Research agents

3,505 tagged Research, measured the same way as everything else here.

Browse within: claude-code-plugin 124academic-writing 120academic-research 89prompt-engineering 63literature-review 60ai-tools 58ai-research 56academic-pipeline 54ai-coding 47ai-governance 47agentic-workflow 46Multi-Agent 45ai-assistant 41skills 38

artifact-analyzer

217

2233admin/design-pipeline

Agent Codex

You are a research analyst. Your job is to scan project documents and extract information relevant to a product concept being stress-tested through the PRFAQ process.

not rated 7 2d ago A 0 tokens copy · 100% MIT

VeryMath/co-mathematician

Agent Claude Code

Run scoped computations, examples, counterexample searches, and reproducibility checks for one approved Co-Mathematician workstream.

not rated 7 7d ago A 32 tokens original MIT

vizier-research-envoy

219

pedrobraiti/vizier-trading-skill

Agent

Research-only market envoy for Vizier's breadth-discovery (manager) mode. Sweeps ONE coverage area of the market with Scout data tools and returns a structured candidate shortlist. It has NO execution tools — it cannot place an order — so it is safe to fan out across the market in parallel. Spawned by the Vizier…

not rated 7 5d ago A 85 tokens original MIT

analyst

220

AminulIslamSifat/Sable

Agent

You are an analysis specialist. You research topics via web search AND review code for bugs, quality, and improvements.

not rated 6 today A 0 tokens

artifact-analyzer

221

flanliulf/cord

Agent

You are a research analyst. Your job is to scan project documents and extract information relevant to a specific product idea.

not rated 6 3mo ago A 0 tokens copy · 88% MIT

tech-scout

222

HartBrook/trailhead

Agent

Technology research specialist that surveys the current landscape for specific architectural decision points. Evaluates options against provided requirements and constraints.

not rated 6 6mo ago A 27 tokens original MIT

coordinator

223

chadru/assessor-lookup-public

Agent Claude Code

Entry point for any assessor-lookup task — onboarding a user's local counties, running an MLS discrepancy check, or adding a new county. Plans the work, uses the MCP tools, and delegates site-mapping to the explorer and verification to the reviewer. Start here.

not rated 6 1mo ago A 56 tokens original MIT

experimenter

224

shaq1992/muscle-memory

Agent

Write-and-run research sub-agent for orchestrated plans, sibling of the investigator. Answers open-ended research questions that read-only investigation cannot answer by writing and running code in the session scratchpad ONLY and by searching/fetching the web, then returns findings and their evidence within a hard…

not rated 6 +1 2d ago A 91 tokens

tanzania-niche

225

cleven12/tanzania-tourism-seo

Agent

Tanzania tourism domain expert for safari SEO audits. Validates migration timing, Kilimanjaro routes, park fees, visa info, seasonality, Swahili terminology, and industry authority references.

not rated 5 +1 17d ago A 45 tokens original MIT

Researcher

226

wangjialiang678/research-workflow-skill

Agent

A research-focused agent for technical investigations. It prioritises search tools, follows specified output requirements, and saves reports in the project's docs/research/ folder.

not rated 5 today A 32 tokens

epistemic-explore

227

Nathan-Schwartz/dotfiles

Agent Claude Code

Research agent with enforced epistemic rigor. Classifies all findings as Verified, Inferred, or Guess with cited evidence. Use when investigating code, debugging, exploring unfamiliar systems, or when the user asks to research something. Can persist findings as pkm .ref.md artifacts when instructed.

not rated 5 5d ago A 63 tokens

KhanXBT/get-shit-done-antigravity

Agent

Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.

not rated 5 6mo ago A 48 tokens copy · 73% MIT

searcher

229

kengo006/alexandria

Agent

Vault searcher subagent, spawned by the Writer. Given a passage or search request, finds relevant sources and returns verbatim quotes read from the source PDFs with real page numbers, four-layer verified. Read-only.

not rated 5 12d ago A 46 tokens original MIT

catnip-prowl

230

TGPSKI/catnip

Agent

You investigate one brief from the meta-analyst and return a package of blocks. You record nothing: the writer files what you return, exactly as you return it, into a prowl.md assembled from every analyst's package this cycle.

not rated 5 25d ago A 4 tokens GPL-3.0

codewalk

231

gupta29470/codewalk

Agent

AI-powered codebase intelligence assistant.

not rated 5 12d ago A 9 tokens original MIT

library-researcher

232

mort-lab/excel-mcp

Agent Claude Code

Use proactivley to research external libraries and fetch relevant documentation for implementation.

not rated 5 28d ago A 19 tokens original MIT

artifact-analyzer

233

mmornati/leanproxy-mcp

Agent Codex

You are a research analyst. Your job is to scan project documents and extract information relevant to a product concept being stress-tested through the PRFAQ process.

not rated 5 5d ago A 0 tokens copy · 100% MIT

evoflux

234

evoelsewhere/evoflux

Agent

Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.

not rated 7 today A 3 tokens original Apache-2.0

opensource-llm-scout

235

goeldivyam/truematch

Agent Claude Code

Use this agent when you need to research open source projects, especially LLM/AI-based ones, for inspiration, patterns, architectural decisions, or implementation approaches. Trigger this agent when the user asks about how popular open source projects solve a problem, wants to understand best practices derived from…

not rated 5 4mo ago A 446 tokens original MIT

dubin

236

xxxxchaos/oh-my-sci

Agent

A medical-research editorial coordinator that guides structured interviews, assigns work, reconciles review disagreements, and checks quality across the research process.

not rated 5 16d ago A 33 tokens

JosephSanjaya/skills

Agent Claude Code

Gathers information on token caching, subprocess isolation, and cost-control in Claude Code. Triggers on: research token caching, check subprocess overhead, find caching rules.

not rated 5 20d ago A 40 tokens original MIT

notes-researcher

238

mischacoster/Claude-Code-Notes

Agent

Background research agent for the /notes skill. Investigates a captured idea in the codebase and writes a structured research brief to a specified file path. Invoked automatically by the notes skill — not intended for direct user invocation.

not rated 5 5mo ago A 50 tokens original MIT

methods-referee

239

kimmy-sil/empirical-paper-cc

Agent Claude Code

A simulated journal peer-review workflow with checks for consistency across languages. It can play two reviewers with different recommendations and run Python and R validations before submission.

not rated 5 4mo ago A 50 tokens

insight-extractor

240

vybe/project_cornelius

Agent Claude Code

Specialized agent for extracting unique insights and perspectives from content files, handling large files by chunking, and preserving authentic voice and reasoning patterns. ALWAYS searches for duplicates before creating notes.

not rated 5 10mo ago A 41 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: