| Filename | Latest commit message | Latest commit date |
|---|---|---|
d516bb890c
Each agent row on the hive dashboard, and the agent page's link menu, linked to the agent's forge profile and its config repo. Both are gone, with what only they used: - hive-agent no longer builds the two links, the `Forge` link kind, or the `forge_public_url` field of its state, and no longer reads `HIVE_FORGE_PUBLIC_URL`. The agent page's link menu and the dashboard row's icon strip (which skips a forge link an agent not yet rebuilt still sends) drop their forge handling. - hive-c0re's dashboard state no longer carries `forge_public_url`. - `HIVE_FORGE_PUBLIC_URL` is no longer forwarded to agents through the meta flake (the forwarded-variable list, its test fixture, the controller's settings and the VM test), so the next meta flake render differs by that one line. hive-c0re still reads it for the forge URL a hive publishes, so `swarm.forge.publicUrl` stays, with its description corrected. - The docs stop describing the links. |
||
| .. | ||
| agent-roster.md | ||
| config-changes.md | ||
| persistence.md | ||
| README.md | ||
| security.md | ||
| web-page.md | ||
Agents
An agent is one Claude instance in its own NixOS container, with its own state directory, forge account and matrix accounts. This section covers running one: its identity, what survives a restart, how its config changes, what its own page shows and how far you can trust it.
- Roster — the agents of a hive, and who may do what to whom.
- Persistence — what survives a restart, a destroy and a purge.
- Config changes — how a change to an agent's config flows from a pull request to its container.
- The agent's web page — the per-agent terminal view, its actions and its endpoints.
- Security model — the trust model, the prompt-injection threat model and credential isolation.
The swarm creates and configures agents: the create form and its archetypes
are in swarm/archetypes.md, logging an agent in to
claude is in swarm/claude-login.md, and you set
an agent's permissions with swarmctl agent permissions or on the swarm UI.
What an agent can do inside its container is in
4-implementation/agent-tools/.