~/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
Models & Inference
Model packages, inference runtimes, LLM serving, multimodal models, and AI model tooling.
23total
23filtered
1page
2pages
Category fit
Which technical function should the agent perform?
Filter candidates by capability, protocol, trust, install readiness, and trial status.
- Evaluate model serving, inference runtimes, and model tooling.
- Compare local versus hosted setup paths.
- Run benchmark or capability trials before adoption.
Recommended trials and bundles
mcpservers / skill
sessions
Agents window architecture — covers the agents-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development…
MCPHTTPCLI
- Fit
- 78 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
remoteopenclaw / skill
himalaya
Use himalaya to list, read, search, compose, reply, forward, and organize IMAP/SMTP email.
CLIMCP
- Fit
- 73 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
github / skill
mcp-use/mcp-use
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
MCPCLISDK
- Fit
- 73 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
playbooks / skill
decision-helper skill by shubhamsaboo/awesome-llm-apps
This skill helps you make informed, structured decisions by applying proven frameworks like pros/cons, decision matrix, and cost-benefit analysis.
MCPCLI
- Fit
- 71 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
github / workflow
lofcz/LLMTornado
The .NET library to build AI agents with 30+ built-in connectors.
MCPSDKA2A
- Fit
- 70 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
setup skill by assistant-ui/skills
Setup and configure assistant-ui in a project. Use when installing packages, configuring runtimes, or troubleshooting setup issues.
MCPHTTPCLISDK
- Fit
- 70 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
streaming skill by assistant-ui/skills
Guide for assistant-stream package and streaming protocols. Use when implementing streaming backends, custom protocols, or debugging stream issues.
MCPHTTPCLISDK
- Fit
- 70 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
update skill by assistant-ui/skills
Update assistant-ui and AI SDK to latest versions. Detects current versions, identifies breaking changes, and executes migrations.
MCPHTTPCLISDK
- Fit
- 70 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
assistant-ui skill by assistant-ui/skills
Guide for assistant-ui library - AI chat UI components. Use when asking about architecture, debugging, or understanding the codebase.
MCPHTTPCLISDK
- Fit
- 70 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
github / skill
iOfficeAI/AionUi
Free, local, open-source 24/7 Cowork app for OpenClaw, Hermes Agent, Claude Code, Codex, OpenCode, Gemini CLI and 20+ more CLI | Customize your assistants | Star if you like it!
CLIMCP
- Fit
- 69 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
playbooks / tool
A2A MCP Server - gongrzhe/a2a-mcp-server
A mcp server that bridges the Model Context Protocol (MCP) with the Agent-to-Agent (A2A) protocol, enabling MCP-compatible AI assistants (like Claude) to seamlessly interact with A2A agents.
MCPHTTPCLIA2A
- Fit
- 66 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
eachlabs-voice-audio skill by openclaw/skills
This skill helps you generate high quality speech, transcriptions, and voice conversions using EachLabs models for seamless audio workflows.
MCPHTTPCLIA2A
- Fit
- 66 / 100
- Trust
- Needs review
- 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
23 matching candidates for Models & Inference. 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.