asakin
Show HN: Dragoman – Multi-model routing for Claude Code via sub-agents
https://github.com/asakin/dragoman
I use Claude Code and also pay for Perplexity, OpenAI, Gemini, and run Ollama locally. Got tired of switching tabs when the right model for a question wasn't Claude.Dragoman is a small CLI (~800 lines) that plugs into Claude Code's sub-agent system. Ask about the news → routes to Perplexity. "Try Gemini" → goes to Gemini. "Run locally" → Ollama. You can fan out to four models and have Claude...
The era of "malicious compliance" in AI identity is here
Built this for my own workflow — I'm running LLM wikis (llm-context-base) and switching context between different agent roles constantly. The startup latency was killing the flow. Happy to answer questions.
Show HN: LLM-primer – pre-warmed Claude Code session pool, zero startup wait
https://github.com/asakin/llm-primer
Claude Code sessions that read a real CLAUDE.md take 30-60 seconds to initialize. Fine once. Friction when you're switching contexts constantly.llm-primer keeps a pool of warm sessions in the background. When you need one, it's already past the startup protocol.Happy to answer questions. The main motivation was that I'm running LLM wikis (llm-context-base) and switching context between...
Show HN: LLM-context-base – Git template for LLM-powered personal wikis
https://github.com/asakin/llm-context-base
Main additions on top of the pattern: a training period where the AI learns how you work over 30 days then gets quieter over time, a metadata standard so files are queryable by summary, and a lint pass for stale content and context loading optimization. Never have to design a taxonomy upfront.