Thinking-loop guard for dsh: observes the llm/stream waterfall and breaks a model that degrades into a loop. Detects three per-call shapes (reasoning-only calls, restated-material calls, self-repeating low-entropy reasoning) and re-fires instead of latchi
Cross-referenced across 55 tracked directories
#9126
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
9/8/2026
First Seen
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
benvargas
AI SDK v6 provider for Claude via Claude Agent SDK (use Pro/Max subscription)
packy-anthropic
The official TypeScript library for the Anthropic API
GitHub Actions
Detect agentic coding environments and AI assistant tools
jagdishpal02000
Apple's on-device (Foundation Models) and Private Cloud Compute LLMs from Node: tools, streaming, structured output, an OpenAI-compatible server and a Vercel AI SDK provider. No API key, no account.
...more