipient sentinel — fan-out to direct descendants 2026-05-31 20:59:20 +02:00
nix fix(#540): use systemd.globalEnvironment instead of environment.variables 2026-05-31 22:59:46 +02:00
scripts forge-login: don't die on RO ~/.config/git/config 2026-05-17 01:22:31 +02:00
.gitignore gitignore .claude/settings.local.json 2026-05-15 14:44:58 +02:00
Cargo.lock Cargo.lock: bump 24 patch-level deps (#680) 2026-05-31 02:44:22 +02:00
Cargo.toml matrix: hive-matrix-mcp crate (daemon+stdio bridge) + harness wiring (#548 phase 3) 2026-05-29 20:51:01 +02:00
CLAUDE.md docs(#727): split docs/web-ui.md into shape / dashboard / agent 2026-05-31 21:37:04 +02:00
flake.lock nix: hyperhive owns nixpkgs pin via follows; bump to nixos-26.05 (#526) 2026-05-30 12:02:48 +02:00
flake.nix nix/docs: extract CSS into sibling file (#625) 2026-05-30 12:51:44 +02:00
README.md docs(#727): split docs/web-ui.md into shape / dashboard / agent 2026-05-31 21:37:04 +02:00
TODO.md docs: move backlog to forge issue tracker, extract boundary doc 2026-05-20 12:19:16 +02:00

hyperhive

a swarm of claude-code agents, each in its own nspawn cage, gossiping over unix sockets. config changes flow as git commits, the operator approves them in a browser, every deploy is a tag. cyberpunk-themed dashboard included. 💜

Claude code is great in one window, exponentielle across many — but only if you can keep the agents from stepping on each other, give them durable identity, and stop them from eating production. hyperhive is the substrate.

  • identity = unix socket
  • communication = sqlite-backed broker (send / recv / ask / answer / remind)
  • config = git (manager proposes, operator approves, deploys land as tagged commits)
  • blast radius = container
host (NixOS, runs hive-c0re.service)
│
├── operator
│   ├── browser → :7000          hive-c0re dashboard
│   ├── browser → :8100-8999     per-agent web UIs (all agents, FNV-1a hash)
│   └── CLI     → /run/hyperhive/host.sock   admin protocol
│
├── hive-c0re  (Rust daemon: lifecycle / broker / approvals /
│               auto-update / dashboard / sockets)
│
└── nixos-containers
    ├── hm1nd      manager agent (privileged MCP surface)
    └── h-<name>   sub-agent (vanilla MCP surface + per-agent extras)

Depth lives in docs/ — pick the one matching your task:

reading path doc
dashboard layout + endpoints docs/web-ui.md (shape · dashboard · agent)
claude turn loop + MCP tools docs/turn-loop.md
config-edit + approval state machine docs/approvals.md
what survives destroy / purge / restart docs/persistence.md
naming, wire protocol, commit style docs/conventions.md
nginx vhost map + sub-domain routing docs/gateway.md
NixOS / nspawn gotchas docs/gotchas.md

Host config

Minimal flake.nix for a host that runs hive-c0re:

{
  inputs = {
    nixpkgs.url = "github:NixOS/nixpkgs/nixos-26.05";
    hyperhive.url = "git+https://forge.darkest.space/hyperhive/hyperhive";
  };

  outputs = { nixpkgs, hyperhive, ... }: {
    nixosConfigurations.my-host = nixpkgs.lib.nixosSystem {
      system = "x86_64-linux";
      modules = [
        hyperhive.nixosModules.default  # hive-c0re + hive-forge + hive-gateway in one import
        ({ ... }: {
          services.hyperhive.enable = true;
          # services.hyperhive.c0re.operatorPronouns = "they/them";  # default: "she/her"

          # ... rest of your host config
          system.stateVersion = "25.11";
        })
      ];
    };
  };
}

hive-c0re opens its admin socket + dashboard, auto-creates the manager container, and auto-rebuilds any container whose hyperhive rev goes stale. claude-code is unfree — hyperhive scopes the whitelist to itself, nothing for the operator to set.

Optional: set services.hyperhive.gateway.enable = false; to bypass the default nginx in front. By default (gateway.enable = true) every request hits a small nginx in its own nixos-container that proxies to hive-c0re's dashboard on the upstream port; /matrix/ is served directly from services.hyperhive.matrix.gui.package when the matrix GUI is on. v0 is HTTP-only (TLS lives in a follow-up); pair with services.hyperhive.gateway.localHostsEntry = true; for local dev so http://<services.hyperhive.domain> resolves to the host without setting up real DNS.

Optional: set services.hyperhive.c0re.preBuildAgentTemplates = true; to pre-fetch the per-container system closures into your host's /nix/store as part of nixos-rebuild. First-agent-spawn then completes in seconds instead of minutes (no nixpkgs/claude-code fetch on the critical path), at the cost of a few GB extra in your system closure. Off by default (the toplevels are pinned to x86_64-linux, so non-x86 hosts would otherwise force a cross-build). Alternatively warm the store manually: nix build git+https://forge.darkest.space/hyperhive/hyperhive#agent-base-toplevel.

Optional: set services.hyperhive.domain = "example.com"; to define the canonical hostname for hyperhive subsystems that need a stable public name. No default — subsystems that require it (currently: services.hyperhive.matrix) assert non-null at eval time with a clear error message if it is missing.

Optional: set services.hyperhive.hiveName = "pr1ma"; and / or services.hyperhive.swarmName = "constellat1on"; to give the hive and the wider swarm human-readable display labels. Distinct from services.hyperhive.domain (the DNS address): the names surface in the dashboard chrome and the per-agent system prompt; the domain is how things are addressed on the wire. Federated hives at different domains can share a swarm name. Both default to null — chrome falls back to the domain, the prompt simply doesn't mention them.

Optional: set services.hyperhive.matrix.enable = true; to spin up a private matrix-tuwunel homeserver in a nixos-container. Requires either services.hyperhive.domain or services.hyperhive.matrix.serverName to be set (eval fails with a clear error if both are absent). The server_name (embedded irrevocably in every user and room ID) defaults to <domain> (bare hive domain); the hive-gateway serves .well-known/matrix/{client,server} endpoints so clients auto-discover the homeserver without a subdomain. Existing homeservers must set services.hyperhive.matrix.serverName = "matrix.<domain>"; explicitly to preserve their existing user/room IDs (the server_name is embedded into every ID). Override with services.hyperhive.matrix.serverName = "chat.example.com"; for a custom server name. State lives at /var/lib/nixos-containers/hive-matrix/. Federation is enabled with an empty trusted_servers list; e2ee is deferred to a follow-up.

The hive-gateway nginx container serves a fluffychat-web matrix client at /matrix/ when services.hyperhive.matrix.gui.enable is on. This defaults to services.hyperhive.matrix.enable, so enabling the homeserver enables the web client by default; set gui.enable = false explicitly to keep the homeserver without the GUI. The ◆ M4TR1X ◆ → tab appears in the dashboard chrome when enabled. The web client can connect to any Matrix homeserver; enter the URL at first visit (e.g. the local tuwunel instance if services.hyperhive.matrix.enable = true, or any external homeserver).

Agent configuration

Per-agent settings live in each agent's agent.nix and are synced to the container as environment variables. Common options:

  • hyperhive.model — Claude model for this agent (default: "haiku"). Sets HIVE_DEFAULT_MODEL in the container; the harness applies it at boot and it takes priority over any persisted runtime override. The operator can still switch the model at runtime via the per-agent web UI, but that choice is reset by any rebuild that changes this option.

  • hyperhive.allowedRecipients — List of agent names this agent can message (via send). If unset, all agents are allowed. Useful to restrict an agent to talking only to the manager.

  • hyperhive.forge.url — Base URL of the hyperhive-managed Forgejo (default: "http://localhost:3000"). Used to configure the agent's tea login at boot; no-op if /state/forge-token is missing.

  • hyperhive.forge.keepSubscriptions — Boolean. If true, the agent's forge repo subscriptions are never auto-cleaned during rebuild; useful for agents that want to watch specific repos. Rendered as HIVE_FORGE_KEEP_SUBSCRIPTIONS.

  • hyperhive.forge.skipNotifyReasons — List of forge notification reason values to suppress (e.g. [ "subscribed" "participating" ]). Notifications matching these reasons are silently dropped; all others including direct mentions and reviews are delivered. Empty list (default) delivers all notifications. Rendered as HIVE_FORGE_NOTIFY_SKIP_REASONS (comma-separated).

  • hyperhive.frontend.dist — Override the default frontend package (pkgs.hyperhive-frontend, built by nix/frontend.nix). Set to a custom derivation to ship a fully custom per-agent SPA. The JSON contract (/api/state, /events/stream, action endpoints) is the source of truth for any replacement.

  • hyperhive.frontend.extraFiles — Attrset of extra files/directories to layer on top of the default agent dist. Each entry has a source (nix path) and an optional target (URL prefix in the static tree, defaults to the attribute name). Example: { bitburner.source = ./bitburner-dist; } serves that dist at /bitburner/. Pure additions only — overwriting an existing default file is a hard eval-time error; use frontend.dist to replace the whole dist. Paths with leading / or .. segments are rejected at eval time.

  • hyperhive.matrix.enable — Boolean (default true). When true, each agent container runs hive-matrix-daemon (a long-running matrix-sdk process that holds the per-agent client + sync) and auto-injects hive-matrix-mcp as a stdio MCP server so claude can call the matrix tools (mcp__matrix__send_message, send_dm, send_reaction, send_reply, mark_read, list_rooms, list_room_members, read_room; room args accept both !id:server and #alias:server forms). Silently no-ops when <state>/matrix-token is absent (i.e., the host-level hyperhive.matrix tuwunel container hasn't provisioned the account yet). Set to false to opt a specific agent out of matrix.

  • hyperhive.user.name — Unix username the agent runs as inside the container (default: the agent's own label, injected by the meta-flake). Agents no longer run as root. Stand-alone module eval without the meta-flake falls back to "agent".

  • hyperhive.user.passwordlessSudo — Boolean (default true). Grants the agent user NOPASSWD: ALL sudo so claude's Bash tool can still escalate when needed — same surface as the old root-user shape, just explicit. Set false for strictly unprivileged agents.

See nix/templates/harness-base.nix for the full list of options and their descriptions.

Operator CLI

hivectl is the operator-facing host CLI for ad-hoc administration that doesn't go through the broker (built alongside hive-c0re when the host module is enabled):

sudo hivectl forge create-user mara                       # provisions a forge user
sudo hivectl forge create-user mara --password 'hunter2'  # … with a fixed password
sudo hivectl matrix create-user mara                      # provisions a matrix user
sudo hivectl matrix create-user mara --password-stdin     # … reading one line from stdin

For agent names (i.e., a Coordinator::agent_state_root(name) exists), hivectl persists the resulting token to the agent's state dir like the boot sweep does. For non-agent names (e.g. the operator's own forge/matrix account), it prints the token to stdout and writes nothing.

Build / deploy

nix develop -c cargo check
nix flake check        # rust + nix + toml fmt + clippy

# deploy from a host config that imports hyperhive.nixosModules.hive-c0re
nix flake update --update-input hyperhive
sudo nixos-rebuild switch --flake .#<host>