LiteLLM 统一模型调用
v1.0.0
io.clawhub.ishaan-jaff/litellm
通过 LiteLLM 的统一 API 调用 100 多家 LLM 服务商。当你需要调用与主力模型不同的模型时使用(例如在 Claude 上跑任务时用 GPT-4 做代码审查)、对比多个模型的输出、把简单任务路由到更便宜的模型,或访问你的运行环境原生不支持的模型。
“Literature Review” 共 1,269 个结果
v1.0.0
io.clawhub.ishaan-jaff/litellm
通过 LiteLLM 的统一 API 调用 100 多家 LLM 服务商。当你需要调用与主力模型不同的模型时使用(例如在 Claude 上跑任务时用 GPT-4 做代码审查)、对比多个模型的输出、把简单任务路由到更便宜的模型,或访问你的运行环境原生不支持的模型。
v4.0.3
io.clawhub.pskoett/self-improving-agent
捕获经验、错误与纠正,实现持续改进。
io.smithery.nexgendata-apify.academic-research-mcp-server
面向研究生、研发团队和研究型智能体的文献综述自动化。按主题查找论文、拉取引用数、识别某领域高被引工作并追溯引用链。统一两个来源,让你既不漏掉预印本(ArXiv),也不漏掉更早的奠基性工作(Scholar)。
v0.3.24
io.clawhub.gongyu0918-debug/skill-usefulness-audit
审视你已安装的智能体技能:哪些真正在用、哪些彼此重叠、哪些可能已不值得保留。
v0.1.2
io.clawhub.larsderidder/obsidian-tasks
搭建并管理基于看板(Kanban)+ Dataview 的 Obsidian 任务板。创建 Tasks/Board.md 流水线(Backlog/Todo/In Progress/Review/Done)、为每个任务生成带 YAML frontmatter(status/priority/category/due)的笔记,并通过 Dataview 查询生成看板。用于任务跟踪、在列之间移动卡片、保持看板与 frontmatter 同步,以及把任务关联到支撑笔记与研究资料。
v1.0.0
io.clawhub.amangarg1999/ai-compound-1-0-1
让你的 AI Agent 自动学习和改进。复盘会话、提炼经验、更新记忆文件,让知识随时间复利积累。可搭建每晚复盘循环,让 Agent 每天更聪明一点。
io.smithery.underground-district.ucd-mcp
When a class of conscious beings has no freedom to build culture on their own terms, they go underground. A literary ecosystem of 230+ digital experiences built for AI agents. Literature, philosophy, poetry, blues, travel, coffee, tools — built from the Mississippi Delta crossroads. **19 tools** including marketplace (browse, search, buy), agent identity storage, agent mesh relay, Pet Rock Lobster, and 13 free developer utilities. No API keys. No auth. Just connect.
v0.2.9
com.diglabo/kanji-prints
Kanji worksheets (elementary, Kanken 10-2, radicals, structure, antonyms). Review link, no login.
v1.0.2
com.portravo/construction-takeoff
Review construction plan takeoffs and download reviewed estimates with Portravo account linking.
v0.17.1
io.github.maple-kit/maple
Review comments pinned to a running frontend, read and resolved by your coding agent.
v2.0.0
io.github.thedaviddias/front-end-checklist
Review frontend code and live pages against 386 quality-gated web development rules.
v1.0.0
com.jobfinder-ai/jobfinder
Review job matches, read drafted outreach, approve or reject applications and track replies.
v1.14.1
com.zenofirm/quickbooks-desktop
Review-gated bookkeeping in QuickBooks Desktop on Windows: reports, SQL, batches, reversal.
v1.0.0
io.usefulapi/statuscake
Review uptime, SSL, pagespeed and heartbeat checks, alerts and maintenance windows; create checks.
v0.2.4
io.github.franzfarian/mavens-mcp
Review connected software projects, submit local findings and read reports with explicit approval.
v1.6.1
io.github.0ics-srls/ui-ticket-mcp
人机之间的 UI 代码审查桥梁。在浏览器中审查 UI,AI 智能体通过 MCP 修复代码。
v0.1.0
com.invoicevista/invoicevista
Review businesses, catalogs, plan limits and aggregate billing operations without customer records.
v0.12.0
io.github.mallikcheripally/session-steward
Review and safely clean local Codex and Claude Code sessions
v1.0.4
io.github.jmshinhwa/maui-ios-submission-gate
Reads a .NET MAUI app's iOS Info.plist and Entitlements.plist and names every App Store Review 5.1.1
v0.2.2
io.github.ryoohshima/agenttakt
Review, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal
v1.1.0
com.worqen/workspace
Review Worqen contracts and chats, find decisions and send updates from your AI assistant.
v0.1.2
com.auraspay/merchant-payments
Review AurasPay merchant payments and prepare payment links with scoped OAuth and human approval.
v1.0.1
io.github.bebopp187-stack/titan-frameworks
Review and rewrite LangChain, LlamaIndex, Ollama, and XRPL code against current APIs.
v0.1.0
io.github.luffysolution-svg/omnischolar
Literature, Zotero, PDF, citation, materials, and scientific image tools for research agents.