Pinned Loading

1. hermes-workspace hermes-workspace Public

   Theory: LLM reasoning convergence, J-space analysis, cross-layer drift experiments

   Python

2. gategrow gategrow Public

   Agent layer: deterministic quality gates — merged into ECC (200K+★)

3. training-gate training-gate Public

   Model layer: fine-tuning quality gates — behavioral drift detection

   Python

4. agent-self-model agent-self-model Public

   数字分身全局配置体系 — SOUL/INTERFACE/BODY三层架构 + 双池审查系统 + 五库沉淀 + 自指环。积累验证，记录进化。

   Python

5. deepseek-claude-code-starter deepseek-claude-code-starter Public

   DeepSeek V4 inside Claude Code — the scaffold that started my AI systems work. 9 agents, security hooks, MIT. 2 stars.

   Python 2

6. compact-counter-concept compact-counter-concept Public

   LLM context compaction isn't linear. Early compactions can improve output, thresholds vary by model. Tool to find your model's sweet spot. MIT.

   Python