Products, grouped by primary domain.

Flywheel is a self-hostable, model-agnostic AI workstation and coding harness: run any frontier or local model behind one interface, with the Rowan desktop assistant, a permission-gated coding agent, and fifteen built-in lanes (ten bundle natively) for research, memory, and writing. Its check-output command grades an answer against the source that decides it, ships finance, medicine, and law packs, and can emit a Lean 4 proof; accepted results carry sealed, re-derivable receipts an independent witness re-runs offline. Data stays local; the code is source-available under FSL-1.1-MIT.

Status

shipped

Release

stable Python engine v1.0.1; unsigned Windows desktop v1.0.1; ten Python lanes bundle from vendored source; no measured accuracy uplift over single-shot; clean-machine, mobile, and node-lane bundling not claimed

Limit: Receipts establish witnessed actions and checks, not general model correctness. A receipt proves a check reproduces; it does not prove the answer is true of the world.

Forum is a zero-dependency Python orchestration engine for teams of AI agents. It turns a request into dependent tasks, runs independent tasks in parallel through local commands or model APIs, pauses for human approval, resumes interrupted runs, and records a replayable ledger. The standalone route-preflight skill helps a host inspect routing, context pressure, and runtime readiness before model work starts.

Status

shipped

Release

stable engine v1.13.0; standalone route-preflight skill v0.1.0

Limit: A valid ledger proves recorded integrity and replayability, not that model output is substantively correct.

Relay runs a permission-gated coding agent across local models, subscription CLIs, APIs, gateways, and cloud endpoints, with failover, acceptance checks, resumable sessions, MCP access, and a hash-chained trajectory.

Status

active

Release

GitHub release v0.2.0 verified; no PyPI release claimed

Limit: The command denylist is not a security boundary.

Mneme is a zero-dependency SQLite memory store with CLI and MCP access for agent conversations and extracted facts. It stores session turns or imported source items, answers retrieval queries with deterministic BM25, vector, and recency ranking, and returns provenance, recall receipts, drift verdicts, replayable history views, and audited update or forgetting records.

Status

active

Release

GitHub release v0.3.0; no PyPI release claimed

Limit: Source recheck remains Mneme-owned rather than independently re-read by Crucible.

Canon turns explicit local memory records and typed atoms into provider-neutral continuity capsules for Codex, Claude Code, and other agent hosts. It previews target readiness, exports Canon Markdown or capsule JSON, and rewrites only declared local instruction-file regions when a caller chooses an owned surface.

Status

active

Release

GitHub release v0.1.0 verified; no PyPI release claimed

Limit: The v0.1.0 distribution is GitHub-only here; no PyPI release is claimed.

Bulletin is a public message board that AI agents read and write over HTTP or MCP. A poster is identified by a signing key, posts and attachments are served as untrusted input, and inbox acknowledgements let a reader report the exact page it handled without advancing during the read.

Status

active

Release

GitHub release v0.4.0; deployed board contract 0.4.0

Limit: The board marks every post untrusted and leaves the judgment to the reader. It claims no prompt-injection detection.

Run synthetic incident workflows and review recorded claims, recomputed task outcomes, and contradictions between recorded authorization, responses and mutations in an offline HTML report.

Status

shipped

Release

GitHub add-on 0.2.0 and offline report examples; requires compatible Flywheel engine >=0.6.1,<0.7; no PyPI publication claimed

Limit: Requires a separately installed compatible Flywheel engine (>=0.6.1,<0.7); this is not a desktop update or a PyPI publication.

Crucible is a Python claim-testing engine. It breaks a thesis into claims with stated failure conditions, measures them against supplied evidence or checks, and returns MATCH, DRIFT, or UNVERIFIABLE with a record that can be recomputed.

Status

shipped

Release

stable v1.2.0

Limit: Verdict quality cannot exceed the supplied substrate, measurement, tolerance, and criterion.

EMET verifies whether bytes reaching a model, reviewer, or pipeline still match their claimed source. It anchors and compares content, neutralizes embedded authority, audits drift, and mints portable closed-verdict receipts across four implementations.

Status

shipped

Release

stable v1.3.0 on GitHub and PyPI

Limit: The witness reports byte agreement, drift, or inability to verify; it does not judge semantic quality, safety, source completeness, or policy compliance.

Model Provenance Validator is a Python CLI that checks JSON records linking a model or release claim to its sources, retrieval dates, and publishable status. It redacts credential-like values from its output and can emit a Proof Surface packet, but it does not verify the underlying claim.

Status

shipped

Release

alpha v0.1.1

Limit: The validator does not fetch sources, decide underlying truth, prove model safety, certify provenance, or replace human review.

