My Hermes Agent just fixed a broken repo with every token generated on one desk-sized…
This is a AI post classified by AGK Intelligence as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Ripple-65B Preview × DGX My Hermes Agent just fixed a broken repo with every token generated on one desk-sized box. No cloud. The repo had 4 failing tests. Hermes read the code, found all 4 bugs, patched them and re-ran the tests on its own. 5/5 pass in 1m 36s, 14 tool calls, about 44 W of GPU power. The model behind it is Ripple-65B Preview from @RicursiveAI, a 65B dense, Apache 2.0 model that beats Meta's 816B Muse Spark Open on Terminal-Bench 2.1 (80.5 vs 76.4, self-reported). I put it on our NVIDIA GB10 DGX box to see if it holds up as a real agent backend. It does. Setup: NVFP4 weight
Posted by HOPE. (2.6k followers) 1 days ago · 6 likes · 434 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Qwen 4 (unnamed quant) — @loktar00
- 北冥有鱼，其名为鲲。 — @NFT_Chen
- If you want to get started with Local AI but dunno where to start, THIS IS FOR YOU 🚨 — @javierbits
- 💥重磅！Qwen3.8-Flash-Next 量化版炸裂升级：Token消耗直接腰斩50%，准确率暴涨15%！本地32GB丝滑跑通125B级MoE！ — @NFT_Chen
- This could be so cool. — @niklaslenz_ai
- Qwen is teasing a new model — @RoundtableSpace
- 时代变了，以前是token每秒，有人提出了秒每token。。。。 — @mylifcc
- Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use. — @UnslothAI
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.