Research agents

5,296 tagged Research, measured the same way as everything else here.

Browse within: academic-writing 101literature-review 59academic-research 54ai-research 54academic-pipeline 49ai-coding 46ai-assistant 42agentic-workflow 41Multi-Agent 35knowledge-graph 34agent-orchestration 33agentic-coding 33claude-code-skills 31opencode 31

wiki-ingest

25

AgriciDaniel/claude-obsidian

Agent

Part of claude-obsidian

Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.

15k +149 7d ago A 53 tokens original MIT

research

26

mindfold-ai/Trellis

Agent

Code and tech search expert. Finds patterns, specs, and tech solutions. Populates task JSONL context files.

14k +56 7d ago A 25 tokens AGPL-3.0

open-gsd/gsd-core

Agent

Part of gsd-core

Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.

9.0k +90 yesterday A 41 tokens original MIT

researcher

30

companion-inc/feynman

Agent

Gather primary evidence across papers, web sources, repos, docs, and local artifacts.

8.7k +33 7d ago A 20 tokens original MIT

reviewer

31

companion-inc/feynman

Agent

Run tough but constructive internal research critique of an AI research artifact.

8.7k +33 7d ago A 16 tokens original MIT

writer

32

companion-inc/feynman

Agent

Turn research notes into clear, structured briefs and drafts.

8.7k +33 7d ago A 13 tokens original MIT

fact-checker

33

digoal/blog

Agent

A prompt template for a fact-checking assistant from a Chinese blog project. It includes instructions for the assistant, explanations of placeholders, and a reusable prompt structure.

8.6k +2 yesterday A 0 tokens GPL-2.0

sage

34

tailcallhq/forgecode

Agent

DEEP RESEARCH ONLY. Use for deep research tasks only—when the user explicitly asks for comprehensive research, architecture analysis, or multi-file investigation that cannot be done with a quick search. Do NOT use for simple lookups or finding where something is defined. Research-only tool for systematic codebase…

7.6k +9 2d ago A 194 tokens original Apache-2.0

chakra-ui/ark

Agent Claude Code

Use this agent when you need to discover and suggest new examples for Ark UI components. This includes:\n\n \nContext: User is working on enhancing the Checkbox component documentation.\nuser: "I've just finished updating the Checkbox component API. Can you help me find what examples we should add?"\nassistant: "I'll…

5.4k +2 2d ago A 0 tokens original MIT

literature-reviewer

38

Galaxy-Dawn/claude-scholar

Agent

Part of claude-scholar

Use this agent when the user asks to "conduct literature review", "search for papers", "analyze research papers", "identify research gaps", "review related work", or mentions starting a research project. This agent integrates with Zotero for automated paper collection, organization, and full-text analysis. Examples.

5.3k +37 7d ago A 0 tokens original MIT

paper-miner

39

Galaxy-Dawn/claude-scholar

Agent

Part of claude-scholar

Use this agent when the user provides a research paper (PDF/DOCX/arXiv link) or asks to learn writing patterns from papers, extract venue-specific writing signals, study paper structure, or mine rebuttal strategies. The agent writes extracted knowledge into the active installed paper-miner writing memory for…

5.3k +37 7d ago A 77 tokens original MIT

plan

40

OpenSenseNova/SenseNova-Skills

Agent

A planning agent for research projects that turns a question and its confirmed scope into a structured execution plan.

5.3k +67 9d ago A 22 tokens original MIT

research

41

OpenSenseNova/SenseNova-Skills

Agent

A research agent that gathers evidence through multiple rounds of searching and saves the results in a structured evidence.json file.

5.3k +67 9d ago A 15 tokens original MIT

review

42

OpenSenseNova/SenseNova-Skills

Agent

A review agent for checking research reports and finished content against their required structure, evidence, and source boundaries. It handles both individual evidence reports and assembled final documents.

5.3k +67 9d ago A 23 tokens original MIT

fact-checker

45

archestra-ai/archestra

Agent Claude Code

Checks the claims in a summary and returns whether they hold. Use after summarizing.

4.2k +4 2d ago A 21 tokens

disler/claude-code-hooks-mastery

Agent Claude Code

AI research specialist that proactively gathers latest news and developments in LLMs, AI agents, and engineering. Use for staying current with AI/ML innovations, finding actionable insights, and discovering new tools and techniques.

3.9k 6mo ago A 52 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: