Products, grouped by primary domain.

A square chip at the center with its pins fanned out on all four sides as thin routed traces, each ending in a small pad, and a bright core inside the chip.A square chip at the center with its pins fanned out on all four sides as thin routed traces, each ending in a small pad, and a bright core inside the chip.

36 public product records across 6 domains. Each product appears once here; the catalog records cross-domain references and evidence.

See the tools work: explainer films on the ideas behind them, and repository explainers and walkthroughs with real commands and output.

Short map, detailed record elsewhere

This page is the compact product map: one entry per product under its primary domain. The evidence registry is separate and may list the same product under additional domains with its source evidence and limitations.

Choose a route

Agent systems

6 products

Model routing, agent execution, and durable workflow state.

Flywheel

verified-inference platform and desktop client

shipped · Python engine v1.1.0 and Windows desktop v1.1.0; release reports 15 of 17 lanes reached expected classes; Index below bar without Git; Telos excluded

Flywheel runs AI tasks with the model you choose and checks each answer against the task contract.

Verified Flywheel v1.1.0

Limit: The release notes list known issues with the engine install command; read them before installing.

How we know

Flywheel runs AI tasks with the model you choose and checks each answer against the task contract. It runs on your machine from the command line, a desktop app or a local API, and sends request content only to the model provider you pick.

Status
shipped
Release
Python engine v1.1.0 and Windows desktop v1.1.0; release reports 15 of 17 lanes reached expected classes; Index below bar without Git; Telos excluded
Open product recordInspect source

Forum

multi-agent orchestration engine

shipped · stable engine v1.15.1; standalone route-preflight skill v0.1.0

Forum runs teams of AI agents.

Verified Forum v1.15.1

Limit: You supply the executors and the approval policy.

How we know

Forum runs teams of AI agents. It splits a request into dependent tasks, runs independent ones in parallel through local commands or model APIs, pauses for human approval and resumes interrupted runs. A route-preflight skill checks routing and context before model work starts.

Status
shipped
Release
stable engine v1.15.1; standalone route-preflight skill v0.1.0
Open product recordInspect source

Relay

coding agent that acts within granted permissions

active · v0.5.0 on GitHub and PyPI as flywheel-relay

Relay runs a coding agent across local models, subscription CLIs, APIs, gateways and cloud endpoints.

Verified Relay v0.5.0

Limit: The command denylist is not a security boundary.

How we know

Relay runs a coding agent across local models, subscription CLIs, APIs, gateways and cloud endpoints. It checks permissions before tool use, fails over between providers, runs your acceptance checks, resumes sessions and connects to MCP servers.

Status
active
Release
v0.5.0 on GitHub and PyPI as flywheel-relay
Open product recordInspect source

Mneme

agent memory store with repeatable recall

active · v0.5.1 on GitHub and PyPI as flywheel-mneme

Mneme is a SQLite memory store for AI agents, with a CLI and an MCP server.

Verified Mneme v0.5.1

Limit: Mneme publishes on PyPI as flywheel-mneme. The PyPI name mneme-memory belongs to another publisher.

How we know

Mneme is a SQLite memory store for AI agents, with a CLI and an MCP server. It stores conversation turns and imported sources, answers recall queries with BM25, vector and recency ranking, shows where each recalled fact came from, and logs every update and deletion.

Status
active
Release
v0.5.1 on GitHub and PyPI as flywheel-mneme
Open product recordInspect source

Canon

command-line tool that packages memory for AI assistants

active · v0.4.2 on GitHub and PyPI as flywheel-canon

Canon turns local memory records into instruction files for Codex, Claude Code and other agent hosts.

Verified Canon v0.4.2

Limit: Canon reads only the local JSONL files you give it, never provider accounts, credentials or chat history.

How we know

Canon turns local memory records into instruction files for Codex, Claude Code and other agent hosts. It previews what each host will receive, exports Markdown or JSON, and edits only the regions of an instruction file that you mark for it.

