A useful session can still leave no durable operation.
Chat history is a fragile place to keep project state. Decisions, discoveries, verification, and the next action need a home that another session can inspect.
Case 001Released · Agent operations
Citadel
Agents can write code. The harder problem is operating them across work that has to survive a single chat.
ArtifactReleased open-source system
ProblemOperating agents across real work
RoleRepository-local operating layer
Try the operating idea
From request to evidence to the next useful action.
Citadel is the harness around Claude Code and OpenAI Codex: routing, durable project state, repository safeguards, verification, and coordinated work. This public-safe instrument reconstructs that operating loop without exposing a private repository.
Public-safe reconstructionMission Control / operating loop
01 Intent router
Describe the work. Inspect the operating choice.
Selected operating modeCampaign
DurableThe work needs phases, decisions, handoffs, and a concrete place to resume after interruption.
- Campaign state
- Phase evidence
- Session handoff
02 Mission Control
One operating loop. Visible state.
Choose a stage to inspect what Citadel keeps legible.
Current stageRoute
Start with the outcome. Citadel selects the lightest operating mode that fits the work.
/do + routing recordOperationservice-refactorEvidenceInspectableNext actionResume phase 03
The software-shaped problem
The model is only one part of the system.
More agents create an operating problem.
Parallelism is valuable only when scopes are independent, branches are isolated, discoveries travel, and a human can review what should actually land.
“Done” should resolve to evidence.
Citadel records checks and handoffs with explicit passed, failed, blocked, or unknown states. It improves operating discipline; it does not replace code review or guarantee correctness.
The governing model
Engine, operating layer, source of truth.
Citadel does not try to become a new coding-agent runtime. It supplies the workflows and durable state that help existing runtimes operate inside a real repository.
03RepositoryCode, rules, project state, verification evidence
02CitadelRoute, coordinate, safeguard, verify, hand off
01Coding agentClaude Code or OpenAI Codex executes the work
Evidence and limits
Show the operating claim. Keep the proof boundary visible.
One natural-language entry point
/do routes a request toward a focused workflow, campaign, fleet, or other bounded operation.
State outside the chat
Campaigns, decisions, discoveries, reports, and handoffs live with the project instead of disappearing with a context reset.
Evidence with named states
Checks remain passed, failed, blocked, or unknown. A missing result does not become success through presentation.
Discipline is not correctness
The harness runs with the agent’s permissions and cannot eliminate human review, repository-specific tests, or consequential approvals.
Inspect the system
Open source, documented, and designed to be reversible.
The repository contains the install path, demo workflow, Mission Control specification, operating contracts, verification gates, threat model, and removal path.