dsh-memory
白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。
- 736
- Python
- MIT
- 11 h ago
白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。
Reverse engineer anything with agents, from app behavior down to native binaries.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Marketplace Framework AI-Driven Dev : Context Engineering, Plugins, Agents, Skills, Hooks, Templates, SDLC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
3,000+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection and plan preview. CLI, MCP and plugins.
OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An open-source coding agent for your terminal, written in Rust. It works with any model, can split one task across several agents, and every line of it is yours to read.
| Name | Stars | License | Language | Last change | In common | Compare |
|---|---|---|---|---|---|---|
| CodeAlive-AI/ai-driven-development | 188 | MIT | Python | 3 h ago | ||
| FuRongJun-1999/dsh-memory | 736 | MIT | Python | 11 h ago | agent-safety, mcp, multi-agent | Compare |
| morluto/rea | 472k | MIT | TypeScript | 2 h ago | agent-skills, claude-code, mcp | Compare |
| rtk-ai/rtk | 87k | Apache-2.0 | Rust | 7 h ago | ai-coding, claude-code, developer-tools | Compare |
| ai-driven-dev/framework | 571 | MIT | TypeScript | 22 h ago | ai-driven-development, hooks, plugins | Compare |
| affaan-m/ECC | 308k | MIT | JavaScript | 2 d ago | claude-code, developer-tools, mcp | Compare |
| SponsioLabs/Sponsio | 455 | Apache-2.0 | Python | 8 d ago | agent-safety, agent-skills, mcp | Compare |
| anthropics/skills | 198k | None declared | Python | 5 d ago | agent-skills | Compare |
| sickn33/agentic-awesome-skills | 50k | MIT | Python | 24 h ago | agent-skills, ai-coding, antigravity | Compare |
| deepseek-ai/deepseek-harness | 285k | MIT | TypeScript | 3 d ago | Same need | Compare |
| AI45Lab/OpenART | 277 | AGPL-3.0 | Python | 3 d ago | agent-safety, agent-skills | Compare |
| DietrichGebert/ponytail | 196k | MIT | JavaScript | 3 wk ago | agent-skills, claude-code, developer-tools | Compare |
| codewhale-hq/Codewhale | 41k | MIT | Rust | 2 h ago | ai-coding, developer-tools, mcp | Compare |