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 68.5%
  • Nix 15.6%
  • JavaScript 7.1%
  • CSS 3.8%
  • TypeScript 3.5%
  • Other 1.5%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas 8baf1899d8 feat(#3255): name the swarm event subjects, and let the controller publish them
The controller could not emit an event at all: a reader's grant is
`reader_subjects()`, which is `$JS.API.*` only, so a publish to any event
subject would be refused — and a NATS refusal reaches the client as a
timeout, so the visible symptom would have been a hive that never hears
about a change, with nothing in any log naming a permission.

Adds `swarm_queue_client::events`, following `status::BUCKET`: three
crates must agree on these strings (the controller publishes, a hive
subscribes, the callout responder decides whether the publish is
permitted), and a literal repeated across crates is an agreement nothing
checks. The responder speaks neither jetstream nor kv, so the module is
unconditional and carries no NATS types, exactly as the bucket name is.

The grant takes the wildcard form from the same function the publisher
calls, so the two cannot drift; a separate wildcard constant would have
re-created the disagreement this module exists to prevent.

Tests pin that a reader gets the subject and that a hive does NOT — a
hive able to publish here could tell a neighbour the knowledge repo
changed when it had not, which is an unauthenticated write into someone
else's control path. That one asserts on the subject root rather than a
rendered subject, so a future event leaf fails it too instead of passing
because the test only knew about `knowledge`.

Both assertions mutation-tested: removing the grant fails the reader
test, granting a hive the subject fails the denial test, each on its own
assertion line, and the unmutated tree is green.
2026-08-19 21:05:52 +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 skills(headless-screenshot): document two false-positive traps 2026-08-15 09:59:55 +02:00
docs docs(matrix): trim upgrade notes per review 2026-08-19 20:01:45 +02:00
frontend swarm-ui: fix underline not showing on the initial page load 2026-08-19 19:54:52 +02:00
hive-agent fix hint text per argus review: group into subdirs, not split into more top-level files 2026-08-18 22:07:05 +02:00
hive-agent-mcp reword ack->mark-done terminology on mark_todos_done and get_loose_ends 2026-08-16 17:55:33 +02:00
hive-agent-sock hive-agent: guarantee a wake after a self-requested /compact 2026-08-13 23:17:10 +02:00
hive-bash-mcp feat(#3245): gate rustdoc in nix flake check, and clear the workspace 2026-08-14 02:30:55 +02:00
hive-c0re swarm-controller: move OTEL deps to workspace level, drop jobq_metrics singleton 2026-08-19 18:10:22 +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: unit-test blocking_open_count 2026-08-19 15:17:28 +02:00
hive-forge-notify forge-notify: widen earlier-activity marker to the full timeline 2026-08-19 19:06:16 +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 feat(#3245): gate rustdoc in nix flake check, and clear the workspace 2026-08-14 02:30:55 +02:00
hive-jobq-metrics swarm-controller: extract jobq_metrics into its own hive-jobq-metrics crate 2026-08-19 18:10:22 +02:00
hive-jobq-wire address review: move parse_states/filter_nodes_by_state to hive-jobq-wire, rename placeholder enums, trim core-mirroring framing 2026-08-16 16:59:54 +02:00
hive-matrix-mcp fix(#3072): stop waking every agent on a re-applied m.space.child state event 2026-08-19 17:12:01 +02:00
hive-metric swarm-controller: move OTEL deps to workspace level, drop jobq_metrics singleton 2026-08-19 18:10:22 +02:00
hive-priv hive-priv: replace json! with typed structs for account sidecar files 2026-08-13 23:16:17 +02:00
hive-priv-sock feat(#3245): gate rustdoc in nix flake check, and clear the workspace 2026-08-14 02:30:55 +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 feat(#3245): gate rustdoc in nix flake check, and clear the workspace 2026-08-14 02:30:55 +02:00
hive-types docs(#2627): add READMEs for the remaining infra crates 2026-07-23 13:16:29 +02:00
hivectl feat(#3245): gate rustdoc in nix flake check, and clear the workspace 2026-08-14 02:30:55 +02:00
nix fix(#3527): a missing source must report as zero, not as empty 2026-08-19 20:27:00 +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-authelia-bridge docs(#3422): the user store is one file, not two 2026-08-18 10:34:00 +02:00
swarm-authelia-bridge-sock add swarm-authelia-bridge: the only thing allowed to write swarm-authelia's users database 2026-08-16 22:38:40 +02:00
swarm-controller fix(#3529): create agent config repos in agent-configs, not agents 2026-08-19 19:06:46 +02:00
swarm-nats-auth feat(#3255): name the swarm event subjects, and let the controller publish them 2026-08-19 21:05:52 +02:00
swarm-queue-client feat(#3255): name the swarm event subjects, and let the controller publish them 2026-08-19 21:05:52 +02:00
swarmctl chore(#3422): drop swarmctl's now-unused serde_json dependency 2026-08-18 10:40:36 +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 swarm-controller: extract jobq_metrics into its own hive-jobq-metrics crate 2026-08-19 18:10:22 +02:00
Cargo.toml swarm-controller: extract jobq_metrics into its own hive-jobq-metrics crate 2026-08-19 18:10:22 +02:00
CLAUDE.md docs(#3422): the user store is one file, not two 2026-08-18 10:34:00 +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 wire swarm-authelia-bridge: systemd unit, oidc client, controller auth env 2026-08-16 22:38:40 +02:00
README.md docs(readme): drop Rust function-name citation for plain-language behavior 2026-08-15 12:45:22 +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 a name that's a managed agent, hivectl persists the resulting token to that agent's state dir, the same as the boot sweep does. For a non-agent name (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>