selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

raytsystem logo

Self-host raytsystem

Local-first agent workspace for knowledge and workflows

AlphaOpen SourceApache-2.0
Updated2 weeks ago
LanguagePython
Setup difficultyAdvanced
Stars
149
Port
8765 (loopback web UI)
Install with Build from Source
Command Center showing synthetic local workspace stateDocuments with a synthetic Markdown document openKnowledge Universe showing a synthetic graphAgents catalog with synthetic definitionsSkills catalog with synthetic definitionsTasks surface with synthetic task stateSafety surface showing local-only boundaries

What is raytsystem?

raytsystem is a self-hosted workspace for managing knowledge, tasks, and documents with AI agent assistance. It runs a local web interface on 127.0.0.1:8765 that includes a Command Center dashboard, a Documents section for Markdown files with search and history, a Knowledge Universe graph view, an Agents and Skills catalog, a Tasks and Runs tracker, and a Safety panel with approvals and feature flags. Installation is from source using git and uv on macOS, Linux, or WSL 2 with Python 3.12–3.14. The project is pre-1.0, does not claim production readiness, and keeps external model execution and network access disabled by default. It is licensed under Apache-2.0.

Should you self-host raytsystem?

raytsystem scores 38/100 on selfhost.directory (how scoring works) and ranks #177 of 209 in AI Agents. It has 149 GitHub stars.

There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.

Setup is advanced: plan for several services and some ongoing maintenance. It is Apache-2.0-licensed and written mostly in Python.

Its closest alternative on selfhost.directory is Orca (91/100, 108 739 stars). It scores higher overall, so compare the two before you pick. See raytsystem vs Orca side by side.

Features

  • Agents and Skills catalogDefinitions do not imply execution; external execution disabled by default
  • Backup and RestorePre-1.0; operators must verify backups before migration
  • Code Graph
  • Command Center
  • DocumentsManaged Documents writes are experimental
  • Knowledge Universe
  • Safety and Systems
  • Tasks and Runs

raytsystem README

How to install raytsystem

Install raytsystem with Build from Source

git clone https://github.com/romarayt/raytsystem-public-os.git raytsystem cd raytsystem uv sync --dev uv run raytsystem doctor uv run raytsystem start

Only supported installation method; no packaged installers or Docker images

How to configure raytsystem

  • config/platform.yamlPlatform feature flags, default policies, and circuit breaker thresholds

    Platform feature flags, default policies, and circuit breaker thresholds

  • config/policies.yamlKnowledge promotion rules, external action policies, model egress rules, and reviewer roles

    Knowledge promotion rules, external action policies, model egress rules, and reviewer roles

  • config/raytsystem.tomlCore settings: schema version, data paths, limits, and core feature flags in [features] section

    Core settings: schema version, data paths, limits, and core feature flags in [features] section

  • config/runtime-adapters.yamlCatalog of runtime adapters (executors); all have state: disabled by default

    Catalog of runtime adapters (executors); all have state: disabled by default

  • config/sources.yamlSource normalization routes and network settings (network disabled by default)

    Source normalization routes and network settings (network disabled by default)

More in Task Management

Rate this project

Click to rate — no account needed.

0 comments

Posting as guest
Loading comments…