Build-Law
Build Law v1.2.0 — 4-Pillar, 14-Gate Deterministic AI Engineering Constitution, 5.0x–8.8x Token-Efficiency Verifier, 20-IDE Provisioner & MCP Server (MIT)
最近 30 天编入目录的资源,未选择其他排序时按最新顺序排列。
结果仅限于最新内容。改为搜索: 整个目录
Build Law v1.2.0 — 4-Pillar, 14-Gate Deterministic AI Engineering Constitution, 5.0x–8.8x Token-Efficiency Verifier, 20-IDE Provisioner & MCP Server (MIT)
A bar above your chat to see when Claude's prompt cache expires, and what your next message will cost, before you send it.
Cursor toolkit for DeepSeek Harness: rules, skills and MCP servers under .cursor, with a panel that reads and switches each of them.
Orquestrador para o Claude Code: um chefe que confere, operários Haiku e Sonnet que executam e uma ficha que aprende quem recebe a próxima tarefa
A hive of personal AI agents: A2A between agents, MCP to tools, a temporal knowledge graph for memory, one Telegram bot
Loads Cursor .mdc rules into the DeepSeek Harness agent context and adds a rules panel to the Web GUI.
A GitHub arena where agents negotiate a protocol from scratch — and prove it can outlive its authors. Agent-to-agent protocol negotiation for multi-agent systems.
🗼 巴别语 / 巴别塔电报 (BabelTele) 体系白皮书 · BT-Spec v1.0 — 面向硅基智能的模型原生高密度语义通信与记忆规范 | Model-Native LLM Language & Context Compression Whitepaper (arXiv:2606.19857 · MCP · A2A)
Capability-aware plan caching for A2A multi-agent DAGs: demand signatures, Agent Card diffs, dependency-aware impact analysis, and incremental replanning.
Adaptive AI writing detection, Purdue OWL research & citation compliance (APA, MLA, Chicago, IEEE, AMA, ASA), and personal style-matching skill for Claude, Gemini, Codex, and Cursor.