{"slug": "show-hn-ototo-a-tool-to-offload-code-exploration-to-a-smaller-model", "title": "Show HN: Ototo: A tool to offload code exploration to a smaller model", "summary": "Developer EOL released Ototo, a tool that offloads code exploration and other token-heavy tasks to a smaller model and returns the result to the main agent, running on Qwen 3.8 27B via a custom inference engine called Shocho built for AMD hardware. Ototo's creator claims it saves tokens versus Anthropic's own exploration agent by using a cheaper or free local model and keeping the main context clearer, and says tests comparing subsequent commits of large repos across Claude, Claude plus an exploration agent, and Claude plus Ototo showed Ototo helped. The project is hosted at ototo.dev and was posted to Hacker News with 1 point and 0 comments.", "body_md": "Hey all - I made a thing with my clanker Kevin: Ototo ([https://ototo.dev/](https://ototo.dev/)) - *yes this is clanker driven dev*. The idea is to offload code exploration and other token'y heavy tasks to a smaller model to do the work and chuck the result back. This helps in a couple of ways (1) it saves tokens if you can offload to a cheaper or free local model (2) it can keep the main context clearer as it removes all the sherlocking thinking/exploration. It also saves more tokens than using anthropics own exploration agent.\n\nI had originally played around with a graph based approach but found this to work better. Currently, I have this running with Qwen 3.8 27B on my framework (I had Kevin build me a custom inference engine to squeeze all the juice I could out of the AMD - [https://gitlab.com/handmadedigital/projects/shocho](https://gitlab.com/handmadedigital/projects/shocho)).\n\nIt's been through a bunch of tests (results are available if people want) against a load of different repos, including comparing subsequent commits of large repos with claude, claude + exploration agent and claude + ototo and so far ototo seems to really help.\n\nThe site is very 'LLM'y at the moment - I haven't had time to edit it to make the text more readable for us humans. Sorry.\n\nHope it helps folks in their day-to-day.\n\n--EOL\n\nComments URL: [https://news.ycombinator.com/item?id=49971028](https://news.ycombinator.com/item?id=49971028)\n\nPoints: 1\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-ototo-a-tool-to-offload-code-exploration-to-a-smaller-model", "canonical_source": "https://ototo.dev/", "published_at": "2026-10-05 21:25:51+00:00", "updated_at": "2026-10-05 21:48:57.150344+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "large-language-models", "developer-tools", "ai-infrastructure"], "entities": ["Ototo", "Qwen 3.8 27B", "Shocho", "AMD", "Anthropic", "Claude", "Kevin", "EOL"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-ototo-a-tool-to-offload-code-exploration-to-a-smaller-model", "markdown": "https://wpnews.pro/news/show-hn-ototo-a-tool-to-offload-code-exploration-to-a-smaller-model.md", "text": "https://wpnews.pro/news/show-hn-ototo-a-tool-to-offload-code-exploration-to-a-smaller-model.txt", "jsonld": "https://wpnews.pro/news/show-hn-ototo-a-tool-to-offload-code-exploration-to-a-smaller-model.jsonld"}}