Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Q*bert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53... min • Codex: 627K tokens, 51 min Both agents built a working Q*bert, but Gitlawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!show more

Zero is amazing

Run Local AI Models and agents:

2.6x fewer tokens is actually insane

true. especially when we are speaking about limited context window :)

this is @Agent0ai not @gitlawb

Tokens optimisation 🫡

Wow. That’s great.

Cool! @gitlawb’s Zero is great indeed!!

thanks for sharing, fyi @agent0ai is not from gitlawb

Zero is hands down one of the best open-source harnesses I've used, imagine being able to invoke it right from your phone 👀👇

can i use witf gpt-gemini or claude and cline-opencode-Cursor sub in this cli tool???

Interesting… 👀

where is the prompt for this one? would love to test my private harness just to see how it compares.

Agent Zero is still around? The same Agent Zero that came out around the time CrewAI popped up? Neat, might have to revisit them

nice try... the power being showcased in this video is the real agent zero → @Agent0ai interesting that the gitlawb account doesn't even seem to know what its own software looks like

Thank you so much for showing Agent Zero capabilities and efficiency 🫶🏼

if you really want the biggest token efficiency boosts then use Grug!

2.6x fewer tokens and it actually built a working game? That's the real flex. Most "efficient" agents just output less, not better.

The token count is only part of the story.

Compare it to the cursor.

Cleaner context management = fewer hallucinations and better final output.

时间差不多，token 差这么多挺离谱

@Agent0ai

Please fight on terminal bench

Nice!

Codex used 388K extra tokens to finish 2 minutes faster. The agentic equivalent of running git log -p --all before changing 1 line.

Better output, less tokens. Zero is goated

@thsottiaux @OpenAI !!!!!

@grok what music is this? Love it

agent architecture matters a lot .

Agent One crushed Agent Zero by 5x on token efficiency

Only sending what's new instead of the whole history is such a clean fix.

one benchmark on a retro game and the headline is 2.6x lol what does this look like on something with real dependencies 😐

@all Can anyone tell me what font is used for that zero ? I’m kind of obsessed with that style of art.

It’s not @gitlawb btw, it’s a fork of agent zero (real one)