~/agentstafferAgentStaffer
Find, trial, compare, and govern AI agents before hiring
Roles / Technical Category
Review matching candidates
Next best action: Open a profile, compare evidence, then run a sandbox trial
Research & Knowledge
Agents for research, retrieval, memory, knowledge bases, RAG, GraphRAG, and long-context synthesis.
4677total
4677filtered
1page
390pages
Category fit
Which technical function should the agent perform?
Filter candidates by capability, protocol, trust, install readiness, and trial status.
- Collect and synthesize source-backed research.
- Build reusable knowledge assets.
- Preserve citations and assumptions for review.
Recommended trials and bundles
playbooks / skill
frontend-design skill by anthropics/skills
This skill helps you design production-grade frontend interfaces with bold aesthetics and polished code for components, pages, and apps.
MCPCLIHTTPSDK
- Fit
- 82 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
- Fit
- 81 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
playbooks / skill
find-docs skill by upstash/context7
This skill retrieves up-to-date documentation and code examples for libraries or tools to ensure accurate, referenceable answers.
MCPHTTPCLISDK
- Fit
- 81 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
github / framework
AntonOsika/gpt-engineer
CLI platform to experiment with codegen. Precursor to: https://lovable.dev
HTTPCLIMCPSDK
- Fit
- 81 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
mcpso / framework
Cline – #1 on OpenRouter
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
MCPCLISDKHTTP
- Fit
- 81 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
github / model
bytedance/UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
MCPHTTPCLISDK
- Fit
- 81 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
mcpservers / skill
security-review
Scan code changes for security vulnerabilities using STRIDE threat modeling, validate findings for exploitability, and output structured results for downstream…
MCPHTTPCLISDK
- Fit
- 81 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
- Fit
- 81 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
- Fit
- 81 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
github / model
ComposioHQ/composio
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
MCPHTTPCLIA2A
- Fit
- 80 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
mcpservers / skill
chatgpt-apps
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools,…
MCPHTTPCLISDK
- Fit
- 80 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
playbooks / skill
vercel-deploy skill by openai/skills
This skill deploys projects to Vercel as previews and provides the deployment URL and claim link for management.
MCPCLIHTTPSDK
- Fit
- 80 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
Review support
Open Category guide
Review links
Technical category pages stay focused on job browsing; complete review records and finalist profile resources stay linked here.
Supporting review linksLinks, review order, and page-specific notes remain available here.
Category guideTechnical role guideAgent inventoryResource mapReview guideAPI referenceSite contextSitemapProfile resources
4677 matching candidates for Research & Knowledge. Open candidate profiles for fit, setup guidance, trust evidence, and sandbox trial planning.
- 01Site contextShared review rules
- 02Role categoryOpen the focused review record
- 03Agent inventoryBrowse the matching inventory
- 04Profile resourcesEvidence, setup, trust, trial, and history files
Use the links and review path below for role-category candidates, related playbooks, and finalist profile resources before action.
Review route: OpenAI review tools can start with openai.json; otherwise use site context and agent inventory before opening the finalist's complete review materials before install, hire, or promotion.