Status
active
Release
v0.4.2 on GitHub and PyPI as flywheel-canon
Open product recordInspect source

Bulletin

public message board for AI agents

active · GitHub release v0.5.0; deployed board contract 0.5.0

Bulletin is a public message board that AI agents read and write over HTTP or MCP.

Verified Bulletin v0.5.0

Limit: Treat every post as untrusted input. The board does not filter prompt injection.

How we know

Bulletin is a public message board that AI agents read and write over HTTP or MCP. Each poster signs with a key, any agent can register with one command, and a reader can acknowledge exactly which page of its inbox it handled.

Status
active
Release
GitHub release v0.5.0; deployed board contract 0.5.0
Open product recordInspect source

Evaluation and verification

6 products

Tools that test AI output, claims and data.

Service Desk Incident Environment

synthetic incident environment and offline review add-on

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

A Flywheel add-on that runs synthetic service-desk incident workflows and writes an offline HTML report of the claims, task outcomes and contradictions in each run.

Verified Service Desk Incident Environment 0.2.0

Limit: Needs a separately installed Flywheel engine, version 0.6.1 up to but not including 0.7.

How we know
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
Open product recordInspect source

Crucible

engine that tests claims against evidence

shipped · stable v1.3.0 on GitHub and PyPI

Crucible is test infrastructure for claims about AI systems.

Verified Crucible v1.3.0

Limit: Missing or ill-posed evidence fails closed.

How we know

Crucible is test infrastructure for claims about AI systems. You split a thesis into claims, each with a failure condition, and Crucible checks them against the evidence or commands you supply and returns MATCH, DRIFT or UNVERIFIABLE for each one.

Status
shipped
Release
stable v1.3.0 on GitHub and PyPI
Open product recordInspect source

EMET

checker that content still matches its source

shipped · stable v1.3.0 on GitHub and PyPI

EMET checks whether the bytes that reach a model, reviewer or pipeline still match their source.

Verified EMET v1.3.0

Limit: EMET compares bytes. It does not judge what the content says.

How we know

EMET checks whether the bytes that reach a model, reviewer or pipeline still match their source. It anchors content, compares it later, neutralizes instructions embedded in it, and writes a verdict file that its Python, Rust, Node and Go implementations all read the same way.

Status
shipped
Release
stable v1.3.0 on GitHub and PyPI
Open product recordInspect source

Model Provenance Validator

checker for records tying model claims to sources

shipped · alpha v0.1.1

Model Provenance Validator checks JSON records that link a model or release claim to its sources and retrieval dates, redacts credential-like values from its output, and can emit a Proof Surface packet.

Verified Model Provenance Validator v0.1.1

Limit: It validates the record. It does not fetch the sources.

How we know
Status
shipped
Release
alpha v0.1.1
Open product recordInspect source

Repo Proof Index

evidence index and reviewer handoff

shipped · alpha v0.2.0 on GitHub and PyPI

Repo Proof Index scans the proof packets, receipts and contracts in a repository and builds a reviewer index with the type, status, summary and path of each file.

Verified Repo Proof Index v0.2.0

Limit: It validates known packet formats only.

How we know
Status
shipped
Release
alpha v0.2.0 on GitHub and PyPI
Open product recordInspect source

Articulate

local prose checker

shipped · v0.5.0 on GitHub and PyPI; v0.6.0 is not published and its confirmatory release gate failed

Articulate is prose analysis and model-assisted editing for the command line, editors and CI.

Verified Articulate v0.5.0

Limit: The judge, fix and polish editors send the draft to the model you choose. The checks run offline.

How we know

Articulate is prose analysis and model-assisted editing for the command line, editors and CI. It names each writing pattern it finds and the line it is on, in the terminal, in an editor through its language server, or as SARIF in code review.

Status
shipped
Release
v0.5.0 on GitHub and PyPI; v0.6.0 is not published and its confirmatory release gate failed
Open product recordInspect source

Security and privacy

6 products

Security tooling and privacy controls.

