mrkeyoor.com_
Wed 02 Sept 03:07 UTC
LLM Toolsevaluationupdated 02 Sept 2026

OpenResearch review

OpenResearch is a local workspace for sending coding agents through literature review, hypothesis development, experiments, and research writing. It solves the messy coordination problem around parallel agent sessions by keeping their code, evidence, runs, and outputs together on your machine.

trackingstars / 7d
Verdict

Our build took 125 seconds, and all 1,370 tests passed. OpenResearch is worth trying if agent-led research in code repositories has outgrown a pile of terminals, branches, and loose notes. Its local ownership, isolated worktrees, and preserved evidence are unusually practical, but the v0.1 label and unauthenticated remote service make it a tool to adopt deliberately, not an unattended shared platform.

We ran it

Install✓ · 26s213 packages
Build✓ · 125s
Tests✓ · 302s1370 passed · 0 failed of 1370 (cargo test)
Repo348 files~111,822 lines of source · 7.8 MB · 6 CI workflows

Answers from our run

Does OpenResearch build from source?

Dependencies installed in 26 seconds (213 packages), and the build succeeded in 125 seconds. We cloned commit c5b49fe into a clean Debian container with 3 CPUs and no project-specific setup.

Do OpenResearch's tests pass?

Yes: 1370 of 1370 passed when we ran the project's own test command (cargo test). Some failures need services or credentials a bare container does not have.

Who should not use OpenResearch?

People seeking a simple paper search box, this is an agent workspace, not a lightweight reader

What are the alternatives to OpenResearch?

GPT Researcher, PaperQA2, STORM. Our build took 125 seconds, and all 1,370 tests passed.

Setup4/5213 packages installed in 26 seconds; source build adds time
Docs4/5Clear quick start, commands, compute choices, and caveats
Community3/5Fresh push and release, 645 stars, only 7 open issues
Maturity3/5Strong test result and CI, but still on the v0.1 line

Who it’s for

Researchers who already use Claude Code, Codex, or OpenCode
Engineering teams running several experimental branches in parallel
Labs that need traceable code, logs, results, and artifacts
Teams that want local, SSH, cluster, or managed compute options

Who it’s NOT for

People seeking a simple paper search box, this is an agent workspace, not a lightweight reader
Windows CLI users, the documented CLI install targets macOS and Linux
Teams requiring a hardened multi-user remote service out of the box, remote mode has no application-level authentication
Anyone unwilling to review autonomous code changes and experiment decisions

Setup reality

Our run installed 213 packages successfully in 26 seconds, built in 125 seconds, and completed 1,370 of 1,370 tests in 302 seconds on 3 CPUs with 12 GB RAM. That supports the README's claim that getting started is straightforward, although the source path is more work than the single installer line suggests. The desktop app and orx up path should be simpler, while remote compute, agent harnesses, and cluster backends will still require the credentials and infrastructure those systems normally need.

OpenResearch turns agent sessions into a research workspace

OpenResearch addresses a problem that appears once research agents move beyond a single prompt: the work becomes difficult to follow. A literature search, hypothesis, code edit, experiment, log, and final artifact can end up scattered across terminals and branches. This project puts those pieces in one local-first workspace and gives each direction an isolated git worktree. At 645 GitHub stars, it remains small, but it is more ambitious than another chat interface.

The product joins a Rust CLI, a browser dashboard, a desktop app, and optional managed compute. Version v0.1.118 was released on August 31, 2026, and the repository was pushed again on September 1. The documented workflow starts with orx up, which opens the dashboard on 127.0.0.1:4791. Projects, experiments, logs, source, and artifacts remain on the user's machine unless a service-owned capability is chosen.

Our clean build passed every test

In our run, installation succeeded in 26 seconds and installed 213 packages. We cloned commit c5b49fe into a fresh, unprivileged Debian container with 3 CPUs and 12 GB of RAM, without secrets. The result shows that the source and dependency path worked in a constrained, repeatable environment.

The build then succeeded in 125 seconds. cargo test finished in 302 seconds with 1,370 passed and 0 failed. Those numbers do not prove experiment correctness or remote-backend reliability, but they show that the checked-out Rust project compiled and its substantial automated suite completed cleanly on our box.

