awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
alphaXiv avatar

alphaXiv/OpenResearch

0
View on GitHub↗
openresearch.sh↗

OpenResearch

OpenResearch is a local-first desktop application that runs coding agents as autonomous research assistants. The agents review scientific literature, form hypotheses, run experiments, and produce research artifacts. They can work alongside a researcher as a copilot, with optional human approval between steps, or operate fully on their own.

What sets it apart is the combination of agent choice, flexible compute, and a persistent record of results. You can pick from several coding agents or connect local models through common runtimes and custom endpoints, so the same research workflow runs with the tools you already prefer. Experiments can be dispatched to a local machine, SSH hosts, Slurm clusters, Kubernetes, or managed cloud compute through one consistent workflow. Every experiment is recorded with its logs, code, and artifacts in a local SQL database, which agents query to learn from earlier results and decide what to try next.

Agents ground their hypotheses in published work through connectors to paper sources such as alphaXiv, bioRxiv, and PubMed. A locally served dashboard in the desktop app lets you inspect what the agents did and the evidence behind each result. Projects, conversations, experiments, logs, and artifacts stay on your own machine, and usage analytics and agent feedback can be switched off. The core runtime is written in Rust.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Scientific Research Platforms - Runs coding agents that review scientific literature, form hypotheses, run experiments, and produce research artifacts, as a copilot or fully autonomously.
  • Autonomous Research Agents - Launches coding agents that review literature, form hypotheses, run experiments, and produce artifacts as a copilot or fully autonomously.
  • Coding Agent Orchestrators - Lets users choose among several coding agents or connect local models through common runtimes and custom endpoints within one research workflow.
  • Coding Agents - Lets users choose among several coding agents or connect local models via common runtimes and custom endpoints.
  • Experiment Tracking - Records every experiment with its logs, code, and artifacts in a local database that agents query to decide what to try next.
  • Remote Run Controllers - Executes experiments on a local machine, SSH hosts, Slurm clusters, Kubernetes, or managed cloud compute from one consistent workflow.
  • Experiment Tracking Systems - Records each experiment's logs, code, and artifacts in one local database so results can be reviewed, compared, and reused.
  • Literature Source Connectors - Connects agents to alphaXiv, bioRxiv, and PubMed so hypotheses and experiments are grounded in published work.
  • Desktop and Local Apps - Ships a desktop app with a locally served dashboard that keeps projects, conversations, experiments, logs, and artifacts on the user's machine.
  • Embedded Experiment Stores - Persists experiments, logs, code snapshots, and artifacts in a local SQL database that agents query to choose next steps.
  • Multi-Backend Compute Dispatch - Dispatches experiments to local, SSH, Slurm, Kubernetes, or managed cloud compute through a single uniform workflow.
  • Agentic Research Loops - Runs agents through repeated cycles of literature review, hypothesis, experiment, and recording results, with optional human approval between steps.
  • Literature Collectors - Connects agents to alphaXiv, bioRxiv, and PubMed so they can find relevant papers and tie experiments to existing research.
  • Automated Experiment Runners - Executes agent-written experiments on local, SSH, Slurm, Kubernetes, or managed cloud backends through one consistent workflow.
  • Scientific Data Source Connectors - Offers pluggable connectors to paper sources such as alphaXiv, bioRxiv, and PubMed that agents call on demand to retrieve papers.
  • Research Job Dispatchers - Dispatches long-running experiment runs to local, SSH, Slurm, Kubernetes, or cloud compute through one uniform execution layer.
  • AI Agents and Workflows - Local workspace turning coding agents into autonomous research assistants.
7,975 stars·536 forks·Rust·MIT·4 views

Star history

Star history chart for alphaxiv/openresearchStar history chart for alphaxiv/openresearch

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Frequently asked questions

What does alphaxiv/openresearch do?

OpenResearch is a local-first desktop application that runs coding agents as autonomous research assistants. The agents review scientific literature, form hypotheses, run experiments, and produce research artifacts. They can work alongside a researcher as a copilot, with optional human approval between steps, or operate fully on their own.

What are the main features of alphaxiv/openresearch?

The main features of alphaxiv/openresearch are: Scientific Research Platforms, Autonomous Research Agents, Coding Agent Orchestrators, Coding Agents, Experiment Tracking, Remote Run Controllers, Experiment Tracking Systems, Literature Source Connectors.

Which projects share features with alphaxiv/openresearch?

Projects with overlapping indexed features include: aipoch/open-science — Open Science is a local-first AI research workbench in which agents plan and run multi-step scientific tasks on the… karpathy/autoresearch — Autoresearch is an autonomous machine learning research agent and architecture search framework. It employs a… aimhubio/aim — Aim is an open-source platform for logging, visualizing, and comparing machine learning training runs and LLM traces.… cursor/cookbook — This repository is a collection of example projects and guides for building with Cursor's coding agents. The samples… openbmb/ultrarag — UltraRAG is an LLM RAG orchestration platform and AI agent research framework designed to coordinate complex… sandbox-quantum/switch — Switch is a self-hosted platform where people and AI agents share chat rooms. Agents built on different coding-agent…

Projects sharing features with OpenResearch

These projects share indexed features with OpenResearch. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • aipoch/open-scienceaipoch avatar

    aipoch/open-science

    5,490View on GitHub↗

    Open Science is a local-first AI research workbench in which agents plan and run multi-step scientific tasks on the user's own computer, with results that can be traced back to their code, inputs and environment. Questions, papers or data files given in plain language are worked through by agents that call tools, execute Python and R code in notebook-style cells, and hand tasks to specialist subagents. A separate review context checks each finished turn against replies, execution records and file evidence, and triggers bounded corrections when it finds problems. What sets it apart is the comb

    TypeScriptagent-skillsai-agentai-for-science
    View on GitHub↗5,490
  • karpathy/autoresearchkarpathy avatar

    karpathy/autoresearch

    99,472View on GitHub↗

    Autoresearch is an autonomous machine learning research agent and architecture search framework. It employs a closed-loop system to programmatically rewrite training and architecture source code to discover optimal language model configurations. The system iteratively modifies code and evaluates performance metrics to improve model quality based on a target objective. It optimizes model performance and training efficiency by tracking validation bits per byte, which allows for a fair comparison of architectural changes independently of vocabulary size. The framework manages the full training

    Python
    View on GitHub↗99,472
  • aimhubio/aimaimhubio avatar

    aimhubio/aim

    6,295View on GitHub↗

    Aim is an open-source platform for logging, visualizing, and comparing machine learning training runs and LLM traces. It provides a remote tracking server and a comparison UI, functioning as an ML experiment tracker, AI workflow logger, and LLM trace recorder that captures prompts, generations, and tool calls from AI applications. The platform distinguishes itself through a run-based data model with local SQLite storage, real-time metric streaming, and a plugin-based explorer system that supports specialized visual analysis of metrics, images, audio, and text. It offers a Python SDK with cont

    Python
    View on GitHub↗6,295
  • cursor/cookbookcursor avatar

    cursor/cookbook

    4,158View on GitHub↗

    This repository is a collection of example projects and guides for building with Cursor's coding agents. The samples cover running agents from TypeScript code against local workspaces or cloud runtimes, streaming their output live, and launching them from a terminal. Other examples include a cloud agent kanban dashboard, a task graph orchestrator, an app-prototyping chat, and a realtime voice intake demo. Several samples go beyond a basic quickstart. The kanban dashboard lists cloud agents as cards grouped by status, repository, or branch, previews their artifacts, and launches new agents fro

    TypeScript
    View on GitHub↗4,158
Compare all 30 related projects→