Research
Work on language models, interpretability, uncertainty, and systems performance.
Work
Selected products, current software, research, teaching, and creative practice.
Browse by practice
Software
Applications, developer tools, libraries, and research infrastructure.
Teaching
Courses, project-based curricula, technical notes, and learning tools.
Creative practice
Photography, interactive systems, physical computing, and making.
Selected products
All products
Current software
Software indexagent-execution
Runs a coding agent as a job under an explicit tool policy (no tools, read-only, or confined writes), with process containment, cost limits, and a record of what the agent was given and what it did. Optionally submits the work as a Weft job.
agent-offload
Sends a coding task to an agent on another machine. The agent edits a snapshot of the source tree as a Weft job, and its work comes back as a diff to verify and apply.
agent-launcher
Launchers for Claude Code, Codex, Kimi, opencode, OMP, and agy that start each agent under agent-command-guards, with stable session identity, model-first commands, resume by name or transcript text, cross-harness continuation, crash recovery, and exit receipts.
issue-ledger
A local issue ledger for locally developed tools: file defects against any component, deduplicated by fingerprint, with occurrence counts and recurrence tracking after close.
Browse across disciplines
Topic pages bring together software, teaching materials, and creative projects that share a subject.