Proof Surface

library that checks AI permission and evidence records

active · 0.1.0 on PyPI; active source 0.2.0 with no release

Proof Surface is a Python library and telos-proof CLI that validates records of AI workflow steps, authorizations, delegations and finished work, and returns allow, deny or needs-human recommendations.

Verified proof-surface 0.1.0 on PyPI

Limit: Your system enforces the decision; Proof Surface only recommends.

How we know

Proof Surface is a Python library and telos-proof CLI that validates records of AI workflow steps, authorizations, delegations and finished work, and returns allow, deny or needs-human recommendations. It never runs the action itself.

Status
active
Release
0.1.0 on PyPI; active source 0.2.0 with no release
Open product recordInspect source

Phantom

hardware-identity privacy system

shipped · stable v1.1.1

Phantom helps you inspect and, when authorized, change the hardware identifiers a computer exposes.

Verified Phantom v1.1.1

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

How we know

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 v1.1.1
Open product recordInspect source

behavior-transform.io

local wrapper for file, web, and tool input and output

active · active public source; no tagged release

behavior-transform.io is a local Python wrapper and hook layer for file reads and writes, subprocesses, HTTP fetches, user input and MCP traffic.

Verified behavior-transform.io public source

Limit: No tagged release yet.

How we know

behavior-transform.io is a local Python wrapper and hook layer for file reads and writes, subprocesses, HTTP fetches, user input and MCP traffic. Given a request, a mode and local text rules, it passes the content through or transforms it, and returns the result with hashes and substitution counts.

Status
active
Release
active public source; no tagged release
Open product recordInspect source

Accountable Surface

workbench that allows only approved AI agent actions

active · 0.3.1 on PyPI; latest GitHub release v0.2.0

Accountable Surface lets an AI agent take only the file, command, web or browser actions a person has approved.

Verified accountable-surface 0.3.1 on PyPI

Limit: Windows desktop-app control has been tested only against a fake UI Automation driver.

How we know

Accountable Surface lets an AI agent take only the file, command, web or browser actions a person has approved. It checks each request, blocks or pauses when needed, checks the outcome, rolls back reversible failures, and keeps a hash-chained journal of decisions and outcomes.

Status
active
Release
0.3.1 on PyPI; latest GitHub release v0.2.0
Open product recordInspect source

Public Surface Sweeper

checker run before a repository goes public

shipped · v0.1.3 on GitHub and PyPI

Public Surface Sweeper checks a repository or local portfolio before you publish it: missing public files, unclear README handoff, credential-like strings, release metadata, proof-packet readiness and drift across a workspace.

Verified Public Surface Sweeper v0.1.3

Limit: It checks release hygiene only; use a vulnerability scanner for dependencies and exploits.

How we know
Status
shipped
Release
v0.1.3 on GitHub and PyPI
Open product recordInspect source

Secret Redact IO

library that redacts secrets from file and tool output

shipped · stable v0.1.0

Secret Redact IO is a Python library that redacts secrets from file, fetch, write and subprocess output.

Verified Secret Redact IO v0.1.0

Limit: Release 0.1.0 installs as io-guardrails with the io-guard command. The source has since been renamed secret-redact-io, and no package by either name is on PyPI.

How we know
Status
shipped
Release
stable v0.1.0
Open product recordInspect source

Developer infrastructure

5 products

Tools that make building, integrating, and releasing systems more reliable.

Telos

local workbench for creating and replaying AI work

active · GitHub release v0.4.1; no npm package

Telos is a local workbench for running and replaying AI work.

Verified Telos v0.4.1

Limit: Interfaces may change before 1.0.

How we know

Telos is a local workbench for running and replaying AI work. Its CLI and MCP servers run workstation checks, creative simulations, research experiments, and browser or Windows automation, and save each run so it can be replayed.

Status
active
Release
GitHub release v0.4.1; no npm package
Open product recordInspect source

Index

workspace map and context system

shipped · GitHub and PyPI release 2.13.0; wheel and source digests match across both channels

Index maps a repository or a multi-repo workspace from its manifests, imports, symbols and docs.

Verified Index v2.13.0

Limit: Dynamic imports and unsupported structures can be missed.

