mindifact

mind + artifact — a versioned, verifiable brain for an agent.

Skills registries distribute modules. A mindifact is the whole installable mind: the rails an agent follows, the scar tissue it must not relearn, the verbs it may run inside your application, the memory it carries forward, and the evals that prove it still works.

Memory layers make an agent better-informed; a mindifact makes it qualified. The unit is never a fact — it is a proven capability: everything an agent needs to perform a defined workflow, installed as one dependency-resolved closure, with the evals that prove the task can actually be done.

Knowledge that pays for itself — and proves it. One governed conversation measured at $2.92 where the ungoverned attempts before it burned ~$17; the staged seal brief targets $0.30. Not a benchmark claim — a sealed run you can audit.

install a mind
claude plugin install parkforge-brain@mindifact
mindifact install parkforge-cinematics   # or just one domain + its deps
1 · captureruns write dated, measured memory — free-write, zero ceremony
2 · gateThe Factory: an author drafts the rule, an adversary attacks it; the promotion ledger is the audit log
3 · releaseversioned packs, per-file provenance, sealed evals — failures published, never rounded up

The unit is the task, not the fact

How a mindifact differs from a memory layer (mem0-style fact stores) — complementary layers, different jobs:

memory layermindifact
unit of value a fact — "user prefers aisle seats" a capability — "can build a fenced path, proven"
kind of knowing knowing-that (declarative recall) knowing-how (workflows, tools, traps, contracts)
loading model retrieve per query, by similarity — fits open-ended assistance install per task, the whole curated closure — fits a defined workflow
negative knowledge no concept of it traps: what must NOT be done, with the scar that taught it
composition facts do not depend on facts capabilities require capabilities — a resolved dependency graph
quality question "did I fetch the right fact, fast?" "can the agent complete the task — and can you audit the proof?"
in hiring terms the employee's notebook their training and certification

Facts still ride along — the memory compartment carries them in service of the workflow, curated rather than similarity-ranked. A memory layer could feed a mindifact's capture stage; the factory decides what becomes law.

Packs

One release train, six packs since v1.6.0: install the meta for everything, or a member pack for one domain — dependency resolution order is validated by mindifact graph.

parkforge-brainmeta-pack — the whole train, self-contained; installs everything below
parkforge-charactersMesh to talking, walking NPC: character-intake and character-dialogue. requires: parkforge-core, unreal-scripting
parkforge-cinematicsCutscene primitives (sequences, spawnable cameras, keying laws) plus the staged cinematic family briefs (stretch-limb, cutscene-grab, lead-npc, cinematic-verification). requires: parkforge-core, unreal-scripting, parkforge-characters
parkforge-coreContracts, traps, governance (brain-maintenance + factory), evals, memory, and the scene-query/world-profile verb base every other pack depends on.
parkforge-terrainGround, routes, fences: the terrain-strokes skill, the pure-math terrain core, and the terrain/route/fence toolsets. requires: parkforge-core
unreal-scriptingEngine-generic Unreal automation: Blueprint graph authoring from Python and fresh-project bootstrap.

Registry — 19 artifacts, searchable

Everything published across the known sources: mindifact packs (meshforge namespace) and agent-office skill artifacts (digest-pinned lockfile). New artifacts appear on the next site build.

parkforge-brain packv1.6.0meta-pack — the whole ParkForge train
parkforge-characters packv1.6.0Mesh to talking, walking NPC: character-intake and character-dialogue
parkforge-cinematics packv1.6.0Cutscene primitives (sequences, spawnable cameras, keying laws) plus the staged cinematic family briefs (stretch-limb, cutscene-grab, lead-npc, cinematic-verification)
parkforge-core packv1.6.0Contracts, traps, governance (brain-maintenance + factory), evals, memory, and the scene-query/world-profile verb base every other pack depends on
parkforge-terrain packv1.6.0Ground, routes, fences: the terrain-strokes skill, the pure-math terrain core, and the terrain/route/fence toolsets
unreal-scripting packv1.6.0Engine-generic Unreal automation: Blueprint graph authoring from Python and fresh-project bootstrap
cluster-update-advisor skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
find-token skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
genesis-train skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
kubernetes-docs skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
mcp-builder skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
openshift-docs skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
product-lifecycle skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
project-board-management skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
skill-creator skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
weekly-ops-report skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
wiki-clip skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
wiki-search skillv0.1.0agent-office skill artifact (OCI, digest-pinned)
wiki-write skillv0.1.0agent-office skill artifact (OCI, digest-pinned)

parkforge-brain v1.6.0 · meta-pack all versions, bundles & sources →

Agent-driven Unreal world-building for welcometotomorrow: terrain strokes, routes, asset/character pipelines, and the operating judgment distilled from the sessions that built them.

contracts2 filesinvariants an operator may never violate
skills6 skills · 23 filesoperating rails, open Agent Skills format
traps17 traps · 1 filenumbered scar tissue, each citing its failure
verbs32 filesjudgment compiled to code, installed into the host app
memory27 entriesdated observations — the only runtime-writable compartment
factory24 filesauthor/adversary briefs that gate every change
evals9 filesreplays that gate the release
118 files · 7 compartments · every file sha256'd and git-traced (91/118 from committed sources) · built 2026-08-10 17:41:48
host application: Unreal Engine 5.8 (welcometotomorrow project, ModelContextProtocol + AllToolsets + ToolsetRegistry plugins enabled)
provides unreal.terrain unreal.routes unreal.viewport unreal.character-intake unreal.character-dialogue

Install the chat half — a real Claude Code plugin

The pack emits a marketplace and a plugin that Anthropic's own tooling validates and installs. No approval process is involved: a marketplace is a git repo you host.

claude plugin marketplace add deanpeterson/mindifact
claude plugin install parkforge-brain@mindifact
claude plugin details parkforge-brain

That mounts brain-maintenance, character-dialogue, character-intake, parkforge-boot, terrain-strokes, unreal-blueprint-scripting, unreal-project-bootstrap plus the editor MCP wiring.

