
cenrax/researchswarm
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
An agentic system that reads research papers (local PDFs or arXiv), generates implementation plans, writes code, and reviews it — all orchestrated by a central Director agent built on the Claude...
概要
An agentic system that reads research papers (local PDFs or arXiv), generates implementation plans, writes code, and reviews it — all orchestrated by a central Director agent built on the . https://drive.google.com/file/d/1_X-twfbmvwykQ3i8JyU2HN_gqcr0T0-S/view?usp=sharing You give the system an (e.g., "Build a transformer text classifier") and . The Director runs a 5-stage pipeline: - Python 3.11+ - Claude Code CLI installed (claude --version) - An Anthropic API key - Docker Desktop (only if using arXiv mode) The system always picks the automatically. The Director provides colored, timestamped logs for every step: Color coding: - — Director messages - — Sub-agent spawns - — Tool calls - — Tool results / successful completions - — Task progress - — Errors The can_use_tool callback in director.py controls what's auto-approved:
README
以下は原文 README の抜粋です。原文を見る。
Research Swarm - Paper-to-Production AI Pipeline
An agentic system that reads research papers (local PDFs or arXiv), generates implementation plans, writes code, and reviews it — all orchestrated by a central Director agent built on the Claude Agent SDK.
Artifacts
Rewrote transformer in C using research swarm
Working video
https://drive.google.com/file/d/1_X-twfbmvwykQ3i8JyU2HN_gqcr0T0-S/view?usp=sharing
Architecture
graph TB
User([User: Objective + Papers]) --> Director
subgraph Orchestration
Director[Director AgentOpus - Orchestrator]
end
subgraph "Stage 1: Read"
Director -->|local files| PaperReader[Paper ReaderSonnet]
Director -->|arXiv IDs| ArxivReader[ArXiv ReaderSonnet + MCP]
end
subgraph "Stage 2: Plan"
Director --> Planner[PlannerOpus]
end
subgraph "Stage 3: Code"
Director --> Coder[CoderOpus + Sandbox]
end
subgraph "Stage 4: Review"
Director --> Reviewer[ReviewerSonnet]
end
PaperReader -->|summaries| Approval1{User Approval}
ArxivReader -->|summaries| Approval1
Approval1 --> Planner
Planner -->|plan| Approval2{User Approval}
Approval2 --> Coder
Coder -->|code| Approval3{User Approval}
Approval3 --> Reviewer
Reviewer -->|review| Approval4{User Approval}
Approval4 --> Deliver([Final Delivery])
style Director fill:#6366f1,color:#fff
style PaperReader fill:#06b6d4,color:#fff
style ArxivReader fill:#06b6d4,color:#fff
style Planner fill:#8b5cf6,color:#fff
style Coder fill:#8b5cf6,color:#fff
style Reviewer fill:#06b6d4,color:#fff
style Approval1 fill:#f59e0b,color:#000
style Approval2 fill:#f59e0b,color:#000
style Approval3 fill:#f59e0b,color:#000
style Approval4 fill:#f59e0b,color:#000
Pipeline
sequenceDiagram
participant U as User
participant D as Director
participant R as Paper Reader
participant P as Planner
participant C as Coder
participant V as Reviewer
U->>D: Objective + Papers (PDF/MD or arXiv IDs)
D->>R: Read & summarize papers
R-->>D: output/summaries/
D->>U: Here's what I found. Proceed?
U->>D: Yes, focus on technique X
D->>P: Create implementation plan
P-->>D: output/plans/plan.md
D->>U: Here's the plan. Approve?
U->>D: Approved
D->>C: Implement the plan
C->>C: Write code + sandbox test each module
C-->>D: output/code/
D->>U: Code ready. Review?
U->>D: Yes
D->>V: Review code vs paper
V-->>D: output/reviews/review.md
D->>U: Review: PASS (score 8/10)
How It Works
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add cenrax/researchswarm