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
129
Δ 7d
+6
Δ 30d
+41
Age
3 mo
Last push
117d ago
90-day star history
Where this sits in the catalog
GroupFrameworks & SDKs
RankingsNot in any top 20 today — see the rankings
Alternatives in Multi-agent orchestration
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first dev…
⭐247.7k
+3,6677d
JavaScript
7 mo
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes…
⭐81.3k
+2717d
Python
1 yr
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, a…
⭐70.4k
+7287d
TypeScript
1 yr
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
⭐70.2k
+1227d
Python
3 yrs
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription.…
⭐61.4k
+4,8957d
TypeScript
5 mo