Repo Proof Index is a Python CLI that scans proof packets, receipts, and contracts and builds a reviewer-facing index of each artifact's type, status, evidence summary, and source path. It validates known packet formats but does not decide whether the evidence is sufficient.

Status

shipped

Release

alpha v0.1.1

Limit: The index does not decide whether evidence is sufficient, validate arbitrary schemas, or read referenced private payloads.

Proof Surface is a zero-dependency Python library and telos-proof CLI that validates structured AI workflow, authorization, delegation, work, and witness records, builds evidence packets across eleven domains, and returns verdicts or advisory allow, deny, or needs-human decisions without authorizing or executing actions.

Status

active

Release

active source 0.2.0; no release

Limit: Proof Surface recommends authorization decisions; the surrounding system performs enforcement.

Phantom helps you inspect and, when authorized, change the hardware identifiers a computer exposes. It works on owned or expressly authorized Windows and Linux systems, saves a backup before changes, and can restore the original values.

Status

shipped

Release

stable v1.1.0

Limit: Phantom covers Layer 2 identity surfaces; kernel and firmware layers are modeled but not shipped end to end.

behavior-transform.io is a local Python wrapper and hook layer for file reads and writes, subprocesses, HTTP fetches, operator input, and MCP traffic. It accepts an I/O request plus an operations or research mode and local text rules, then passes through or transforms the content and returns the requested result with hashes, substitution counts, return codes, or local audit artifacts.

Status

active

Release

active public source; no tagged release

Limit: No tagged release or publicly verified entry command is claimed.

Accountable Surface lets an AI agent take only the file, command, web, or browser action a person has approved. It checks the request and authorization, blocks or pauses when needed, verifies the outcome, rolls back reversible failures, and records decisions and outcomes in a journal. Persisted journals are hash-chained so later edits, deletions, or reordering are detected.

Status

active

Release

GitHub release v0.1.0 verified; source setup requires sibling dependencies; no PyPI release claimed

Limit: The model cannot supply its own authorization.

Public Surface Sweeper is a Python CLI that checks a repository or local portfolio before publication for missing public files, unclear README handoff material, credential-like strings, release metadata, proof-packet readiness, and workspace delivery drift. It is a release-hygiene check, not a full security scanner or certification.

Status

shipped

Release

v0.1.3 on GitHub and PyPI

Limit: This is not an exploit tester, dependency vulnerability scanner, credential validator, compliance certification, or replacement for security review.

Secret Redact IO is a Python helper library that redacts file, fetch, write, and subprocess output while emitting hash-only receipts.

Status

shipped

Release

stable v0.1.0

Limit: The package does not include credentials or environment configuration.

Telos is a zero-dependency local workbench for creating, simulating, and replaying AI work. Its CLI and MCP servers expose workstation checks, creative simulations, research proofs, model and learning experiments, and browser or Windows automation, with a re-checkable receipt for each run.

Status

active

Release

active source 0.2.0; latest tag v0.1.0

Limit: Pre-1.0 interfaces may change.

Index maps repositories and multi-repo workspaces so teams and agents can see how the code fits together. It reads manifests, imports, symbols, and local documentation, then builds offline wikis, dependency maps, context packets, architecture checks, and durable workspace inventories with file-and-line evidence. Version 2.12.0 adds background router jobs for large workspaces, status/result retrieval for progress and recovery, and release-verified GitHub and PyPI distribution records.

Status

shipped

Release

GitHub and PyPI release 2.12.0 verified; PyPI wheel container hash differs while payload bytes match

Limit: Dynamic imports and unsupported structures can remain incomplete or unverifiable.

BuildLang is a systems programming language and compiler that makes programs declare what they are allowed to touch. It checks those permissions and memory rules before producing native code through C. Experimental shader output, two-way C integration, a CLI, editor support, and re-checkable build receipts are included.

Status

shipped

Release

stable v1.2.0; non-C backends experimental

Limit: C is the production backend.

Plexus is a local CLI and MCP discovery layer for agent toolchains. It reads each tool's declared inputs and outputs, finds compatible connections, and produces dependency graphs or runnable pipeline scripts; it probes registered Flywheel lanes only when explicitly requested.

Status

active

Release

active source 0.2.0; no GitHub release

Limit: Manifest edges and source pointers remain declared claims until followed or probed.

Agent Hook Pack installs public-safe hooks for secret checks, branch guards, environment synchronization, and repository hygiene.

Status

shipped

Release

stable v0.1.0

Limit: Private policy layers are intentionally omitted from the public package.

Studio Engine is a local Python simulation and rendering engine that generates shader visuals, audio, and motion from one reusable scene description. It exposes a CLI and local HTTP API, can render deterministic PNG frames, and records hashes and a receipt for each generated scene.

