FWIW this isn’t new, using a Claude/Max subscription auth token as a general-purpose “API key” has been known (and blocked) for ages. OpenCode basically had to impersonate the official Claude Code client to make that work, and it always felt like a loophole that would get patched eventually.
This is exactly why (when OpenCode and Charm/Crush started diverging) Charm chose not to support “use your Claude subscription” auth and went in a different direction (BYOK / multi-provider / etc). They didn’t want to build a product on top of a fragile, unofficial auth path.
And I think there’s a privacy/policy reason tightening this now too: the recent Claude Code update (2.1-ish) pops a “Help improve Claude” prompt in the terminal. If you turn that ON, retention jumps from 30 days to up to 5 years for new/resumed chats/coding sessions (and data can be used for model improvement). If you keep it OFF, you stay on the default 30-day retention. You can also delete data anytime in settings. That consent + retention toggle is hard to enforce cleanly if you’re not in an official client flow, so it makes sense they’re drawing a harder line.
Yea exactly, I’m surprised people are calling this “drama”. It was from the beginning against the ToS, all the stuff supporting it just reverse engineered what Claude Code is doing and spoof being a client.
I tried something similar few months back and Claude already has restrictions against this in place. You had to very specifically pretend to be real Claude Code (through copying system prompts etc) to get around it, not just a header.
How does the memory scale (or not!) over time. If using Letta in a single agent mode, similar to just using claude - how does memory blocks stay relevant and contextual?
I guess what I'm asking is, if there is a memory block limit, is that an issue for self learning over time. Claude as you know just straight up ignores CLAUDE.md and doesnt self-improve it.
I like this approach, and it's very similar to what I'm currently using - albeit my use case is to get Claude to automatically invoke the relevant subagents during both planning and build stages.
Subagents using MCP would solve quite a lot of the context preparation required for a successful session. I'm using GLM-4.6 vision/web search MCP in claude code to relative success as the subagents can access these via API (not true MCP behaviour but close enough)
This is really cool. Really interested in your MCP workaround -
I have three future agents blocked by Issue #7296. Would you be willing to
share more details about your GLM-4.6 setup? Specifically how you're doing
"API (not true MCP behaviour)" to get sub-agents accessing those tools? house-mcp would be super useful for me
Hey -- sorry was out of town so didn't see this! It could definitely work without Linear. You'd need to modify the command for the linear stuff to just write to MD files and make sure you pass those through to the other agents.
I like this solution, I had tinkered with the Otel hoping to get un-redacted prompt and responses but had no luck. Did you perhaps get deeper into what data was useful?
You can get the un-redacted prompts via the OTel event logger[0], but unfortunately it won't give you responses. You could open up a GitHub issue to request that addition!
Disclaimer - I work at Anthropic but not on Claude Code, the team is responsive via GH issues though!
This is exactly why (when OpenCode and Charm/Crush started diverging) Charm chose not to support “use your Claude subscription” auth and went in a different direction (BYOK / multi-provider / etc). They didn’t want to build a product on top of a fragile, unofficial auth path.
And I think there’s a privacy/policy reason tightening this now too: the recent Claude Code update (2.1-ish) pops a “Help improve Claude” prompt in the terminal. If you turn that ON, retention jumps from 30 days to up to 5 years for new/resumed chats/coding sessions (and data can be used for model improvement). If you keep it OFF, you stay on the default 30-day retention. You can also delete data anytime in settings. That consent + retention toggle is hard to enforce cleanly if you’re not in an official client flow, so it makes sense they’re drawing a harder line.
reply