Anthropic leak suggests Claude Conway access ends July 24
testingcatalog · x · 2026-07-20
Anthropic internal access to Claude Conway is reportedly ending on Friday, July 24. The post suggests two possibilities: Conway has been discontinued, or it is being moved into a broader release phase in July.
The screenshot and description indicate Conway is a remote, always-on Claude agent running in a dedicated container, with support for webhooks, connectors, plugins, and custom UI tabs—hinting at a possible Anthropic pattern for shareable UI artifacts around remote agents. It has allegedly been in development since April and tested internally for months.
More from coding & agent
- MCP fault injection study: agent task scores drop 60% under realistic tool failures, scale doesn't help — dair_ai · 2026-10-26
- General agents burn ~140M tokens/month on LinkedIn outreach; scripts do it 60x cheaper — ChrisHarpon2 · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26
- NLI alone rejects 5/6 new agent memories; a 0.45 similarity gate fixes it all — Alternative_Pin9598 · 2026-10-26
- LangChain ships Managed Deep Agents 0.9, walkthrough from Interrupt London keynote — LangChain · 2026-10-26
- Knowledge Worker Kit adds a full section on organizing projects — dSebastien · 2026-10-26