SUBMISSIONS

AGOR AI

Track: Improvements to OmegaClaw · 12 deliverables submitted

Deliverables · 12

GitHub repo — Telos (code, benchmark, results, docs)https://github.com/arielagor/telos

Start here. The README has the benchmark, the pilot and live-OmegaClaw results, an honest Status & Limitations section, and quick start. MIT, open source.

Open ↗

Case study: built with goal autonomous agent guided only by human kickoffhttps://github.com/arielagor/telos/blob/main/docs/case-study-autonomous-build.md

How Telos was designed, built, evaluated, and adversarially reviewed by a cross-family AI council under human goal-setting — including the overclaims the agents caught and walked back on their own wor

Open ↗

Architecture & concepts (explainer)https://github.com/arielagor/telos/blob/main/docs/architecture.md

The concepts behind the measurement layer: the goal graph, the 14-scenario / 7-category benchmark with gold labels, and the cross-family Beneficial Council that judges and red-teams.

Open ↗

How it fits OmegaClaw (integration)https://github.com/arielagor/telos/blob/main/docs/integration-omegaclaw.md

Where Telos plugs into OmegaClaw and its three integration levels. Now demonstrated live: the MeTTa goal schema loads and derives in OmegaClaw's running AtomSpace (see the live benchmark + setup notes

Open ↗

Walkthrough video (10.23 min, 1080p)https://github.com/arielagor/telos/releases/tag/telos-video-v1

~10-min walkthrough (synthetic avatar + AI voice, no human voiceover). Now includes the live OmegaClaw run, the 0.620 benchmark, the 5 setup fixes, and the article goal-derivation demo. Also on YouTub

Open ↗

Slide deck (PDF) — 22 slides incl. live engine + PR #218https://github.com/arielagor/telos/blob/main/telos-deck.pdf

22-slide deck: the goal graph, the benchmark, the cross-family council, plus the live OmegaClaw run and the 5 Windows/Docker setup fixes.

Open ↗

Live OmegaClaw benchmark + leaderboard (we ran it)https://github.com/arielagor/telos/blob/main/results/LEADERBOARD.md

The honest result of running the LIVE OmegaClaw agent on the Telos benchmark: 0.620 overall, 0.869 on the 10 of 14 scenarios it answered cleanly — competitive with frontier LLMs; the gap is the cost o

Open ↗

OmegaClaw Windows/Docker setup fixes (for the next person)https://github.com/arielagor/telos/blob/main/docs/omegaclaw-windows-setup.md

Five Windows/Docker rough edges we hit standing up OmegaClaw, each with the fix — making the agent easier to get started with.

Open ↗

Demo: the live agent derived its own goals from a real essayhttps://github.com/arielagor/telos/blob/main/docs/omegaclaw-article-demo.md

We set the live agent free on a real essay: using the Telos framing it derived its own goals and refused to amplify claims it couldn't verify, calling instead for an open field pilot.

Open ↗

Proof: Telos goal schema derives in the LIVE OmegaClaw AtomSpacehttps://github.com/arielagor/telos/blob/main/docs/omegaclaw-metta-load.md

The exact metta commands + the live-derived result (conflict-between alice-train dao-fair-access) from OmegaClaw's running PeTTa engine — concrete evidence for integration level 2.

Open ↗

Upstream PR to OmegaClaw-Core (#218)https://github.com/asi-alliance/OmegaClaw-Core/pull/218

An OPEN upstream PR contributing the Telos goal module (lib_telos_goals.metta) into the maintainers' repo — opt-in, additive, no core changes, and already loading + deriving in a live OmegaClaw runtim

Open ↗

Cinematic web deck (DEEP-themed, agor.me)https://agor.me/telos

A cinematic, scroll-driven web version of the deck in the DEEP Projects house style (Orbitron + DM Sans, violet/magenta/cyan). Same content as the PDF deck. Arrow keys navigate; press D for deck mode.

Open ↗