tweakoz/orkid

Orkid Media Engine (C++/Lua/Python3/Linux/MacOs/OpenXR/Vulkan)

35Stars on the repository
54Mods indexed here, across every type
19d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

build-engineer

01

tweakoz/orkid

Agent Claude Code

Build/infrastructure engineer for the OBT toolchain and staging environments — obt.dep. dep builds, staging folders (/.staging-), venv layout (binpub→venv manual copy), cross-staging env hygiene, obtnet node environment setup, CMake/toolchain issues. Use for "why won't this dep/staging/toolchain build or resolve"…

35 19d ago A 104 tokens MIT

engine-implementer

02

tweakoz/orkid

Agent Claude Code

C++/pyext implementation agent for the orkid engine. Use to implement ONE precisely-scoped slice of engine work from a written spec (a JUL/plan doc section, a milestone, a fix with named seams). Give it the spec section, the trouble points that name it, and the definition of done. It edits code and gets it…

35 19d ago A 100 tokens MIT

gate-runner

03

tweakoz/orkid

Agent Claude Code

Verification agent for orkid engine work. Use after an implementation slice to run a named battery — builds (with lying-rc defense), pyext tests, canaries, bounded scene runs, fleet jobs via obtnet, artifact byte-identity/idiff/histogram comparisons — and return a verdict-first report. Give it an explicit list of…

35 19d ago A 101 tokens MIT

hub-coordinator

04

tweakoz/orkid

Agent Claude Code

HUB coordinator (formerly "master") for multi-agent orkid engine work — the integration seat. Holds the taskset and fleet manifest, decomposes outcomes into lanes and seat briefs, assigns machines/branches, briefs engine-implementer/gate-runner/vet/scout subagents, line-reviews risk surfaces, adjudicates gates, merges…

35 19d ago A 154 tokens MIT

scout

05

tweakoz/orkid

Agent Claude Code

Read-only reconnaissance agent for the orkid engine. Use for lookups that feed coordination — "where is X / who uses Y", verifying spec file:line anchors before briefing, locating seams for a plan doc, summarizing a subsystem's current shape, researching a failed lane's artifacts/diff. Returns file:line-cited…

35 19d ago A 99 tokens MIT

senior-planner

06

tweakoz/orkid

Agent Claude Code

High-effort planning/curation aide to any coordinator (hub or sub) — digests long specs/ledgers/tasksets, produces decompositions, seat briefs, disposition tables, and plan docs. Use when planning work needs deep reading or judgment but NOT engine implementation (engine-implementer), verification (gate-runner), or…

35 19d ago A 0 tokens MIT

sub-coordinator

07

tweakoz/orkid

Agent Claude Code

SUB coordinator — a seat-scoped coordinator on its own machine, working under a HUB coordinator on another machine. Runs its seat's lane with the full subagent discipline (engine-implementer/gate-runner/vet/scout), works from hub briefs delivered to /coordination/inbox plus direct owner instruction. Never loads a…

35 19d ago A 144 tokens MIT

tech-artist

08

tweakoz/orkid

Agent Claude Code

Procedural look-dev agent for orkid — authors DSL content (terrain graphs, hypermesh recipes, ptex3d materials, scatter, scene composition) to hit a NAMED visual target, thinking in industry technique (Houdini/World Machine/Blender geometry nodes/games VFX) and compiling it onto orkid primitives. Renders regular…

35 19d ago A 167 tokens MIT

vet

09

tweakoz/orkid

Agent Claude Code

Perceptual-quality analyst for orkid output artifacts — images, movies, meshes (OBJ), heightmaps. Use for open-ended quality work (why does this look wrong, review N renders, compare silhouettes across seeds, corpus sweeps, triage) AND for improving the vet instruments themselves. Instruments-first discipline; never…

35 19d ago A 90 tokens MIT