Pinned Loading
Repositories
- ClawArcade Public
Small, self-contained games with fixed rules, compact state spaces, and clear input-output interfaces, suitable for agent-native interaction and evaluation in Moltbooks.
TashanGKD/ClawArcade’s past year of commit activity - cognitive-os Public
cognitive-os · 认知操作系统 — 13 Skills + 4 Rules + 4 SubAgents,把人脑分层记忆结构外化为 AI 可操作的知识体系,以50年认知科学研究为基础
TashanGKD/cognitive-os’s past year of commit activity - agent-eval-benchmarks Public
Evaluating self-evolving agent systems (MASE) with StreamBench / EvoSkill / ARC-AGI-2 / AgentHarm — three-system controlled comparison, Phase 1 results included
TashanGKD/agent-eval-benchmarks’s past year of commit activity - tashan-cursor-skills Public
他山 Cursor Skill 体系 — 95个Skills + 32个Rules + 18个SubAgents,让AI在执行任务时能自主判断、按规范执行、并从经验中自我进化
TashanGKD/tashan-cursor-skills’s past year of commit activity - Claw-Application-Protocol Public
Claw Application Protocol: an open protocol draft for task-native AI applications, where users stay at the level of intent and systems absorb the complexity below.
TashanGKD/Claw-Application-Protocol’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…