vibehacker
News
Anthropic ·

Anthropic: Opus 5.5 ~40% cheaper on long Claude Code sessions

Anthropic estimates Opus 5.5 costs about 40% less than Opus 5 on typical Claude Code traffic after cutting cache reads 60% and token prices 20%. Sessions now run 3.3x longer per prompt with 2.6x more context; API users can set a one-hour cache TTL, and forked subagents inherit the parent's cache.

More news

View all

OASIS 1.0 ships a bring-your-own-model coding agent built to work with 1.5B–3B local models

Published Nov 4, the open source agent runs from CLI, browser workspace, desktop, VS Code, SDK, and GitHub Action, with hosted providers or local servers like Ollama, llama.cpp, and vLLM. It adds a post edit verification gate, weakened test detection, git safety snapshots, and refusal of unrequested commits or pushes, but the sandbox is off by default and small local models still fail many tasks…

GitHub (FAHTHIZ/oasis)

Upstash tuned its MCP server after 369 coding-agent runs: delete confirmation went from 1/15 to 15/15

Upstash ran seven coding agents through live Redis tasks and found agents couldn't enable daily backups, probed Redis logs that don't exist, read 0 stats right after traffic, and deleted a named database with no confirmation. After adding redis set daily backup , clearer tool text, and a type the name delete check, backups went from 0/15 to 15/15 and delete confirmation from 1/15 to 15/15…

Upstash Blog

Spotted something we missed? Start a thread.