OpenResearch is a local-first research workspace that integrates with existing coding agents to turn them into research agents.
Follow OpenResearch to get an email when its listing changes, such as new pricing or features. One digest a day at most, and you can unsubscribe anytime.
It enables users to review literature, develop hypotheses, and run automated experiments while maintaining project lineage, experiment logs, and research artifacts in a local git-native structure.
- 01
Integrates with coding agents like Claude Code, Cursor, and OpenCode
- 02
Git-native experiment tracking with immutable snapshots
- 03
Compute marketplace for on-demand GPU access across multiple providers
- 04
Supports local execution or remote compute via SSH, Slurm, Kubernetes, and Modal
- 05
Literature grounding via alphaXiv, OpenAlex, bioRxiv, and PubMed
Open Source
The tool is open-source and free to self-host. An optional hosted compute marketplace is available on a metered, prepaid, usage-based basis, passing through provider costs directly with no OpenResearch markup.
Best for
ML researchers, AI engineers, and independent scientists who want to run autonomous research experiments on their own infrastructure with full control over data and code.
Not ideal for
Users requiring a fully supported commercial product, security-reviewed remote deployments, or those needing independently validated results from autonomous agent loops.
A powerful, high-velocity, open-source tool for researchers who prefer a local-first environment and want to treat experiment logs and code as primary, version-controlled research artifacts.
Version 0.2.23 released on October 31, 2026, introduced native skill discovery for all supported agents, improved desktop UI polish, enhanced keyboard navigation, and expanded deep linking for Windows and Linux.
As of
Is OpenResearch free?+
Yes - OpenResearch is Open Source. The tool is open-source and free to self-host. An optional hosted compute marketplace is available on a metered, prepaid, usage-based basis, passing through provider costs directly with no OpenResearch markup.
Is OpenResearch open source?+
Yes - OpenResearch is open source. The tool is open-source and free to self-host. An optional hosted compute marketplace is available on a metered, prepaid, usage-based basis, passing through provider costs directly with no OpenResearch markup.
Who is OpenResearch best for?+
ML researchers, AI engineers, and independent scientists who want to run autonomous research experiments on their own infrastructure with full control over data and code.
Who is OpenResearch not ideal for?+
Users requiring a fully supported commercial product, security-reviewed remote deployments, or those needing independently validated results from autonomous agent loops.
What are the best OpenResearch alternatives?+
The closest OpenResearch alternatives on ai.dosa.dev are Jules by Google, OpenHands, SWE-agent - all listed under Autonomous & Async Agents.
Who makes OpenResearch?+
OpenResearch is developed by alphaXiv. It is listed in the Autonomous & Async Agents category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.