Private beta · self-hosted

neutron core

Self-hosted infrastructure for governed agent work across tools, repositories, schedules, and peer instances. Configure many agents from one core image.

01

Work enters through one governed runtime

Interactive chat, repository mentions, API tokens, MCP clients, and schedules all resolve to a named agent with an explicit identity, resource set, model provider, and policy.

neutron core · live product
Neutron core agent workspace with recent conversations and configured capabilities
1
core image
N
configured agents
3
safety modes
1
persistent run history
INPUT

Web UI, GitHub or GitLab mention, token-authenticated MCP, or a durable schedule.

NAMED AGENT

Persona, provider, capability grants, workspace resources, and safety policy are resolved for the turn.

GOVERNANCE

Per-tool allow, gate, or deny decisions on Claude SDK turns; optional approval routing; persistent traces and decisions.

OUTCOME

A saved thread, inline repository reply, pull or merge request work, or an inbox card governed by interruption policy.

02

Governed autonomy is the product

The Claude SDK driver applies controls at the point of action. Neutron-owned connectors use shared policy checks; native OpenCode tool-governance parity remains in progress.

POSTURE

Three safety modes

readonly, approval-gated, and readwrite set the default posture for each agent.

POLICY

Tool-level decisions

Allow, gate, or deny individual tools. New MCP capability tools begin gated until an operator changes policy.

APPROVAL

Routing when required

Route a gated action to a role or named users. Two-person separation is available when the policy calls for it.

ENGINE BOUNDARY

OpenCode enforcement differs

OpenCode currently does not share Neutron's Claude SDK per-tool approval enforcement. Treat that adapter as an explicit trust boundary.

03

Proactive work, without notification noise

Neutron can run headless turns on a clock, retain their results, and decide how urgently those results should reach an operator.

Inbox · proactive output
Neutron inbox with scheduled run results and priority states
SCHEDULES · INBOX · FLEET

Durable schedules meet an interrupt governor

Five-field cron schedules start durable, headless agent turns. Retries survive a pod restart, results stay in per-schedule threads, and typed inbox cards preserve the outcome.

  • The interrupt governor applies quiet hours and priority breakthrough before raising a toast
  • A fleet hub can delegate chat or administration to registered peer instances with scoped tokens
  • Operators can gate schedule mutations and fleet administration with per-tool policy
  • Headless and repository-channel turns deny gated actions when no live approval bridge is available
04

Capabilities and providers are controlled resources

Operators register integrations once, scope credentials and grants, then equip only the agents that need them.

CAPABILITY REGISTRY

MCP servers, tools, and skills

Register OAuth-aware MCP servers, pinned CLI tools, and reusable skills. MCP and skills support both drivers; CLI grants currently use the Claude SDK driver.

PROVIDER CONTROL PLANE

Credentials without redeploys

Scope and rotate named API-key credentials for compatible backends. Manage subscription and catalog connections through OpenCode.

VAULT

Secrets stay governed

Use OpenBao or the assay-engine encrypted vault. Sensitive capability values remain secret references instead of raw registry data.

ENGINE SEAM

One event contract

Claude SDK and OpenCode normalize output and usage behind one event contract. Their native tool-governance paths are not yet equivalent.

05

Repository work stays isolated

GitHub and GitLab workspaces resolve through agent-scoped connections and persistent per-agent worktrees.

WORKSPACES · CHANNELS

One agent identity per working context

Each agent receives only its granted repositories, guides, connections, and capabilities. A shared bare cache keeps checkout efficient while each working tree remains isolated.

  • Investigate, branch, commit, and push according to workspace autonomy and the selected engine
  • PR/MR creation is governed separately and requires host CLI authentication
  • Claude SDK workspace guardrails refuse default-branch pushes
  • GitHub and GitLab mentions reply inline with conversation memory and cost attribution
Settings · Resources
Neutron resource settings with workspace and guide grants
06

Issue autopilot is under development

Today, Neutron responds to GitHub and GitLab mentions and can work inside assigned workspaces. Durable issue claiming, reconciliation, job state, and automatic branch-to-PR lifecycle are roadmap work; the product does not present arbitrary backlog pickup as shipped.

Available now

Mention-driven repository investigation, configured tool use, isolated workspace changes, and inline replies.

Roadmap

Label-driven issue intake, named-agent dispatch, durable progress updates, CI reconciliation, and operator-controlled merge handoff.

Private beta

Operate agents on your terms.

Request access to evaluate Neutron against your infrastructure, identity, provider, and repository requirements.

Private beta access

One confirmation email, then product access updates only.

Review deployment →