By SeeleAI
Orchestrate auditable AI agent workflows with persistent project state, using a debate engine for decision risk assessment, a DAG-based work queue, and a human-visible dashboard for monitoring execution health and lifecycle phases.
Run an adversarial attacker/adjudicator discussion against an idea, work item, or decision.
Run the DAG-first actionable work queue until ready/active/failed work is closed, paused, or stopped.
Alias for `status --dashboard`; manage the local dashboard backed by .thoth ledgers.
Discuss or record planning decisions without entering implementation execution.
Alias for `status --doctor`; strictly audit project health without writing authority.
No model invocation
Executes directly as bash, bypassing the AI model
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Dashboard-first orchestration runtime for autoresearch.
Turn drifting agent work into durable runs, locked work items, and argument-backed verdicts.
v0.4.3 Experiment Workbench · Registry-backed experiments, extension commands, Dashboard compare, and a controlled TUI viewport
THOTH CONTROL PLANE
Claude Code surfaces Codex surfaces
/thoth:* command set $thoth command set
\ /
\ /
+-------------+
|
v
+----------------------------------------------------------------------------+
| Layer 1. Host Surface |
| |
| init discuss run loop argue auto status |
| doctor dashboard tui extension |
+----------------------------------------------------------------------------+
|
v
+----------------------------------------------------------------------------+
| Layer 2. Planning Authority |
| |
| init -> bootstrap/migrate/resync or open raw intent discussion |
| discuss -> record discussions, decisions, work items, and work_graphs |
| |
| Discuss -> Decision -> Work Item Object Graph |
| | |
| v |
| Ready Work (--work-id) |
+----------------------------------------------------------------------------+
|
v
+----------------------------------------------------------------------------+
| Layer 3. Execution Runtime |
| |
| run -> one durable execution packet |
| loop -> one durable recoverable loop packet |
| argue -> adversarial discussion and authority patch preview |
| auto -> DAG-first child loops for actionable work |
| |
| +---------------------------+ |
| | Ready Work (--work-id) | |
| +-------------+-------------+ |
npx claudepluginhub seeleai/thoth --plugin thothThoughtbox observability, protocol enforcement, and CLI for Claude Code
Enterprise AI agent orchestration plugin with 150+ commands, 74+ specialized agents, SPARC methodology, swarm coordination, GitHub integration, and neural training capabilities
AI development loop — orchestrator distributes tasks to headless workers, independent auditor verifies, structural enforcement auto-blocks downstream on upstream failure. Full-cycle validated with 10-scenario test harness.
Autonomous, personalized research loops for Claude Code. Set a topic, walk away, come back to a quality-gated report adapted to your projects.
Context hub for agentic workflows - manage projects, tasks, sessions, and multi-agent coordination
Festival Methodology for Claude Code — goal-oriented project management for human-AI development workflows. Provides fest and camp CLI integration, automatic installation, and methodology guidance.