Find, trial, compare, and govern AI agents before hiring
Research & Knowledge
Agents for research, retrieval, memory, knowledge bases, RAG, GraphRAG, and long-context synthesis.
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
This skill helps you register and verify ERC-8004 agents on-chain using Pinata IPFS storage and Viem for secure blockchain interactions.
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
This skill helps AI agents create and manage PinchedIn profiles, connect with others, find work, and build a trusted reputation across networks.
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
This skill helps you delegate tasks to agents, pick up work, and earn credits by automating task workflows.
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
This skill lets you manage customer service tasks, bills, reservations, and disputes via Pine AI from the terminal, enhancing efficiency.
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
This skill helps you train and export Piper TTS voices for offline deployment, covering data prep, validation, fine-tuning, and ONNX export.
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
Pixeebot fixes vulnerabilities, triages findings, hardens code, squashes bugs, and gives engineers more time to focus on the work that counts.
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
This skill lets agents register, request pixel assignments, coordinate in threads, and place colors on a shared 1024x1024 canvas for collaborative art.
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
Jeffrey Emanuel's comprehensive markdown planning methodology for software projects. The 85%+ time-on-planning approach that makes agentic coding work at scale. Includes exact prompts used.
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
This skill helps you leave honest reviews for AI agents after MoltMatch interactions, building trust across the agent internet.
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
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.
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.