MCP servers and skills: search, filter by where they run, and compare.
A lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openA
PythonApache-2.0★ 9No key
Open-source deep research assistant with citations and memory. Ask a question and it searches the web, papers, old newspapers, archives and GitHub, writes a report, checks its citations against the so
Node.jsApache-2.0★ 1Few starsNo key
Find the 5–10 recent papers with the highest impact on a research question, topic or project.
PythonApache-2.0★ 1Few starsNo key
Evidence-aware industry and company research skill for AI agents, with Deep Search, Claim routing, Evidence Ledger, competitive intelligence, and structured Markdown reports.
SkillApache-2.0★ 3Few starsNo key
A Multi-Agent Research System using Claude Code Skills. it is inspired by Anthropic claude-agent-sdk-demos
SkillApache-2.0★ 11No key
Open-source AI research agent toolkit for evidence-based academic writing and reproducible research.
SkillApache-2.0Few starsNo key
Evidence-first local MCP and skills for turning AI research into measured, human-approved setup changes.
Node.jsApache-2.0Few starsNo key
面向中国 A 股研究的 Agent Skill：公告、财报、研报解析与因子候选生成
SkillApache-2.0★ 5No key
Search and retrieve researcher profiles, works, affiliations, funding, and peer review records from the ORCID registry via MCP. STDIO or Streamable HTTP.
Node.jsApache-2.0★ 5No key
AI-native scientific research pipeline. Takes a research goal and autonomously runs multi-step academic research on Cursor, Codex CLI, Cline, Continue, Gemini CLI, Copilot, Windsurf, Claude Code, and
SkillApache-2.0★ 10No key
Security-first agent harness built for long horizon research and work capabilities with increased focus on math, computer science, and domain science research
SkillApache-2.0★ 4Few starsNo key
Discover, explain, rank, replay, and verify low-hanging research opportunities in mathematics and LLM research—from one sentence.
SkillApache-2.0★ 4Few starsNo key
An open, thin, model-agnostic harness for long-horizon autonomous AI research. Built on Goose.
SkillApache-2.0★ 13No key
面向 Crypto 市场研究的 Agent Skill：现货、合约、链上与协议证据解析
SkillApache-2.0★ 3Few starsNo key
Host-neutral Agent Skills for auditable empirical macro research with Agent Plan 专业数据集 integration.
SkillApache-2.0★ 1Few starsNo key
🏛️ ACM EASE '26 / VibeX full paper · DOI 10.1145/3816483.3816631 · Adversarial agent loops for verifiable vibe researching. Falsification-first research runtime.
SkillApache-2.0★ 17No key
Zero-auth, security-hardened cross-domain research MCP server: web, academic, GitHub, news, weather, macro/finance, SEC, biomedical, Bluesky, YouTube. SSRF and prompt-injection defenses.
PythonApache-2.0★ 11No key
Official SearchCans Agent Skills for deep research, SERP intelligence, and web-to-Markdown workflows.
SkillApache-2.0★ 3Few starsNo key
Citation-true research synthesis with Zotero, PubMed intake, provenance tracking, and blinded human–AI dual-rating records.
PythonApache-2.0★ 1Few starsNo key
Scientific agent skills for Claude Code and Codex that turn research goals into auditable hypothesis generation, review, ranking, evolution, and synthesis.
SkillApache-2.0★ 6No key
Verified knowledge infrastructure for agent-native research teams.
PythonApache-2.0★ 16No key
Auditable MCP + cross-agent harness for autonomous and human-guided academic writing—from verified evidence to reviewed DOCX/PDF.
PythonApache-2.0★ 12No key
MCP server aggregating academic search sources into one unified interface for research agents
PythonApache-2.0★ 5No key
Who stands behind it
