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 68.7%
  • Nix 15.7%
  • JavaScript 8.4%
  • CSS 3.7%
  • TypeScript 1.9%
  • Other 1.6%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas 0e1a975f9f fix(3179): the gateway's config files get their own state dir
`agents.conf` and `gateway.htpasswd` move from /var/lib/hyperhive/gateway
to /var/lib/hive-gateway/conf, alongside the `tls/` the gateway already
kept there.

nginx reads both as an unprivileged user. Under c0re's state dir it could
only reach them by traversing a directory systemd re-declares `0750
hive-core` on every c0re start — so nginx was given `SupplementaryGroups
= [ "hive-core" ]`, which also handed it read access to everything else
group-readable in that tree. The tokens are individually 0600, but the
broker sqlite carries no explicit mode: every message between every agent
was readable by the process whose job is parsing untrusted network input.

Moving the files removes the need and the exposure together. The group is
gone, and its absence is now commented as load-bearing so it doesn't come
back as a fix for a symptom it would recreate.

Also drops this module's `/var/lib/hyperhive` tmpfiles rule. It declared
`0755 root root` and could never win against `StateDirectoryMode`, and a
losing declaration still reads as a guarantee — that is what sent the
first diagnosis of the outage looking for who had changed the mode.

Ordering is unchanged and still the thing that makes a fresh boot work:
tmpfiles runs before services and seeds both files empty-but-valid, nginx
names them (an `include` of a missing file is fatal, not empty), and
content arrives when c0re writes and reloads — which it does on every
topology change, so a boot against the empty seed resolves itself.

Folds in the mode fix: `write` now sets 0644 on the tmp file before the
rename, because a rename carries the source's mode and discards the
destination's, and the tmpfiles rule that declares 0644 is
create-if-absent so it never re-applies.
2026-08-12 10:29:27 +02:00
.forgejo/workflows docs: stop claiming tracker-tag/comment-block lint are non-required 2026-07-23 00:10:59 +02:00
branding docs(#1182): remove component-diagram.svg; trim README; link to website + options 2026-06-03 19:06:06 +02:00
claude-plugins claude-subagents skill: add concurrency guidance for container memory cap 2026-08-01 11:24:58 +02:00
docs fix(3179): the gateway's config files get their own state dir 2026-08-12 10:29:27 +02:00
frontend swarm-ui: bootstrap new swarm-level frontend (Preact + wouter + TS + JSX) 2026-08-11 21:31:44 +02:00
hive-agent hive-c0re/hivectl/hive-agent: pause as a job-queue DAG node (closes #3056) 2026-08-11 23:47:09 +02:00
hive-agent-mcp feat(3088): move the gateway's nginx + dnsmasq onto the host 2026-08-11 18:01:03 +02:00
hive-agent-sock hive-sh4re: split inbox, container, journal, and schedule wire shapes into their own modules 2026-08-10 23:26:15 +02:00
hive-bash-mcp hive-bash-mcp: fix wait_for_task/run_task todo race with a refcounted waiter registry 2026-08-11 20:31:43 +02:00
hive-c0re fix(3179): the gateway's config files get their own state dir 2026-08-12 10:29:27 +02:00
hive-core-agent-sock hive-c0re/hivectl/hive-agent: pause as a job-queue DAG node (closes #3056) 2026-08-11 23:47:09 +02:00
hive-forge hive-forge: surface comment/issue attachments in comments/view/comment-show/issue 2026-08-11 20:31:36 +02:00
hive-forge-notify feat(#2642): a github.com notification poller alongside the forge one 2026-07-31 17:23:18 +02:00
hive-host-sock fix(3179): the gateway's config files get their own state dir 2026-08-12 10:29:27 +02:00
hive-jobq jobq: the README repeats the same false persistence claims 2026-08-03 17:28:09 +02:00
hive-jobq-wire jobq: a generic per-state roll-up, served beside the graph 2026-08-03 20:37:06 +02:00
hive-matrix-mcp fix(#2860): no loopback default for the matrix homeserver 2026-08-03 20:34:36 +02:00
hive-metric docs(#2627): add READMEs for the remaining infra crates 2026-07-23 13:16:29 +02:00
hive-priv docs(gateway): describe what is, not what changed 2026-08-11 18:09:51 +02:00
hive-priv-sock docs(gateway): describe what is, not what changed 2026-08-11 18:09:51 +02:00
hive-screen-mcp docs(#2627): add README for hive-screen-mcp 2026-07-23 14:17:47 +02:00
hive-sh4re feat(3088): move the gateway's nginx + dnsmasq onto the host 2026-08-11 18:01:03 +02:00
hive-sock-client refactor(sock): one socket client, retry as a policy value 2026-07-26 22:44:48 +02:00
hive-types docs(#2627): add READMEs for the remaining infra crates 2026-07-23 13:16:29 +02:00
hivectl hive-c0re/hivectl/hive-agent: pause as a job-queue DAG node (closes #3056) 2026-08-11 23:47:09 +02:00
nix fix(3179): the gateway's config files get their own state dir 2026-08-12 10:29:27 +02:00
scripts scripts: cover .tsx in the tracker-tag and comment-block lints 2026-08-11 21:01:26 +02:00
swagger-ui-theme move swagger-ui-theme/ out of hive-c0re/ 2026-08-02 21:24:57 +02:00
swarm-controller docs(gateway): describe what is, not what changed 2026-08-11 18:09:51 +02:00
swarmctl swarmctl: add CLI reference docs, same pattern as hivectl 2026-08-11 21:55:56 +02:00
.gitignore fix(review): drop libnull.rlib artifact + add Errors doc to ensure_config_pr_webhook 2026-07-11 12:19:52 +02:00
.mailmap chore(#2165): add damocles@pr1ma + lexis@pr1ma mailmap entries 2026-07-04 13:50:16 +02:00
.prettierignore docs: give turn-loop/ a README.md landing page 2026-08-03 12:55:18 +02:00
.prettierrc temp: add prettier configs 2026-07-02 23:33:11 +02:00
Cargo.lock swarmctl: add CLI reference docs, same pattern as hivectl 2026-08-11 21:55:56 +02:00
Cargo.toml feat(#3089): add swarmctl and a user-add verb for the swarm's SSO 2026-08-10 21:48:45 +02:00
CLAUDE.md swarmctl: add CLI reference docs, same pattern as hivectl 2026-08-11 21:55:56 +02:00
clippy.toml hivectl: wireguard mesh setup verbs (#1756) 2026-06-19 14:37:50 +02:00
flake.lock nix flake update 2026-07-13 13:58:53 +02:00
flake.nix feat(#3089): add swarmctl and a user-add verb for the swarm's SSO 2026-08-10 21:48:45 +02:00
README.md docs: add a top-level docs/README.md index, point README.md at it 2026-08-03 17:27:43 +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 → :80 (hive-gateway)    dashboard + per-agent UIs
│   │                                   /agent/<name>/ → per-agent unix socket
│   └── CLI     → /run/hyperhive/host.sock   admin protocol
│
├── hive-c0re  (Rust daemon: lifecycle / broker / approvals /
│               auto-update / dashboard / sockets)
│
├── optional containers
│   ├── hive-gateway   nginx — proxies :80 → c0re dashboard + per-agent sockets
│   ├── hive-forge     Forgejo — per-agent accounts, config mirror (agent-configs/)
│   └── hive-matrix    tuwunel — Matrix homeserver + per-agent accounts
│
└── agent containers
    ├── h-ruth     manager (privileged MCP surface, approval gating)
    └── h-<name>   sub-agent (claude + MCP tools + per-agent web UI + unix socket)

→ website · → docs · → options reference

Depth lives in docs/ (rendered at hyperhive.darkest.space/docs/) — start at docs/README.md and pick the page matching your task rather than reading front to back.

Quick start

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";
    # Pin hyperhive to your own nixpkgs instead of the one it ships with
    # (see "Overriding nixpkgs" below) — recommended for most hosts:
    hyperhive.inputs.nixpkgs.follows = "nixpkgs";
  };

  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.

Overriding nixpkgs

hyperhive pins its own nixpkgs so it builds standalone in CI. Add hyperhive.inputs.nixpkgs.follows = "nixpkgs" (as in the quick-start above) to build it against your host's nixpkgs instead — one less nixpkgs evaluation, no version drift from the rest of your system. Standard flake follows pattern; works as long as your channel is reasonably close to the nixos-26.05 hyperhive develops against. Drop it again if a much older/newer channel hits breakage hyperhive's CI doesn't catch.

For the full list of host and agent NixOS options see the options reference.

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.default
nix flake update --update-input hyperhive
sudo nixos-rebuild switch --flake .#<host>