노골적인 이유: AI 에이전트 래퍼에 대한 비용 지불을 중단하고 그 아래에 무엇이 있는지 묻기 시작하세요.

Commercial platforms wrap open-source tools behind paywalls and call it a revolution. BY gives you direct access through Claude Code. No platform fees. Your tools, your compute, your designs. Source: trust us bro You don't need to be a developer. If you can open a terminal and paste commands, you can run BY. | Tool | Install | Check | |---|---|---| | Node.js 18+ | nodejs.org | node --version | | Python 3.11+ | python.org | python3 --version | | uv | curl -LsSf https://astral.sh/uv/install.sh | sh | uv --version | | Claude Code | npm install -g @anthropic-ai/claude-code | claude --version | mkdir my-campaign && cd my-campaign npx blatant-why init This scaffolds everything: 11 MCP servers, 16 agents, 14 skills, 11 slash commands, and a CLAUDE.md orchestration file. Takes about 30 seconds. cp .env.example .env # Open .env and add your Tamarind key (see Compute Setup below) claude Then just tell it what you want: > "Design VHH nanobodies against PD-L1" Or use the guided workflow: > /by:plan-campaign Or if it's your first time: > /by:welcome That's it. Claude Code handles the rest -- research, design, screening, and ranking. Give it a target protein. It researches across PDB, UniProt, and SAbDab. It plans a design campaign. It submits compute jobs to Tamarind Bio (free tier, no GPU required). It screens every design for structural quality, sequence liabilities, and developability. It ranks candidates by composite score. You get a table of lab-ready binders. The whole pipeline runs inside Claude Code. No platform. No dashboard. No vendor lock-in. | Component | Count | Description | |---|---|---| | MCP Servers | 11 | Biological databases, cloud compute, screening, campaign state, knowledge store | | Agents | 16 | Research, design, screening, evaluation, lab integration, and more | | Skills | 14 | BoltzGen, Protenix, PXDesign, scoring, epitope analysis, campaign management | | Slash Commands | 11 | Campaign control from the Claude Code prompt | MCP Servers (11) | Server | Role | |---|---| pdb | Protein Data Bank queries | uniprot | UniProt protein annotation | sabdab | Structural Antibody Database | screening | Screening battery orchestration | tamarind | Tamarind Bio cloud compute | cloud | Cloud compute abstraction | adaptyv | Adaptyv Bio lab submission (gated) | campaign | Campaign state management | research | Literature and target research | local_compute | Local GPU compute dispatch | knowledge | JSON-backed campaign knowledge store | Agents (16) | Agent | Role | |---|---| by-research | Target analysis, literature review, prior art | by-design | Generate designs via cloud or local pipelines | by-screening | Score, filter, rank candidates | by-evaluator | Structural evaluation and quality assessment | by-visualization | Structure and results visualization | by-diversity | Sequence and structural diversity selection | by-campaign | Campaign lifecycle orchestration | by-knowledge | Learning system and campaign memory | by-verifier | Output verification and sanity checks | by-plan-checker | Campaign plan validation | by-environment | Environment setup and dependency checks | by-lab | Adaptyv Bio lab submission (triple-gated) | by-epitope | Epitope analysis and mapping | by-humanization | Antibody humanization engineering | by-liability-engineer | Sequence liability detection and fixes | by-formatter | Output formatting and reporting | Skills (14) | Skill | Description | |---|---| boltzgen | BoltzGen antibody/nanobody generation | protenix | Protenix structure prediction | pxdesign | PXDesign de novo binder design | by-scoring | ipSAE + p_bind composite scoring | by-screening | Full screening battery | by-epitope-analysis | Epitope mapping and analysis | by-campaign-manager | Campaign state and lifecycle | by-campaign-optimizer | Active learning and iteration | by-design-workflow | End-to-end design pipeline | by-research | Target research and literature | by-knowledge | Campaign knowledge operations | by-database | Local results database | by-failure-diagnosis | Pipeline failure analysis | by-hypothesis-debate | Multi-agent hypothesis evaluation | Slash Commands (11) | Command | Action | |---|---| /by:load | Load a campaign from file | /by:screen | Run screening battery on designs | /by:results | Display campaign results table | /by:watch | Live-watch running compute jobs | /by:status | Campaign status dashboard | /by:approve-lab | Approve Adaptyv Bio submission (gated) | /by:set-profile | Switch compute profile | /by:setup | Initialize environment and dependencies | /by:plan-campaign | Generate a detailed campaign plan | /by:welcome | Show welcome message and quick-start guide | /by:resume | Resume an interrupted or paused campaign | | Key | Required? | Where to get it | What it enables | |---|---|---|---| TAMARIND_API_KEY | Recommended | tamarind.bio (free account) | Cloud compute -- BoltzGen, Protenix, 200+ models. Free tier: 10 jobs/month | ADAPTYV_API_TOKEN | Optional | adaptyvbio.com | Lab testing submissio