Get the CLI

One stdlib Python file, no dependencies, 247 KB. sha256 ea119b0f4e984b73c8da4bb84d11a00d8a5562763c90a9c45cd7b24bcfbc64c4

curl -fsSL https://mindifact.ai/mindifact -o /usr/local/bin/mindifact
chmod +x /usr/local/bin/mindifact
mindifact setup     # pointer-only config; doctor proves every credential it names
mindifact           # the guided wizard: pick a pack, answer, confirm

Install the half a plugin cannot carry

A plugin mounts skills into the agent. It has no way to put working code inside the application the agent operates, and no compartment for memory. That is the gap a mindifact fills:

python3 brainpack/pack.py install --pack <pack.tar.gz> --unreal <UnrealProject>
python3 brainpack/pack.py install --pack <pack.tar.gz> --workspace ~/AgentWorkspace

The first deploys the verbs into the project's Content/Python, templates the registration bootstrap, wires the required engine plugins, and drops a world-profile template. The second writes the boot contract, mounts the skills, and merges memory without overwriting anything the local agent has already learned.

Where the line is

This page is generated from the pack itself, so the inventory above cannot drift from reality. The roadmap below is hand-maintained and deliberately unflattering — a registry whose pitch is verification has no business overstating itself.

provenPack build with integrity90 files across 7 compartments, every one sha256'd into MANIFEST.json, with per-file git provenance (repo, commit, committed/modified status).
provenEmits a real Claude Code pluginpack.py plugin writes a marketplace; claude plugin validate passes and claude plugin install parkforge-brain@mindifact installs 7 skills + 1 MCP server, ~1,484 tokens always-on.
provenInstalls into a host applicationpack.py install --unreal deploys verbs into Content/Python, templates init_unreal.py, wires the .uproject plugins, and drops a world-profile template. This is the part a plugin cannot do.
provenInstalls into an agent workspacepack.py install --workspace writes the boot contract, mounts skills, wires MCP, and MERGES memory without clobbering entries the local agent has already written.
provenGoverned promotion loopRuns record dated learnings; the brain-maintenance skill classifies each one and routes knowledge changes through an author/adversary review gate. promote.py can report and bump versions but cannot write knowledge.
provenEval 0 — pack healthRead-only check against a live editor: verbs exposed, state stores coherent. Passes from a fresh unpack.
provenSealed eval runs — RemakeBench-shaped harnessevals/run_eval.py: frozen sha-stamped task prompts (tampering refuses to run), sealed run records (manifest + checksums + transcript), verdicts PASS / FAIL / BLOCKED — never rounded up. First scored run fenced-path-v1 published as-is: mechanical 4 PASS / 2 FAIL (cost $2.32 > $1.50 bar, duration 537s > 420s) / 2 BLOCKED, visual rubric 8/8. The failures are the roadmap: brief-verb-fenced-path-seal targets both.
partialEvals 1, 2 and 4Specs written with measurable gates (bridge replay, fresh-world bootstrap, character pipeline) plus a mechanical harness. Not yet run end to end by a fresh agent, so no scores are published here.
partialPortability beyond one projectThe world profile removed the hardcoded park constants and the identity proof passed, but only one project has been driven this way so far.
provenPublic distribution channelsThe marketplace installs from deanpeterson/mindifact (proven with Anthropic's own CLI end to end), and the pack round-trips through Quay as a digest-verified OCI artifact -- byte-identical back.
provenThe mindifact CLIOne stdlib file: install/verify/list/search plus a guided wizard that derives its questions from the pack, discovers Unreal projects, remembers answers, and shows the exact command it runs. 199 tests across five suites, two interpreters.
partialDependency modelrequires/provides/conflicts are reserved manifest fields -- parkforge-brain declares five unreal.* authorities -- with a presence check at install. No resolver, no graphs, by design until a second pack exists.
partialPublic registry + searchEach pack now gets a generated detail page (versions, bundles, skills, coordinates — see parkforge-brain), still generated from one local pack. Serving many packs, with S3-backed storage and search, is not built.
not builtPublished eval scoresThe verification pitch only becomes real when scores are produced in CI and shown next to the download. Today evals run by hand.
not builtSigning and dependenciesNo signatures, no pack-to-pack dependency resolution, no conflict detection between packs that teach contradictory rails.

Source

The pack, the emitter, the evals and this generator live in https://github.com/deanpeterson/meshforge — currently a private repository, so the link resolves only for the maintainer. The canonical brain sources sit under brain/; the marketplace is emitted by pack.py plugin.