# Remyx AI

- [Introduction](https://docs.remyx.ai/introduction.md): Decision intelligence for AI teams
- [Quickstart](https://docs.remyx.ai/quickstart.md): Your first Outrider run: connect GitHub and a model provider, install an agent, and watch a draft PR land
- [Using the CLI](https://docs.remyx.ai/cli.md): Install the Remyx CLI, authenticate, and manage Research Interests, recommendations, and search from your terminal.
- [Search](https://docs.remyx.ai/platform/discover/search.md): Semantic search across papers, repos, models, and datasets with runnable Docker environments
- [Feed](https://docs.remyx.ai/platform/discover/feed.md): Personalized daily recommendations grouped by your Research Interests
- [Briefs](https://docs.remyx.ai/platform/discover/briefs.md): Typed, cited research briefs that ground recommendation ranking and your agents' drafting context, plus the Remyx bot
- [Agents](https://docs.remyx.ai/platform/agents/overview.md): Autonomous workers on your repos: set up, run, pause, and drill into each agent's runs, direction, and evidence
- [Actions](https://docs.remyx.ai/platform/agents/outrider-action.md): Remyx agents ship as actions that run in your own CI. Outrider, recent research into draft PRs, is the first.
- [Model backends](https://docs.remyx.ai/platform/agents/backends.md): Two axes: which coding agent runs the implementation, and which model backend serves it, plus the two-tier drafter/refiner pattern
- [Inbox](https://docs.remyx.ai/platform/review/inbox.md): Waiting on you: drafts to review, calls your agents held for you, and anything blocking the loop
- [Reports](https://docs.remyx.ai/platform/review/reports.md): The fleet in one view: what your agents produced, where pools are depleting, and what's waiting on you
- [Evaluation & Decision Policy](https://docs.remyx.ai/platform/review/evaluation.md): Commit how progress gets measured before a result exists: eval templates declare the harness, decision policy renders the bar against the evidence, and validation runs the eval on connected compute.
- [Projects](https://docs.remyx.ai/platform/configure/projects.md): The namespace each initiative runs in: its team, the agents feeding it, and the sources it references — plus the Pro quality gate
- [Connectors](https://docs.remyx.ai/platform/configure/connectors.md): Connect GitHub, model providers, and signal sources — every source feeds a specific part of the next decision
- [Account & keys](https://docs.remyx.ai/platform/configure/account.md): Profile, teams, API keys, agent keys, and where Remyx reaches you
- [MCP Server](https://docs.remyx.ai/resources/mcp-server.md): Drive your Outrider fleet, research, and projects from Claude Code, Slack, or any MCP client
- [ExperimentOps](https://docs.remyx.ai/concepts/experimentops.md): The methodology behind systematic AI experimentation: capture decisions, surface patterns, compound what your team learns
- [Continuous Experimentation](https://docs.remyx.ai/concepts/continuous-experimentation.md): The loop that keeps running on top of ExperimentOps: discovery, drafting, evaluation, and decision, with each turn sharpening the next. CI/CD-style cadence for AI experimentation, with a human at the merge.
- [Causal Intelligence](https://docs.remyx.ai/concepts/causal-intelligence.md): The roadmap for causal inference as the through-line of Remyx's experiment intelligence
- [Maturity Progression](https://docs.remyx.ai/concepts/maturity-progression.md): The four stages of experimentation maturity that Remyx supports, from early dev to counterfactual instrumentation
- [Roadmap](https://docs.remyx.ai/roadmap.md): What's shipped, what's in development, and what's planned for Remyx
- [Tutorials](https://docs.remyx.ai/tutorials/overview.md): Hands-on walkthroughs of the Remyx workflow, from connecting a repo to closing the loop on an experiment.
- [Build Your First Project](https://docs.remyx.ai/tutorials/get-started/overview.md): An end-to-end walkthrough of the experimentation cycle in Remyx. Connect a repo, set up shared context, run an experiment, and review the result.
- [Create your project](https://docs.remyx.ai/tutorials/get-started/create-your-project.md): Connect a repo and watch Remyx extract structured experiment history from your merge log.
- [Set up your discovery feed](https://docs.remyx.ai/tutorials/get-started/set-up-your-discovery-feed.md): Turn your project's extracted history into a daily discovery digest of papers and repos ranked against your team's actual work.
- [Define how progress gets measured](https://docs.remyx.ai/tutorials/get-started/define-how-progress-gets-measured.md): Lock in the eval template and decision policy that future variants will be scored against, before any of them exist.
- [Scope an experiment from a recommendation](https://docs.remyx.ai/tutorials/get-started/scope-an-experiment.md): Turn a paper, repo, or insight from your daily digest into a structured experiment your team can implement.
- [Implement an Experiment](https://docs.remyx.ai/tutorials/get-started/implement-an-experiment.md): Generate a PR that implements your scoped experiment.
- [Run an evaluation](https://docs.remyx.ai/tutorials/get-started/run-an-evaluation.md): Score your variant against the locked eval template on Modal infrastructure, see the side-by-side, and log the decision.
- [Stay in the loop](https://docs.remyx.ai/tutorials/get-started/stay-in-the-loop.md): See velocity across your project, the signal patterns emerging across directions, and the decisions behind every closed loop.
- [Connect Tools to Your Experiments](https://docs.remyx.ai/tutorials/connect-tools-to-experiments.md): Set up GitHub, Linear, and Slack so your experiments automatically link to PRs, tickets, and team conversations.
- [API Reference](https://docs.remyx.ai/api-reference/api-reference.md): REST API for the Remyx ExperimentOps platform
- [API Scopes](https://docs.remyx.ai/api-reference/scopes.md): Key prefixes, the scope catalog, presets, and which surface needs what
- [CLI Reference](https://docs.remyx.ai/api-reference/cli-reference.md): Complete command reference for the Remyx CLI