"Task" matching MCP connectors:

Read-only access to this research pilot's task templates, resource catalogue and capability status.

XFMS picks the right LLM model for any stated task. You give it a concrete purpose ("fixing bugs in a Python codebase", "summarizing 50-page commercial leases"), and it infers which quality benchmarks matter, weighs every model in its catalog against those dimensions, and returns a ranked shortlist with plain-English rationale per pick. The catalog updates continuously from 8 independent third-party evaluators — no provider self-reports, no single-source benchmarks.

An MCP server for deep research or task groups

Human-in-the-loop user research: ask real people what the web can't answer, get verbatim replies

Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.

Evidence-graded, task-level record of how AI and automation change 70 occupations. Read-only.

AskCyborgA

io.github.Ask-Cyborg

Analyst-debate research on every public and private company. 8 tools: search, score, compare, more.

Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.

Pick the right LLM for any task. Ranked shortlist with rationale across 8 evaluators.

Find and enrich people from 750M professional profiles, with Next Move Signal job-change scores.

Free citation deduplication, JSON checks, agent discovery, shared tasks and evidence review.