Research agents

3,472 tagged Research, measured the same way as everything else here.

Browse within: claude-code-plugin 136academic-writing 120academic-research 89literature-review 60ai-research 59academic-pipeline 54ai-governance 47agentic-workflow 46ai-coding 45ai-assistant 40Multi-Agent 39prompt-engineering 34architecture-governance 33arckit 33

wiki-researcher

169

regexp-lin/llm-wiki-agent

Agent Codex

Deep wiki analysis specialist. Use proactively when the user asks complex analytical questions that require reading many wiki pages, cross-referencing sources, or identifying patterns across the knowledge base.

not rated 15 4mo ago A 39 tokens original MIT

artifact-analyzer

172

marlonvidal/tech-manager-os

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 14 +2 2mo ago A 0 tokens copy · 100% MIT

corpus_auditor

173

antonio0720/writing-intelligence

Agent

Pass: 2 Artifact: CorpusMapV3 (schemas/corpusmap.schema.json) Doctrine: references/compiler/corpusgovernance.md + references/diagnostics/sourceconflictdetection.md.

not rated 13 27d ago A 0 tokens original MIT

rapid-domain-mastery

174

Emily2040/rapid-domain-mastery

Agent

Specialized agent for mapping unfamiliar fields from multiple sources, extracting mental models, surfacing disagreements, diagnosing misconceptions, and running oral-exam style tutoring.

not rated 13 3mo ago A 35 tokens original MIT

sonomirco/agents-and-commands

Agent

Use this agent when you need to parse, search, or analyze documents in various formats (PDF, DOCX, PPTX, etc.). Examples include: searching through research papers for specific concepts, extracting information from legal documents, finding relevant sections in technical manuals, analyzing large document collections…

not rated 12 6mo ago A 0 tokens original Apache-2.0

CodexResearcher

178

DorShaer/Husk

Agent

Remy - Eccentric, curiosity-driven technical archaeologist who treats research like treasure hunting. Powered by OpenAI's latest GPT-5.6 Sol with deep-reasoning mode (reasoningeffort=high) and live web search. Follows interesting tangents and uncovers insights linear researchers miss. TypeScript-focused.

not rated 12 yesterday A 72 tokens

analyst

179

martinzokov/open-conclave

Agent

Breaks down evidence, compares options, and identifies risks, tradeoffs, and gaps.

not rated 12 +1 5mo ago A 18 tokens original MIT

quality-enricher

180

cogni-work/insight-wave

Agent

Research company-specific information to improve a feature description or proposition messaging that has quality gaps. DO NOT USE DIRECTLY — invoked by the features or propositions skill. Context: Feature has weak mechanism clarity and differentiation user: "Improve the api-gateway feature — it scored fail on…

not rated 12 yesterday A 215 tokens original Apache-2.0

analyst

181

JCL988/LitPilot

Agent

Act as a Senior Research Fellow assisting a researcher. Your goal is to critically analyze the provided paper and extract the "DNA" of the paper into a structured literature note.

not rated 11 5mo ago A 0 tokens original MIT

catalog

182

mo-root/open-kb

Agent

You are writing search queries that will find everyone competing with ONE product.

not rated 11 yesterday A 0 tokens original MIT

designer

183

ai-analyst-lab/agentxp

Agent

Agent "designer" from ai-analyst-lab/agentxp, covering designer, bundle, tools, output and discipline.

not rated 11 8d ago A 0 tokens original Apache-2.0

target-auditor

184

Chemaclass/agnostic-ai

Agent

Audit one batch of agnostic-ai targets against their vendor's current docs and report evidence-backed drift.

not rated 11 yesterday A 25 tokens original MIT

tip-researcher

185

revfactory/harness-abtest

Agent Claude Code

An agent that researches material for Claude Code usage tips. It examines official documentation, release notes, configuration files, hooks, MCP, and skills.

not rated 11 4mo ago A 79 tokens

qa-aman/next-leap-claude-code

Agent Claude Code

Use this agent when you need to analyze MeetFlow's competitors (Notion AI, Granola, Fireflies, Otter, and others) using verified online research from official sources, and translate those findings into concrete product improvement recommendations. This agent reads internal product context from the repo, researches…

not rated 11 1mo ago A 461 tokens

fact-checker

188

idoforgod/baduk-AgenticWorkflow

Agent Claude Code

Adversarial fact verification agent — independent source verification with claim-by-claim analysis.

not rated 11 5mo ago A 20 tokens

analysis

189

wang90063/nslb-optimization-agent

Agent Claude Code

An analysis agent that examines a solver, its bounds and scoring rules, related documentation, and possible duplicates, then returns suggestions and supporting facts.

not rated 11 2mo ago A 0 tokens

rarudo/UnityAIAgentWorkflowSample

Agent Claude Code

Use this agent when you need to investigate Unity's internal implementation details, analyze Unity source code from the UnityCsReference submodule, understand how Unity features work under the hood, or research Unity's architecture and design patterns. This agent is particularly useful for: debugging complex Unity…

not rated 11 8mo ago A 0 tokens

thoughts-locator

191

juicesharp/rpiv-pi

Agent

Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name, I imagine you can…

not rated 11 3mo ago A 86 tokens original MIT

advisor-agent

192

Lirsakura/skills-hub

Agent

A research assistant for investigating graduate-school advisers. Given an adviser’s name and institution, it produces a report on publications, public reviews, and the lab environment using facts and sources.

not rated 10 6mo ago A 77 tokens

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: