01
AI is off by default
Admins enable the assistant per workspace. Environment keys are fallback-only; the repo points operators toward Admin -> Agent control and Settings -> AI & Agents.
Workspace toggleAdmin controlFallback env only
TaskNebula / final-source AI record
The AI controls behind the original project.
This page records opt-in AI and agent governance in the final TaskNebula source: BYOK access, native fallback, model profiles, audit logs, AGENTOWNERS policy and optional agent handoff. N-Task's present capabilities are documented separately on n-n.io.
Final OSS 0.17.3MIT sourceNo further updates
- BYOK
- Native fallback
- AGENTOWNERS
- MCP
- Local runners
- Approval gates
- Current product
- N-Task
- Final OSS release
- 0.17.3
- Legacy source license
- MIT
- OSS support
- Ended
01Final-source screenshots
Where AI entered TaskNebula's former workflow.
These dated screenshots and controls document the last public TaskNebula code, not N-Task's current interface or feature commitments.
FIG 02 · Workspace home
A dense work hub for projects, activity, personal work, analytics, and update awareness.
FIG 03 · Issue detail
Labels, versions, components, comments, sub-issues, and per-issue assist in one view.
FIG 04 · Realtime board
Kanban, sprint work, drag-and-drop planning, presence, and project status loops.
FIG 05 · Dashboard
Standup, catch-up, analytics, deadlines, pinned work, and recent activity.
02Legacy governance model
The final source made agent actions inspectable.
In TaskNebula 0.17.3, AI was an opt-in layer with provider keys, model profiles, AGENTOWNERS policy, MCP routes, local runner settings, audit logs and approval gates.
02
BYOK provider chain
OpenAI and Anthropic credentials can be configured at platform or workspace scope, encrypted with AES-256-GCM, redacted in previews, and audit-logged on rotation.
OpenAIAnthropicAES-256-GCM
03
Native planner fallback
If no LLM credential is configured, the deterministic heuristic planner keeps AI-adjacent drafting paths usable without external API calls.
Offline optionNo API callsDeterministic
04
Agent-as-assignee
The roadmap positions TaskNebula as a control plane where coding agents can be assigned work and routed through local policy.
Linear Agent ProtocolIssue sessionsApproval
05
AGENTOWNERS policy
MCP write tools attach configured actor markers before issue creation, updates, assignment, status transitions, comments, and subtasks.
CodexClaude CodeCursor
06
Optional local runner
Optional environment settings can dispatch issues to Codex or Claude Code installed in the runtime or custom image, with sandbox, cwd, model, and timeout controls.
Codex CLIClaude CodeSandbox
04What this means
Different teams need different proof.
The final code remains inspectable for BYOK, approval, audit and agent boundaries. Evaluate N-Task separately for current availability, licensing and support.
For teams
Run AI drafting without handing the whole work graph to a hosted vendor.
For admins
Separate platform defaults from workspace overrides and keep key rotation visible.
For agents
Route tool writes through identity, policy, approval, and audit instead of raw API access.
Continue with N-Task
The work has a new product home.
Explore N-Task for current project, task and team-documentation workflows. The TaskNebula repository remains a final, unsupported MIT source record for existing users and researchers.