qiqihezh/deepresearch-agent
一个生产级的深度研究 Agent 系统，从零构建多智能体编排、Red-Blue 对抗降噪、 语义级上下文压缩、跨 Agent 共享记忆四大核心能力，配套 165 次独立实验 + Bootstrap 统计显著性检验的完整评测体系。
View on GitHub →Pythonadversarial-trainingasynciodeep-researchllm-agentllm-evaluation
Stars
46
Δ 7d
—
Δ 30d
—
Age
2 mo
Last push
67d ago
90-day star history
Alternatives in Multi-agent orchestration
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first dev…
⭐230.5k
JavaScript
6 mo
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes…
⭐77.3k
Python
1 yr
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
⭐69.4k
Python
3 yrs
🌊 The leading agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, an…
⭐64.7k
TypeScript
1 yr