ClawsGO
Get started

CHANGELOG

What shipped.

Features, improvements, and fixes — newest first, recorded as they ship.

Plan names

Personal plans are now Plus, Pro, Max and Ultra. The old Ultra is now Max, with the same price and benefits

Release media (placeholder)
  • The old Team plan is now Ultra and includes Claude Fable 5.1
  • Plans for organizations are now Business and Enterprise. The old Enterprise is now Business, and the new Enterprise adds private deployment and SLAs

· v1.5

Credit multipliers

Usage is metered per token, with one multiplier per model shown on the model menu

Release media (placeholder)
  • Bills show credits only — no more dollars
  • Claude Fable 5.1 is now exclusive to Team and Enterprise plans. Contact us to enable it

· v1.4

Team workspaces, in beta

Team workspaces enter beta: share tasks, reports, and credits — one workspace for the whole research group

Release media (placeholder)
  • Hand any task off: every member can inspect the agent's full search trail, reading log, and edit history
  • Workspace-level billing in credits, with monthly exports for admins
  • Open to all members during beta — create one from Settings in a click

· v1.3

Long-task reliability

Tasks running past six hours now checkpoint automatically and resume from the interruption, never from zero

Release media (placeholder)
  • Fixed deep search re-fetching the same sources, noticeably improving source diversity in long reports
  • The task page now streams live steps: what the agent is doing, which model it is using, and what it has spent
  • Fixed an occasional citation misalignment in PDF exports

· v1.2

Citation panel, rebuilt

Rebuilt the citation panel: every claim carries a clickable citation that jumps back to the exact source passage

Release media (placeholder)
  • Citations now group by source type — papers, news, official documents, datasets
  • New citation health checks automatically flag dead links and retracted papers
  • Export citations in APA, MLA, or GB/T 7714

· v1.1

Auto routing is live

Auto routing is live: every step of a task is routed across Claude Sonnet 5, Claude Opus 5, and GPT 5.6

Release media (placeholder)
  • Search and reading go to Claude, pure logical reasoning to GPT — which model ran each step is always visible
  • Routing decisions are written to the task log, replayable step by step
  • You can still pin a single model manually, metered by its credit multiplier

· v1.0

ClawsGO 1.0

Give ClawsGO one research brief; a cloud agent searches, reads, analyzes, and drafts until it delivers a file you can cite

Release media (placeholder)
  • Launch deliverables: research reports, literature reviews, data tables, and decision briefs
  • Membership dues become credits, metered per token with each model’s multiplier on the menu
  • Free to start, no credit card, your first task runs in minutes

Only what has shipped makes this list.