Pinned Loading

1. rasputin-memory rasputin-memory Public

   The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model reranking, and 77.7% LoCoMo accuracy. MCP native, REST API, self-…

   Python 33 5

2. llm-stress-harness llm-stress-harness Public

   Diagnostic toolkit for self-hosted LLM inference: failure-taxonomic stress harness + 4-phase orchestrator + parametric vLLM launchers

   Shell

3. qwen-bench qwen-bench Public

   Hub for ongoing Qwen inference benchmarks on NVIDIA Blackwell. Indexes all studies, hosts the rolling SOTA leaderboard, points to the toolchain.

   Python 2 1

4. qwen36-27b-blackwell-inference-study qwen36-27b-blackwell-inference-study Public

   Systematic 24-hour benchmark study of Qwen3.6-27B inference on dual NVIDIA RTX PRO 6000 Blackwell SM120 (TP=2). 8 experiments comparing repne/vllm fork vs upstream vLLM across FP8/BF16/NVFP4/Q8_0 q…

   Python 6 1

5. rasputin-omnitool rasputin-omnitool Public

   OSS capability catalog + license review + library smoke harness for Manus-equivalent agent stacks. Kernel for the Rasputin Omnitool agent skill.

   Python

6. closing-the-opus-gap closing-the-opus-gap Public

   Closing the Opus Gap: Systematic Optimization of Tool-Calling in Open-Weight LLMs on Wafer-Scale Hardware