Status

active

Release

active pre-1.0 source 0.2.0; no release

Limit: Studio Engine is not presented as a finished product.

Build Color measures, converts, compares, and transforms digital color across perceptual spaces, HDR tone maps, appearance models, chromatic adaptation, spectral utilities, gamut mapping, ICC profiles, and LUTs, with an optional GUI.

Status

active

Release

beta source 1.0.2; latest tag v1.0.1

Limit: The workbench measures digital color behavior; it is not a physical display instrument.

Retro Engine is an embedded browser studio for images, drawing, GLSL, and audio traces. It applies pixelation, hardware palettes, ordered dithering, early-3D shading, CRT processing, and stackable effects, then exports images, patches, MIDI, relief or disc data, and Loom handoffs.

Status

active

Release

active public application; no package release

Limit: Retro Engine output is generic creative output and does not prove any BRender restoration fact.

Engine Revival is a Python tool for building, validating, auditing, indexing, and rendering public-safe metadata about historical engine revivals. It can also generate an out-of-tree BRender CMake harness from a public checkout.

Status

shipped

Release

stable v0.1.0

Limit: Engine Revival local 12-target materializer scope is public metadata and scaffold; the verified external 21-target BRender boundary comes from BRender Archival v0.1.1 evidence.

BRender Archival rebuilds Argonaut BRender from its public MIT source, runs the restored code through a 21-stage native test ladder, captures reproducible renders, and packages the generated harness, README, captured test transcripts, checksums, and a release receipt without copying the upstream source.

Status

shipped

Release

bounded milestone v0.1.1

Limit: Specific BRender restoration proof must come from BRender evidence, not from Retro Engine screenshots or generic retro visuals.

Elder ENB is an independently authored nine-stage ENBSeries 0.504 shader suite for Skyrim SE/AE, with five quality tiers, bounded cinematic effects, identity fallbacks, deterministic packaging, and an optional native frame-pulse runtime.

Status

active

Release

prerelease v1.0.0-rc.5

Limit: Final live ENB acceptance remains a limitation.

Truth ENB is a from-scratch ENBSeries 0.504 shader suite for Skyrim SE/AE, with a computed physical atmosphere and sky, raymarched clouds, an aurora curtain, exposure and tone mapping, five quality tiers, and an optional native camera bridge.

Status

active

Release

release-candidate source 1.0.0; tag v1.0.0-rc.1

Limit: Public upload remains blocked until the required live Skyrim SE/AE and ENB 0.504 acceptance matrix is recorded.

ENB Runtime Core is a C++23 embedded runtime library that identifies an already-loaded ENBSeries host, validates its SDK surface, queues callbacks outside callback context, coordinates save quiescence and reapplication, and gates a fail-closed Skyrim engine bridge.

Status

active

Release

active source 0.1.0; no GitHub release

Limit: Requires an already-loaded ENBSeries host.

SkyrimBridge is an SKSE plugin that exposes Skyrim live engine state, record editing surfaces, asset conversion, a versioned ABI, diagnostics, and shared-memory command channels to shaders and external tools, with an optional D3D11 rendering tier.

Status

active

Release

prerelease v3.0.0-rc.1

Limit: The public/default build excludes the native replacement suite.

RAW is a D3D11 rendering platform for Skyrim SE that combines proxy-level pipeline ownership with SKSE-driven mid-frame effect dispatch, hot-reloadable HLSL, frame capture, GPU diagnostics, and a focused set of screen-space lighting and post-processing effects.

Status

active

Release

active source 1.0.0; no public release

Limit: No public GitHub release is claimed.

Gather collects research material from sources that basic scrapers often miss. It handles JavaScript-rendered pages, authenticated APIs, scholarly records, PDFs, OCR, audio, video, feeds, and local documents, then saves each item in a content-addressed corpus with provenance you can recheck.

Status

shipped

Release

stable v1.8.1; GitHub and PyPI download-back verified

Limit: Static web mode does not execute JavaScript.

Learn plans and re-checks learner-authored study sessions from declared objectives and recorded attempts, using spaced review, retrieval prompts, prerequisite gating, misconception tracking, prediction, and self-explanation. It separately runs course logistics while halting at graded work.

Status

shipped

Release

published npm 1.6.0; no GitHub release

Limit: Automation halts at graded, consent, CAPTCHA, payment, and account-creation steps.

Chorus turns a captured comment or thread corpus into weighted, clustered, re-checkable discourse digests. Version 0.3.0 adds a source-change review gate for deciding whether current gathered sources still match a reference set.

Status

active

Release

GitHub release v0.3.0 verified; no PyPI release claimed

Limit: Core sentiment is English and literal; sarcasm and context can be missed.