EvoOntology makes semantic context versioned agent state that can improve from observed…
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
EvoOntology makes semantic context versioned agent state that can improve from observed data-agent trajectories. A builder grounds Terms, Mappings, Constraints and Evidence in the underlying data, exposes them through MCP tools, then an evolution agent patches the content, schema or tool layer. A candidate ontology is promoted only after paired evaluation against its parent with the same data, model, decoding settings and interaction budget. Across the paper’s four-backbone subset, DDR-Bench rises from 69.5 to 89.5, while InsightBench moves only from 53.2 to 54.2, showing how workload-dependen
Posted by Sandhya (1.3k followers) 3 days ago · 10 likes · 430 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: evoontology.
More dev work like this
- Hallmark has been installed 50k+ times! — @nutlope
- Your AI coding agents need a workflow, not more babysitting. — @DanKornas
- Register by October 7 and save >> https://bit.ly/4vkntyD — @linuxfoundation
- Nimble is able to process images! — @madiator
- Your agent already solved this. Finding the session is the problem. — @DanKornas
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- gpt 5.6 terra = gpt 6 astra — @notjazii
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.