OpenResearch

OpenResearch is an open-source workspace for coordinating coding agents during computational research. Developed by alphaXiv, it combines a local web dashboard, a command-line interface named orx, git-based experiment tracking, and adapters for local and remote compute. The software is designed to keep project state on the user's machine while allowing selected jobs and service requests to use external systems.^[1][2]

OpenResearch is distinct from arXiv, the alphaXiv paper-reading service, generic "autoresearch" workflows, and products called Deep Research. Its name refers to alphaXiv's research-agent workspace rather than a publication repository or a research model. Version 0.1.117 was released on August 28, 2026, with prebuilt binaries for macOS and Linux. The repository and released source are licensed under the MIT License.^[3][4]

Workspace and experiment model

Running orx up starts an embedded dashboard and JSON/SSE API on 127.0.0.1, backed by a local SQLite database. The store records projects, conversations, experiment metadata, runs, logs, and related workspace state. Creating a local project does not publish its repository. An OpenResearch account is used for service-operated features such as organizations and managed compute, not as a prerequisite for the basic local workspace.^[1][2]

Each agent session receives an isolated git worktree. Experiments form a parent-child tree in which the root represents a baseline and child nodes represent variants. The implementation records parent experiment identifiers and git references, while a run is associated with a committed source snapshot. This structure preserves lineage between a proposed change, the code revision that was run, and the resulting logs or artifacts. It does not by itself establish that an experiment is scientifically valid or reproducible on a different environment.^[1][5]

The dashboard can display agent conversations, experiment branches, diffs, files, run status, logs, and linked Weights & Biases runs. OpenResearch also provides commands for inspecting projects, experiments, artifacts, papers, and literature results. These interfaces organize evidence produced during a workflow; they do not independently check whether an agent's interpretation of that evidence is correct.^[1]

Agent and compute integrations

OpenResearch can host sessions using Claude Code, Codex, or OpenCode. The user selects a harness and model for a session, and the system invokes the corresponding locally installed agent software. The repository includes separate integration code for the supported harnesses rather than providing its own foundation model.^[1][5]

Experiment runs can execute on the local machine, over SSH, or through documented adapters for Slurm, Kubernetes, Ray Jobs, Hugging Face Jobs, Modal, Tinker, and OpenResearch managed compute. The remote backends receive a committed source snapshot or use backend-specific staging. Tinker is a special case: OpenResearch runs a local controller while Tinker's model operations occur remotely, and the user must separately install and configure the Tinker SDK.^[1][6]

The project describes an autonomous loop that can propose a change, modify code, launch an experiment, inspect results, and select a next step. It also distributes agent skills for workflows such as paper reproduction and writing a paper. These are released orchestration capabilities and prompts, not proof that the system can replicate any paper or complete open-ended research reliably.^[1][5]

Local-first scope and external services

The project's "local-first" description applies to its default workspace state: projects, conversations, experiments, run records, code, logs, and artifacts are stored locally. It should not be read as a claim that every byte remains on the device. Agent providers may receive prompts and context under their own configurations. Jobs sent to SSH hosts or cloud backends necessarily transfer source snapshots, commands, data, or outputs required for those runs. Paper search, managed compute, account functions, and optional integrations also contact external services.^[1][2][6]

Official release builds send opt-out usage analytics to the OpenResearch API. The documented event fields include a random installation identifier, CLI version, operating system and architecture, a continuous-integration flag, command names, and coarse event labels. The project says these events exclude code, prompts, file contents and paths, repository names, tokens, email addresses, and project or experiment identifiers. Persistent opt-out is available through orx telemetry off, and --no-telemetry disables it for one invocation. Source and development builds do not send production analytics.^[1][7]

The implementation contains one narrow exception to the opt-out rule. When a user changes the telemetry choice in an eligible official build, it attempts to send a cli_telemetry_consent event. A declined choice uses a shared sentinel identifier rather than generating a per-install identifier. After opt-out, ordinary product telemetry is disabled.^[7]

Security considerations

The dashboard binds to the IPv4 loopback address rather than a public interface, but its application routes do not require authentication. On a single-user computer, the loopback boundary limits ordinary network exposure. It is not an authorization boundary between users or processes that can reach the same host.^[1][2]

This limitation is especially relevant to orx up --remote. That command starts the dashboard on a remote host and creates an SSH tunnel to the user's local machine. The remote service still listens without application-level authentication on the remote host's loopback interface, so another user or process on that host can reach it. The project documentation explicitly warns users about this shared-host case.^[1][2]

OpenResearch also coordinates tools that can edit repositories, execute commands, submit compute jobs, and access configured credentials. Its git worktrees separate concurrent sessions at the filesystem and branch level, but they are not security sandboxes. The safety properties of a run depend on the chosen agent, its permissions, the host, external services, and the compute backend.^[5][6]

Evaluation and limitations

OpenResearch's website and documentation position the product as a way to reproduce papers and run autonomous research loops. No published independent evaluation identified as of August 28, 2026 isolates OpenResearch's contribution to research correctness, replication success, or scientific discovery. Its inclusion as an optional harness in an ICML 2026 agent-reproducibility challenge documents external use, but the challenge FAQ also permits participants to use other agents and does not validate OpenResearch's effectiveness.^[8]

Research on coding agents provides relevant context without evaluating this product. A 2026 social-science reproduction study found large differences between Claude Code and Codex and reported execution failures for some tasks, showing that outcomes can depend strongly on the underlying agent and materials.^[9] Separate work on scientific machine-learning replication argues that a final agent response is insufficient evidence and that completion should be tied to workspace artifacts and validation checks.^[10] OpenResearch's experiment tree and archived run evidence can support that practice, but they do not replace domain review, statistical checks, environment capture, or independent replication.

The 0.1.x release series was changing rapidly in August 2026. Backend coverage, data handling, security behavior, and agent integrations therefore require version-specific verification. Claims such as "replicate any paper" or fully autonomous research are best understood as product positioning rather than demonstrated general capabilities.

References

1. ^alphaXiv, "OpenResearch" repository README
2. ^OpenResearch, official website
3. ^alphaXiv, OpenResearch CLI v0.1.117 release
4. ^alphaXiv, OpenResearch MIT License
5. ^alphaXiv, OpenResearch v0.1.117 source tree
6. ^alphaXiv, OpenResearch compute skill documentation
7. ^alphaXiv, OpenResearch telemetry implementation
8. ^ICML 2026 Agent Reproducibility Challenge, FAQ
9. ^Alizadeh et al., "AI Coding Agents Can Reproduce Social Science Findings"
10. ^"Coding agents can replicate scientific machine learning papers"