autonomous research / AI paper generation
AutoResearchClaw is a fully autonomous, self-evolving research agent that converts a research idea into a complete paper via multi-agent debate, experiment execution, and self-improvement.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
same end-to-end idea-to-paper workflow with human-in-the-loop experiment assistance.
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
same blueprint-driven pipeline from idea through experiments to paper and peer review.
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Apple Silicon/MLX implementation of an autonomous research loop, platform-limited.
Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.
autoresearch via autonomous coding agents (Claude Code/Codex) with grading and multi-agent evolution.
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
self-evolving research colleague with persistent memory and skills, written in TypeScript.
🔬🦞 A self-evolving AI research colleague for scientists. 285 skills, zero hallucination, persistent memory.
self-evolving AI scientist platform with different architecture and workflow.
🔬 Harness Vibe Research with Self-evolving AI Scientists
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
narrower: synthesizes web research into reports, no experiment or paper pipeline.
An autonomous agent that conducts deep research on any data using any LLM providers
narrower: leading deep-research agent focused on report generation, not full paper authorship.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
narrower: local-only web research and report writing, no experiments.
Fully local web research and report writing assistant
narrower: deep research agent for search/comprehension benchmarks, not experiment execution.
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
narrower: deep research over private data producing reports, not papers.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
narrower: LLM-agnostic deep research report generation, no experiment loop.
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
narrower: automates deep-learning experiment runs only, without report/paper generation.
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
narrower: OpenAI Agents SDK-based iterative deep research, report output.
An implementation of iterative deep research using the OpenAI Agents SDK
narrower: LangGraph multi-agent research with credibility scoring, report output.
Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search
narrower: local-first agentic research workflow, no experiment execution.
Cerno is a local-first research platform that leverages agentic AI to break down complex queries into verifiable, multi-step workflows. Switch seamlessly between cloud LLMs and self-hosted models, track every reasoning step, and optimize cost and tokens—all while keeping your data on your machine.
narrower: deep research framework with progressive search/cross-evaluation, report-oriented.
A deep research framework based on progressive search and cross-evaluation.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
markdown skill pack that needs Claude Code to run, not a standalone system.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
These projects were analysed and named AutoResearchClaw among their alternatives. The relationship is not symmetric — how AutoResearchClaw rates them is a separate judgement, made when AutoResearchClaw is analysed in its own right.
calls AutoResearchClaw “Use when you want an autonomous research agent that generates complete academic papers from idea to final draft.”
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
calls AutoResearchClaw “choose for a self-evolving autonomous pipeline from idea to paper instead of manual supervision”
Academic Research Skills for Claude Code: research → write → review → revise → finalize
calls AutoResearchClaw “Fully autonomous self-evolving idea-to-paper system with its own runtime; choose it for a turnkey pipeline.”
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
calls AutoResearchClaw “choose it if you want a self-evolving system that autonomously drives a research project from idea to paper.”
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
calls AutoResearchClaw “Autonomous research-to-paper pipeline; choose when you need a full academic paper rather than a markdown summary.”
Fully local web research and report writing assistant
calls AutoResearchClaw “Use if you want an autonomous research agent that goes from an idea to a full paper.”
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
calls AutoResearchClaw “standalone idea-to-paper research agent, choose if you want a self-contained pipeline rather than a pi extension.”
Autonomous experiment loop extension for pi
calls AutoResearchClaw “choose it if you want a chat-initiated, self-evolving research loop instead of v2's tree-search pipeline.”
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
calls AutoResearchClaw “Hands-off idea-to-paper autonomy with no per-step checkpoints; take it when you want a pipeline to run, not prompts that ask you questions.”
An AI workflow skill pack for research, competitions, and innovation projects.