Follow Your Star
A coding and research cockpit where models, tools, and a living world meet.
ONE-COMMAND LINUX INSTALL · x86_64 · BUILDS FROM SOURCE ON FIRST RUN
git clone https://github.com/newjordan/angelX.git && cd angelX && ./bin/angelX
AngelX created by Jordan Newman @frostforger✦
The terminal interface.
A recorded look at the multi-panel terminal cockpit. Interface capture: September 2026.
What it does.
Models and formations
Choose models and thinking levels, configure teams, and run agent graphs.
Repository tools
Search files, inspect symbols, follow definitions, and review diffs.
Content-checked edits
Hashline editing checks file content before applying anchored changes.
Programmable tools
Run tool calls, loops, and filters locally in JavaScript with code_mode.
Long-session context
Compact, deduplicate, and age retained context as work continues.
Project memory
Review source-linked knowledge in Atlas and reuse it in later tasks.
Persistent goals
Resume sessions and autonomous work with configurable run limits.
Headless runs
Record task settings, source identity, tool activity, and acceptance evidence.
Adventure world model TUI
Introducing the early stages of Cyberdynamic world tui for reviewing work, presenting data graphs, adventure, and model behavior.
Measured benchmarks
Calculate measured changes from paired benchmark samples.
Measured campaigns
Evaluate isolated attempts with verifiers and independent review.
Research loops
Match the tooling to the model: determinate systems for lighter models; expansive RL toolsets and confirmation systems for frontier models, built for long-form research and development.
A coding and research harness.
angelX is a cyberdynamic tool for explorers pushing the boundaries of research with AI. It is also a coding tool, a mini world, and a growing, self-reflective piece of software — built to evolve over time and adapt to the person driving it.
Built in Rust for long-running research, coding workflows, and model teams. The public 0.2.3 release also includes browser seats and a shared adventure world.
- CUSTOM TUI LAYOUT
- agent thinking · actions as primary surfaces
- DEEP TOOLING
- research · loops
- WORLD MODEL
- self-referential · adapts per user
- MEASURED
- evaluator-graded coding tasks