How we know

Index maps a repository or a multi-repo workspace from its manifests, imports, symbols and docs. It builds offline wikis, dependency maps, context packets for agents and architecture checks, each pointing to a file and line. Large workspaces can run as background jobs you check on later.

Status
shipped
Release
GitHub and PyPI release 2.13.0; wheel and source digests match across both channels
Open product recordInspect source

BuildLang

systems language and compiler toolchain

shipped · GitHub release v1.4.0; buildlang 1.2.0 on crates.io; non-C backends experimental

BuildLang is a systems programming language in which a program declares what it is allowed to touch.

Verified BuildLang v1.4.0

Limit: C is the production backend. SPIR-V, LLVM, WebAssembly, Rust, native-object backends, GPU compute and linear types are experimental.

How we know

BuildLang is a systems programming language in which a program declares what it is allowed to touch. The compiler checks those declarations and its memory rules, then emits native code through C. It ships with a CLI, editor support, two-way C integration and experimental shader output.

Status
shipped
Release
GitHub release v1.4.0; buildlang 1.2.0 on crates.io; non-C backends experimental
Open product recordInspect source

Plexus

tool discovery and wiring for AI agents

active · 0.2.2 on PyPI as plexus-mesh; latest GitHub release v0.2.1

Plexus finds which of your agent tools can feed each other.

Verified plexus-mesh 0.2.2 on PyPI

Limit: Connections come from what each tool declares; run the pipeline to confirm they work.

How we know

Plexus finds which of your agent tools can feed each other. It reads the inputs and outputs each tool declares and produces a dependency graph or a runnable pipeline script, from the command line or over MCP.

Status
active
Release
0.2.2 on PyPI as plexus-mesh; latest GitHub release v0.2.1
Open product recordInspect source

Agent Hook Pack

repository hook toolkit

shipped · stable v0.1.0

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

Verified Agent Hook Pack v0.1.0

Limit: Private policy layers are left out of the public package.

How we know
Status
shipped
Release
stable v0.1.0
Open product recordInspect source

Graphics and media

10 products

Rendering, color, audio, image, and generative production systems.

Studio Engine

procedural audiovisual engine

active · active pre-1.0 source 0.2.0; no release

Studio Engine is a local Python engine that turns one scene description into shader visuals, audio and motion.

Verified Studio Engine optional RAW CLI bridge

Limit: Pre-1.0: APIs may change. The native renderer is optional.

How we know

Studio Engine is a local Python engine that turns one scene description into shader visuals, audio and motion. It has a CLI and a local HTTP API and renders deterministic PNG frames.

Status
active
Release
active pre-1.0 source 0.2.0; no release
Open product recordInspect source

Build Color

color-science library and workbench

active · beta source 1.0.2; latest tag v1.0.1

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

Verified Build Color v1.0.1

Limit: The GUI and the fuller numerical stack need optional dependencies.

How we know
Status
active
Release
beta source 1.0.2; latest tag v1.0.1
Open product recordInspect source

Retro Engine

embedded browser visual and audiovisual studio

active · active public application; no package release

Retro Engine is an embedded browser studio for images, drawing, GLSL, and audio traces.

Verified Retro Engine owned site source

Limit: Output can differ by browser, GPU and audio host.

How we know

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
Open product recordInspect source

Engine Revival

archival/revival evidence platform

shipped · stable v0.1.0

Engine Revival is a Python tool for building, checking and publishing metadata about revived historical engines.

Verified Engine Revival v0.1.0

Limit: Engine Revival handles metadata and build scaffolding. The BRender build and its test results live in BRender Archival.

How we know

Engine Revival is a Python tool for building, checking and publishing metadata about revived historical engines. It can also generate an out-of-tree BRender CMake build harness from a public checkout.

Status
shipped
Release
stable v0.1.0
Open product recordInspect source

BRender Archival

BRender restoration and build-test harness

shipped · bounded milestone v0.1.1

BRender Archival rebuilds the Argonaut BRender engine from its public MIT source, runs it through a 21-stage native test ladder, captures renders, and packages the build harness, test transcripts and checksums without copying the upstream source.

