Pinned Loading

1. closed-loop-llm closed-loop-llm Public

   A tiny, transparent example of a self-improving LLM system. The model never changes, the memory does. Companion code for the talk "Designing Self-Improving Systems with LLMs."

   HTML 1

2. apprenticeops apprenticeops Public

   Open, reproducible benchmark for small, quantized, fully-offline local LLMs as homelab ops assistants — profiling quality × safety × energy together and reducing model choice to a measured Pareto f…

   Python

3. architrave architrave Public

   Judge-gated agent crew for GitHub Copilot and Claude Code: Storybook-first UI, contract-first backend, plan-only infrastructure, and optional read-only runtime observation.

   Shell

4. libgsa libgsa Public

   corecrypto-free implementation of Apple's GrandSlam (GSA) authentication — SRP-6a + crypto in C/C++ on OpenSSL. Drop-in replacement for the Apple corecrypto dependency in AltSign/AltServer-Linux.

   C

5. LibreChat LibreChat Public

   Forked from danny-avila/LibreChat

   Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching,…

   TypeScript