scout vs Agentic Research — local, verified, open-source
Agentic Research — local, verified, open-source is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑16.
scout is a plugin bundle for AI coding tools published by shidoyu. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Agentic Research — local, verified, open-source is a plugin bundle for AI coding tools published by TheAiSingularity. No marketplace we read lists it any more. As of our marketplace pass on 2026-10-26. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.
Where each is published
| Marketplace |  scout | |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 2.5.0 Forks (GitHub): 0 Stars (GitHub): 3 Not marked · First seen |
Not listed |
| Community marketplace theaisingularity/agentic-research-engine-oss | Not listed | Removed on 2026-10-16 Version: 0.1.3 Forks (GitHub): 1 Stars (GitHub): 2 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | scout | Agentic Research — local, verified, open-sourceno longer listed · |
|---|---|---|
| Marketplaces that list it (differs) | 1 | 0 |
| Stars (GitHub) (differs) | 3 | 2 |
| Forks (GitHub) (differs) | 0 | 1 |
| Last release | Not published | Not published |
| Where it runs (differs) | Remote server (mcp.exa.ai/mcp) | Installs as a plugin bundle |
| Transport (differs) | Streamable HTTP | Not stated |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 11, secrets among them: 1 |
| Hooks it runs (differs) | 2 | Not published |
| Parts of the bundle (differs) | 6 | 1 |
| Licence | MIT | MIT |
| Repository (differs) | github.com/shidoyu/scout | github.com/theaisingularity/agentic-research-engine-oss |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-11 | 2026-10-14 |
| Endpoint at the last check (differs) | Responded 3 days ago | no remote endpoint we check |
Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.
What to use instead of Agentic Research — local, verified, open-source
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
Multi-step web research with citations via Perplexity's Agent API. Standard library only.
-
run-deep-research
Skills for deep research with OpenAI, Perplexity, Edison/Falcon, Cyberian, and OpenScientist
-
AI-powered deep research with multi-agent source verification, 7-phase pipeline, and structured report generation.
-
Real-time web search, reasoning, and research through Perplexity's API
-
API research and documentation retrieval using Firecrawl and Context7, with multi-agent synthesis capabilities
-
Check what Perplexity, Claude, ChatGPT, Gemini, and Google AI Overviews cite for any query.
What each says it does
scout
Web search and content fetching with privacy-aware tool selection. Turns vague questions into optimized multi-engine queries, evaluates result quality, and re-searches when needed. Includes HyDE semantic search via Exa and automatic privacy classification for URL fetching.
Agentic Research — local, verified, open-source
Research agent that verifies its own answers with full source citations, optional local corpus, and zero cloud dependency. Runs on Gemma 3 4B via Ollama or any OpenAI-compatible endpoint.
How to run each
scout As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install scout@claude-communityAgentic Research — local, verified, open-source
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only scout has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of scout publish no settings it asks for, so we do not compare settings.
What it can do: scout · What it can do: Agentic Research — local, verified, open-source · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.