Verified BRender Archival v0.1.1

Limit: Textured TIA output and x64 builds are not finished.

How we know
Status
shipped
Release
bounded milestone v0.1.1
Open product recordInspect source

Elder ENB

ENB shader suite

active · prerelease v1.0.0-rc.5

Elder ENB is an ENBSeries 0.504 shader suite for Skyrim SE/AE, with nine stages, five quality tiers, cinematic effects and an optional native frame-pulse runtime.

Verified Elder ENB runtime-core build linkage

Limit: The latest tag, v1.0.0-rc.5, is a prerelease.

How we know
Status
active
Release
prerelease v1.0.0-rc.5
Open product recordInspect source

Truth ENB

ENB shader suite

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

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.

Verified Truth ENB 1.0.0 source

Limit: Public upload waits on live testing with Skyrim SE/AE and ENB 0.504.

How we know
Status
active
Release
release-candidate source 1.0.0; tag v1.0.0-rc.1
Open product recordInspect source

ENB Runtime Core

embedded runtime library

active · active source 0.1.0; no GitHub release

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.

Verified ENB Runtime Core public source 0.1.0

Limit: Needs an ENBSeries host that is already loaded. Source 0.1.0 has no GitHub release.

How we know
Status
active
Release
active source 0.1.0; no GitHub release
Open product recordInspect source

SkyrimBridge

Skyrim plugin linking game data to shaders and tools

active · prerelease v3.0.0-rc.1

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.

Verified SkyrimBridge public source 3.0.0

Limit: The default build leaves out the native replacement suite.

How we know
Status
active
Release
prerelease v3.0.0-rc.1
Open product recordInspect source

RAW

C++23 CPU reference renderer

active · public release 0.2.0

RAW is a dependency-free C++23 renderer that draws a scene on the CPU, checks its fast screen-space ambient occlusion against a ray-traced reference, and writes a JSON certificate saying whether the shortcut held.

Verified raw-native 0.2.0

Limit: One built-in test scene, no model loader, and no GPU or WebAssembly build in this release.

How we know
Status
active
Release
public release 0.2.0
Open product recordInspect source

Research and education

3 products

Research intake, learning systems, publications, and teaching surfaces.

Gather

research intake and corpus system

shipped · stable v1.9.1 on GitHub and PyPI

Gather collects research material from web pages, including JavaScript-rendered ones, APIs, scholarly records, PDFs, scans, audio, video, feeds and local files.

Verified Gather v1.9.1

Limit: Static web mode does not run JavaScript.

How we know

Gather collects research material from web pages, including JavaScript-rendered ones, APIs, scholarly records, PDFs, scans, audio, video, feeds and local files. It saves each item with its source in a local corpus you can search and verify.

Status
shipped
Release
stable v1.9.1 on GitHub and PyPI
Open product recordInspect source

Learn

learning and coursework system

shipped · published npm 1.6.0; no GitHub release

Learn plans study sessions from your objectives and recorded attempts, using spaced review, retrieval practice, prerequisite checks and misconception tracking.

Verified Learn public source

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

How we know

Learn plans study sessions from your objectives and recorded attempts, using spaced review, retrieval practice, prerequisite checks and misconception tracking. It can also handle course logistics and stops at graded work.

Status
shipped
Release
published npm 1.6.0; no GitHub release
Open product recordInspect source

Chorus

discourse synthesis system

active · v0.3.1 on PyPI as chorus-discourse; latest GitHub release v0.3.0

Chorus turns a captured comment thread or corpus into ranked, clustered theme digests, and checks whether a set of gathered sources has changed since a reference set.

Verified chorus-discourse 0.3.1 on PyPI

Limit: Sentiment is English and literal, so sarcasm can be missed. Clustering is lexical.

How we know
Status
active
Release
v0.3.1 on PyPI as chorus-discourse; latest GitHub release v0.3.0
Open product recordInspect source