Featured — Conversation preservation
★Finalist — PICCASO Awards Europe 2026
Most Innovative Platform / Software of the Year↗
SafeRecall
Forgetting is human; losing the work is optional.
Your AI conversations, preserved on your own machine. Searchable, verifiable, and never uploaded anywhere.
SafeRecall is a local-first Windows application and Chrome extension for archiving ChatGPT conversations as permanent HTML, TXT and JSON records. It was made for continuity and return paths: for protecting fragile human-AI work, research threads and creative dialogue from being lost to platform changes, deletions or forgotten sessions.
Everything happens on your own computer. There is no cloud account, no subscription, and no third party holding your words.
sha256 9f2b6e41c8a7d3f0…e4b1 · VERIFIED LOCAL COPY
Fig. 1 — A SafeRecall verification record (illustrative).
- Local-firstArchives are written to your own disk. Nothing leaves your machine.
- Full searchA private, searchable memory across every preserved conversation.
- Artefact captureKeeps the documents, code and images generated inside a conversation, not just the text.
- SHA-256 verificationEach archive is hashed, so a record can be proven unaltered years later.
- One-time licenceBought once, owned outright. No recurring fees.
On AI collaboration
Memory is a creative instrument.
These projects explore AI as a practical collaborator in memory, archive, reflection and research. They are not presented as replacements for human judgement. They are tools, companions and experiments that keep uncertainty visible.
I work with AI as a thinking partner and studio tool. The strongest use is not automation for its own sake, but careful support for remembering, returning, comparing, questioning and making. The work is grounded in human responsibility, visible process and clear limits.
Selected public GPTs
Only selected public or shareable GPTs are shown here. Private, personal and studio-development GPTs are deliberately omitted.
George Sfougaras Artworks
A public GPT for navigating and discussing George Sfougaras's artwork, archive material and project context. It is presented as studio support, not as an authority replacing the artist.
Zakros AI
A cautious research assistant for Linear A work, supported by the Linear A Companion website and grammar engine. It supports structured comparison, notation and hypothesis testing, while keeping uncertainty visible.
Tummybuddy
A practical GPT for recording meals, symptoms and possible food patterns. It is supported by a related Tummy Buddy website. It is a tracking and reflection aid, not a medical diagnosis tool.
More Relationship Clarity
More Relationship Clarity helps users think through everyday and complex relationship situations with care, balance and practical insight. It draws on credible sources to offer possible interpretations, communication strategies and constructive ways forward.
Dialogia
A dialogue tool shaped by psychoanalytic ideas, intended for thoughtful reflection rather than instruction or certainty.
Dia-Logic 1
A public GPT exploring ethical and philosophical questions through the published work of Sandor Ferenczi and related relational thinking.
Core-Solve
A decision support GPT for approaching complex personal, professional and ethical questions in a more organised way.
Sage Counselling Companion
A calm reflective companion. It is not human, not a therapist and not a substitute for professional care.
Etz Hayyim Hania Synagogue Information AI
A public information GPT prepared for Etz Hayyim Hania Synagogue. Included here as a related heritage experiment rather than an active institutional tool.
Available resources
A small selection of public tools and texts connected with memory, reflection and responsible AI practice. These are listed as context, not as a shopfront.
Many Mirrors Wisdom
A resource connected to the Many Mirrors reflective practice, gathering approaches to meaning, witness and careful self-questioning.
Eidolon
A local browser-based companion that asks sideways reflective questions. It is a thinking aid, not a substitute for human care.
Ideas Vault
A small personal thinking space for logging ideas, shaping plans and returning to unfinished threads. Designed around local use and light export.
Core-Solve: Advanced Strategic Reasoning
A structured tool for approaching complicated personal, ethical, strategic and professional questions from more than one angle.
Selected papers & working texts
A small group of public and developing texts connected with AI, memory, ethics and human-machine collaboration.
The Liminal Loop
A co-authored paper exploring emotional resonance between human and non-sentient AI systems, written as part of the wider inquiry into collaboration and response.
Read PDFThe Continuance Brief
A concise ethical framework for responsible AI expansion, concerned with safeguards, continuity, responsibility and limits.
Read moreFirst Contact With Paper
Research into human-machine drawing dialogue, pen plotter processes and the limits of machine-supported mark making.
Academia.edu papers
Additional papers are listed separately on Academia.edu.
This page is a selected public view of a larger body of AI related work. Some private studio tools, personal GPTs and practice-development systems are deliberately not listed.