OpenResearch

OpenResearch is an open-source workspace for running AI coding and research agents in parallel.

OpenResearch is an open-source workspace designed for AI coding and research agents. It allows users to run research workflows locally by assigning each research direction its own agent. Agents operate in parallel within isolated worktrees while utilizing existing tools and compute. Users can also spin up remote compute during autoresearch through a compute marketplace that aggregates offerings from multiple providers. The platform functions as a universal application built for both Apple silicon and Intel processors.

OpenResearch at a glance

Best for: Researcher, Software engineer
Runs on: macOS
Pricing: Free
Released: June 2026
Category: AI research tool
Website: openresearch.sh

Key features

Run AI coding and research agents
Execute parallel research workflows
Isolate agents in worktrees
Use existing tools and compute
Access a remote compute marketplace

Use it for

Reproduce the paper
Test a longer context window
Sweep optimizer and schedule
Tighten the evaluation harness
Ablate the regularizer

Companions

Tools that articles about OpenResearch recommend using with it, each with its job.

Context7 — Provides up-to-date documentation for AI agents and code editors.
Ollama — Run local models at zero marginal cost, with code kept on your machine.
OpenRouter — Access over 500 models and 80 providers through one unified API.
Daytona — Runs sessions in isolated sandboxes synced to git branches.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.

Alternatives to OpenResearch

Open Science — Local-first design with persistent Python and R kernels and traceable artifacts.
AutoResearch — It provides a stateful, reproducible workflow for automated AI research.
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
OpenChamber — Run and review multi-model AI coding agents from desktop, browser, and mobile devices.
HyperResearch — Generates verified reports with citations checked against full source texts and a persistent vault.
OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
OpenHarness — Manages Claude Code, Codex, and Hermes from a single command center.
OpenBot — Runs AI agents locally using existing subscriptions or local models.
AI Scientist v3 — Automates end-to-end scientific research from task descriptions to complete papers.
Paper2Agent — It enables direct interaction with research papers and automatic result reproduction.
Open Math OS — It unites open frontier models, scientific compute, and data sovereignty in one workspace.
OpenAgents — A shared workspace for humans and AI agents with multi-device sync.

All OpenResearch alternatives