The repository contained 348 files, about 111,822 lines of source, and occupied 7.8 MB when checked out. We found 6 CI workflow files, no Dockerfile, and no top-level tests directory. That directory's absence is not an absence of testing, as the 1,370 passing Cargo tests show, but operators who standardize around container recipes must supply that packaging.

Isolated work and evidence are the real strengths

The best idea here is not simply running several agents at once. Each research direction gets an independent session and isolated git worktree, while experiments live in a git-native tree. Every run receives an immutable archive of its recorded commit. When 2 variants differ, a lab can inspect the exact source snapshot, logs, files, and artifacts connected to each run.

OpenResearch also avoids forcing one agent harness on the team. The README supports 3 choices, Claude Code, Codex, and OpenCode, selected per session. Execution can stay local, use the team's infrastructure, or move to managed OpenResearch compute. That flexibility suits groups whose laptop workflow eventually needs remote GPUs without publishing the repository.

The compute list names 8 routes: SSH, Slurm, Kubernetes, Ray, Hugging Face Jobs, Modal, Tinker, and the managed service. orx up --remote user@host keeps the browser on a laptop while the workspace runs near remote hardware. Visible CLI commands cover projects, runs, logs, experiments, keyword discovery, and papers by arXiv ID or DOI.

Early-version rough edges need operational care

The clearest reservation is maturity. A clean 1,370-test run is reassuring, yet v0.1.118 still signals a rapidly changing interface where teams should pin versions and test upgrades. The supplied evidence does not establish how evenly Slurm, Kubernetes, Ray, and every hosted backend are covered in real deployments. Verify the path you intend to use.

Remote mode deserves special attention. The service binds to loopback but has no application-level authentication, and the README says other users on that host can reach it. Port 4791 should not be treated as a shared, hardened team service merely because SSH provides transport. Use host isolation and access controls appropriate to sensitive research code and artifacts.

Official release builds send coarse, opt-out usage analytics tied to a random installation ID. The stated exclusions include code, prompts, file contents or paths, repository names, tokens, emails, and project or experiment identifiers. Privacy-sensitive labs must actively choose orx telemetry off, check orx telemetry status, or use the 1-command --no-telemetry option where policy requires it.

Current activity is promising, not conclusive

Project health looks positive today. The repository was pushed on September 1, v0.1.118 arrived on August 31, and only 7 issues were open. Trending snapshots recorded gains of 90 stars for OpenResearch and 65 for the CLI listing. Current code activity and low issue volume are better evidence than a release tag viewed alone.

Those signals cannot tell us response quality, maintainer capacity, or long-term compatibility. The 645-star audience is meaningful but not proof of widespread production use. Six CI workflows and our passing suite strengthen the engineering case; the early version line and small issue sample keep the community and maturity scores at 3.

It fits beside your repositories and compute

In a real stack, OpenResearch belongs beside source control and execution infrastructure, coordinating work rather than replacing either. Run the dashboard near a repository, give agents isolated worktrees, attach experiments to recorded commits, and send expensive jobs to an existing SSH host or scheduler. The local SQLite store and loopback default make the single-user boundary understandable, while 8 named remote or managed routes offer room to grow.

Choose it when research includes code changes, repeatable experiments, and evidence review across 2 or more branches. Choose PaperQA2 for focused questions over scientific documents, GPT Researcher for autonomous cited reports, or STORM for topic research and long-form synthesis. OpenResearch is stronger when provenance and experiment lineage are the product, provided a human reviews agent decisions before valuable compute or sensitive systems are involved.

Alternatives

ProjectWhat it isPick it when
GPT Researcher gh↗An autonomous research agent focused on gathering material and producing cited reports.Pick this instead when the deliverable is a web or local research report, not a git-native experiment workspace.
PaperQA2A scientific document question-answering and retrieval package built around cited evidence.Pick this instead when your main job is asking grounded questions across a document collection.
STORMA knowledge-curation system that researches a topic and writes a cited long-form report.Pick this instead when you want report generation around a topic more than experiment execution and lineage.

What people are saying

  1. [github-trending] alphaXiv/OpenResearch
  2. [github-trending] alphaXiv/openresearch-cli

Sources

  1. OpenResearch GitHub repository
  2. OpenResearch homepage

More llm tools reviews

rig · open-knowledge · graphiti · cve-mcp-server · minimind · SillyTavern · the whole board →