Framework for AI agents to build and maintain a digital brain through Obsidian wiki
Skill for a persistent LLM-managed wiki — the LLM writes and cross-references while you curate sources.
Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with every conversation. Works with Obsidian, Logseq, etc. or just folders on your local drive. Compiled memory for your LLM sessions. Crossplatform. GUI install on Claude Desktop, no terminal, no code.
An agent skill to evolve the quality of LLM-Wiki (Graphify) at test time.

Portable Agent Skills for building and maintaining Open Knowledge Format project wikis in plain Markdown.
LLM-maintained personal knowledge base for Obsidian. Based on Andrej Karpathy's LLM Wiki pattern.
Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.
Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.
Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.