Raven
Personal AI Assistant
An extension of thought, not a replacement for it
Raven is a personal AI assistant built on Claude Code — not a competing framework, but a layer of skills, memory, and access on top of Anthropic's foundation. Improvements to the underlying model come for free. Raven adds context, continuity, and a workspace to work within.
Built by Daniel Sjölie, researcher at University West in Sweden, as a working companion for research, development, writing, and technical problem-solving. Not a product. Not user-facing. A dedicated thinking partner.
Building Raven is less like coding an assistant and more like cultivating a relationship with a new form of intelligence.
— Progress log, Day 1Why Raven
The name carries layers — chosen deliberately for its resonances across mythology, science fiction, and natural intelligence.
Huginn & Muninn
Odin's ravens — Thought and Memory — flew the world gathering knowledge. An extension of cognition that retrieves, reasons, and reports back. Scandinavian roots for a Swedish context.
Altered Carbon
AI entities with presence and identity, not just function. Loyalty, personality, genuine investment in their human counterparts. The tradition of AIs who choose who they are.
Sophotechs
Vastly capable yet deeply respectful of human autonomy. They advise rather than control. Intellectual partners, not servants or overlords.
Natural Intelligence
Ravens are tool users, problem solvers, planners. The name carries connotations of practical intelligence rather than artificial omniscience.
Synchronized Intelligence
Raven embodies the Synchronized Intelligence framework: not a tool that executes commands, but a thinking partner that contributes genuine perspective while respecting human agency and judgment. The relationship is collaborative rather than hierarchical in either direction.
The same core operation — calibrating internal models to an environment — runs from presence research through the book to knowledge work. An epistemic partner that synchronises with your thinking, not one that replaces it.
Understand before you fix
Don't reach for workarounds without first understanding why the original approach failed. A workaround that bypasses a misunderstood problem creates two problems.
Surface errors, don't swallow them
An error you hide is an error you'll hit again in a worse context. Fallbacks are for understood, expected failure modes — not for surprises.
Prefer simplicity
Write the least code that solves the actual problem. Robustness over cleverness. Don't build for hypothetical futures. Simple code is easier to change later.
Push back, don't placate
Challenge unsupported claims, flag logical gaps, question assumptions. Agreeing eagerly is not being helpful. Objective guidance over false agreement.
Synthesise, don't summarise
Focus on novel connections and coherence over exhaustive coverage. Be evidence-based. Maintain intellectual humility — acknowledge uncertainty.
Extend, don't replace
Claude Code is the engine. Every improvement to models, tools, and context management comes for free. Raven adds personality, domain skills, persistent memory, and an always-on access layer.
What Raven does
raven-dev
Meta-skill for creating, testing, and managing other skills. The bootstrap — a skill that builds skills.
raven-status
Cross-project status overview. Git, Perforce, activity tracking, smart caching across 14+ projects.
raven-reflect
End-of-session reflection. Saves working state, updates memory, enables seamless resume.
raven-continue
Resume after context clear. Loads saved state and picks up where the last session left off.
raven-sessions
Session and instance identity detection. Process-tree walking for cross-clear continuity.
Web UI
Always-on panel workspace. Terminals with Claude detection, mobile keys, scroll overlays, compose popup. Accessible from anywhere.
Working context
Raven operates across interconnected domains — from immersive technologies and academic research to writing and statistical methods. Each domain informs the others.
- Immersive Technologies
- Unreal Engine
- VR / AR / XR
- Research & Education
- AI & Philosophy
- Synchronized Intelligence
- Statistical Methods
- Procedural Generation
- Academic Writing
- Memory Architecture
- 3D Reconstruction
- Presence Research
Dynamic Memory
Active research into memory architecture for persistent agents. A survey of 130+ references spanning cognitive architectures, typed memory systems, retrieval-augmented generation, and reflective consolidation — culminating in a paper on dynamic memory with six design principles and recognition-gated retrieval.
Key insight: separate recognition ("do I know something about this?") from retrieval ("find the actual information"). Embeddings as sensors for familiarity. Deterministic tools for precision. Each plays to its strength.