{"ok":true,"repo":{"id":610,"full_name":"kerpopule/hermes-jev-skills","url":"https://github.com/kerpopule/hermes-jev-skills","description":"Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)","language":"Python","topics":[],"stars":852,"stars_delta":5,"forks":78,"first_seen":"2026-09-26T18:13:21.577517Z","last_seen":"2026-09-26T21:36:36.229422Z","mentions":0,"platforms":[],"score":0.0,"summary":"A set of Python-based agent 'skills' that offload small, frequent decisions from expensive frontier LLMs to Jev, TypeSafe's decision-only model. It handles model routing, memory filtering, prompt-injection screening, transcript compaction, skill selection, message triage, mailbox sorting, and computer/browser use. Skills ship as plain SKILL.md files, so they work with Hermes agents, Claude Code, Codex, or anything that reads skill files.","why":"Recently created and climbing the most-starred new repos list, with freshly published evaluation scorecards showing strong injection-detection and recall results.","audience":"Developers building or running coding agents who want to cut token costs and latency by routing trivial decisions to a cheap decision model.","tags":["ai-agents","model-routing","prompt-injection","python","claude-code","llm"],"summarized_at":"2026-09-26T18:17:16.401590Z","summary_model":"glm-5.3-flash","fetched_at":"2026-09-26T21:36:54.172105Z","meta":{"license":"MIT","archived":false,"homepage":null,"first_stars":847},"pushed_at":"2026-09-26T18:12:24Z","created_at":"2026-09-18T20:01:29Z","watchers":1,"open_issues":0,"mentions_list":[{"platform":"github","url":"https://github.com/search?q=created%3A%3E2026-09-12&s=stars&o=desc","title":"new repos, most starred","seen_at":"2026-09-26T21:36:36.229657Z"}],"snapshots":[{"captured_at":"2026-09-26T18:17:10.513361Z","stars":847,"forks":78},{"captured_at":"2026-09-26T18:17:10.563862Z","stars":847,"forks":78},{"captured_at":"2026-09-26T18:27:05.235450Z","stars":847,"forks":78},{"captured_at":"2026-09-26T18:28:41.849758Z","stars":847,"forks":78},{"captured_at":"2026-09-26T18:43:41.730479Z","stars":847,"forks":78},{"captured_at":"2026-09-26T18:56:55.347018Z","stars":847,"forks":78},{"captured_at":"2026-09-26T19:12:02.533313Z","stars":847,"forks":78},{"captured_at":"2026-09-26T19:15:24.035955Z","stars":848,"forks":78},{"captured_at":"2026-09-26T19:18:54.983174Z","stars":848,"forks":78},{"captured_at":"2026-09-26T19:20:55.694884Z","stars":848,"forks":78},{"captured_at":"2026-09-26T19:27:27.682882Z","stars":848,"forks":78},{"captured_at":"2026-09-26T19:31:03.110240Z","stars":848,"forks":78},{"captured_at":"2026-09-26T19:34:07.555227Z","stars":848,"forks":78},{"captured_at":"2026-09-26T19:49:08.655423Z","stars":850,"forks":78},{"captured_at":"2026-09-26T20:04:14.573406Z","stars":850,"forks":78},{"captured_at":"2026-09-26T20:19:08.462845Z","stars":851,"forks":78},{"captured_at":"2026-09-26T20:34:08.269763Z","stars":851,"forks":78},{"captured_at":"2026-09-26T20:49:07.728146Z","stars":851,"forks":78},{"captured_at":"2026-09-26T20:51:55.004465Z","stars":851,"forks":78},{"captured_at":"2026-09-26T21:06:54.300204Z","stars":852,"forks":78},{"captured_at":"2026-09-26T21:21:53.969598Z","stars":852,"forks":78},{"captured_at":"2026-09-26T21:36:54.173211Z","stars":852,"forks":78}]}}