Coding Review
Review a diff or file for bugs, risky paths, and missing tests — without auto-committing or running destructive commands.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamLibrary · Teams
Pick a job, see Verified / Untested counts, then choose a runtime implementation.
10 Teams · 70 implementations · Verified 3 · Untested 67 · Marketplace product pages stay separate.
Source on GitHub · registry.json
An AI Team is a group of AI agents, tools, or workflows organized to complete a job together. On BotShelf, each canonical AI Team is one job concept with multiple runtime implementations — not seventy separate Teams.
Frameworks and architectures use related labels. An AI Team may also show up as an AI agent team, agent team, multi-agent system, or multi-agent workflow when that architecture fits. Broader phrases like agentic workflow, agent orchestration, or AI workflow help discovery; they are related concepts, not automatic synonyms of AI Team.
Terminology varies by runtime. A CrewAI sketch can honestly be a multi-agent system; an Ollama prompt pack is usually a local AI agent / local workflow for the same Team job. We do not collapse Skills, Prompts, MCP packs, or marketplace Team product pages into this entity.
Review a diff or file for bugs, risky paths, and missing tests — without auto-committing or running destructive commands.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamSummarize pasted tables or CSV snippets into findings, caveats, and what to check next. Analysis only.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamTurn a fuzzy question into a sourced research brief with open questions and next checks — not a final verdict.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamReview docs for clarity, broken promises, and missing prerequisites before publish.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamBuild a respectful lead brief from public facts you paste — no scraping secrets, no spam scripts.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamTurn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamDaily capture → prioritized plan with stop rules. Local-first; does not spend money or send mail alone.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamProduce a one-page SEO brief (intent, title options, outline, risks) from a keyword and URL context.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamClassify an inbound message, propose a first reply hold, and flag escalation — human sends.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open teamDraft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics.
7 implementations · crewai, langgraph, lm-studio, mcp, n8n, ollama, open-webui
Open team