Anton Razzhigaev

Ph.D, AI researcher, Head of AI

[Anton Razzhigaev @AbstractDL]

Finally tech report about Ouroboros. How we achieved SOTA on Terminal-Bench and OSWorld and how to make autonomously evolving agents safe.

https://t.co/lKvvjk7ZsR

[Anton Razzhigaev @AbstractDL]

@_alphashark_ Yep, the spike came from GitHub Trending. I only posted this after it had already crossed 1K, so X gets no credit here :)

[Anton Razzhigaev @AbstractDL]

Ouroboros hit GitHub Trending for this week and crossed 1K stars.

I wired in Claudexor: connect multiple OAuth accounts for Claude Code, Codex, and Cursor. Claude Code and Codex get automatic quota rotation.

https://t.co/fOgErVbzNa

[Anton Razzhigaev @AbstractDL]

Everything is public and reproducible:

GitHub: https://t.co/fOgErVbzNa
Desktop app: https://t.co/M2LyaTSj5i

[Anton Razzhigaev @AbstractDL]

Ouroboros is now SOTA on Terminal-Bench 2.1, OSWorld-Verified, and CL-Bench.

It started as a crooked pure-Python agent loop in Google Colab. A few months of self-evolution later, it beats Codex, Claude Code, Cursor, and Hermes on the main coding / computer-use benchmarks.

I now do almost all of my research and development through it.

Code, scripts, methodology, and full traces are public.

P.S. Agent benchmarks are insanely expensive. Running the full suite costs about as much as an apartment. Not a joke.

[Anton Razzhigaev @AbstractDL]

Claudexor v3 has now passed 2,500 downloads and 300 GitHub stars.
If you have several Claude Code or Codex subscriptions, you can add all of them to Claudexor.

It monitors the quota available on each account and automatically routes the next step to another account when the current one runs out, while passing along the task state needed to continue.

v3.1.2 is available now. MIT licensed, and open to issues and PRs:
https://t.co/jCehzlmXZA

[Anton Razzhigaev @AbstractDL]

@HopeEvolving Elaborate, i didn’t get it

[Anton Razzhigaev @AbstractDL]

Each candidate runs in its own isolated Git worktree from the same snapshot, so they can’t step on each other. Claudexor reviews and compares the resulting diffs, then applies only the verified winner. If the repo changed meanwhile or the patch conflicts, it refuses instead of overwriting anything.

[Anton Razzhigaev @AbstractDL]

I got tired of choosing between Claude Code, Codex and Cursor — and manually switching whenever one of them hit a limit.
So I built Claudexor: a harness-agnostic control plane that routes work across them, runs them in parallel and makes them review each other.
Open-sourcing it today.

[Anton Razzhigaev @AbstractDL]

The nicest part: you can use Claudexor from inside your favorite coding agent.
“Before implementing this plan, roast it through Claudexor in multi-harness mode.”
“After finishing, run a multi-model review and fix the findings in a loop.”
I use it from Claude Code most of the time.
MIT licensed. Issues, feedback and PRs are welcome.
GitHub: https://t.co/34xAtpDBJl
npm: https://t.co/2U8TuvfVym

[Anton Razzhigaev @AbstractDL]

My personal API burn went from roughly $15k/month to about $1.2k/month in subscriptions.
I currently have 3 Claude Code, 3 Codex and 3 Cursor subscriptions.
This is my workload and my particular degree of illness — not a promise that everyone will get the same savings.

[Anton Razzhigaev @AbstractDL]

@sichuantofu Sure

[Anton Razzhigaev @AbstractDL]

Daily reminder what agentic harness is

[Anton Razzhigaev @AbstractDL]

https://t.co/vP67SRU4dj

[Anton Razzhigaev @AbstractDL]

Fun fact: Fable-5 is 3x cheaper than gpt-5.5-pro on OpenRouter. So... not actually that expensive 🤷‍♂️

[Anton Razzhigaev @AbstractDL]

@HopeEvolving And how is it?