Features

A useful boundary around
agent work.

A reusable orchestration core for independent tasks. Your application keeps ownership of its data, prompts, and validation rules.

01 / Inputs

Plain prompts. Explicit arguments.

Store templates in a prompts directory and supply task arguments as JSON objects. Values are inserted literally; they are not executed as code.

  • Reusable task inputs across multiple runs
  • String application identifiers separate from task IDs
  • Prompt paths contained within the configured directory
02 / Execution

Codex CLI, coordinated.

The framework launches independent Codex CLI workers. Each stored run determines the model and reasoning effort used by its tasks.

  • Configurable concurrency and attempt deadlines
  • A shared rolling limit on task runner starts
  • Soft-stop draining and forced process cleanup
03 / Results

An outcome you can follow.

A successful response and its terminal attempt state are committed together. A failed attempt stays in history when an explicit retry is created.

  • One saved successful response per run and task
  • Distinct task progress and historical attempt totals
  • JSONL export with application unit identifiers
04 / Monitoring

A local view of the work.

The operator dashboard shows the selected run, active workers, recent completions, and effective session limits.

  • Processing rate and estimated remaining time
  • Reported token usage, when available
  • Account-wide quota observations kept separate
05 / Storage

A small, deliberate data model.

Four framework-owned SQLite tables hold tasks, runs, attempts, and results. Application data stays in a separate database.

  • WAL mode and foreign-key enforcement
  • One local coordinator per service database
  • Explicit migrations preceded by a verified backup
06 / Integration

Your application at both ends.

Preparation and export scripts are invoked separately. Another domain can connect through the Store API without adding application SQL to the core.

  • Prepare tasks and create a runnable batch
  • Validate saved text using application rules
  • Own your conflict checks and export policy
Current boundaries. Responses are stored as text. Domain validation and application delivery belong to the integration; durable automatic delivery and distributed execution are not implemented.

A clearer workspace for your agents.

The project and its GitHub repository will be publicly available soon.

Release information