# TianyuCodings/JevHarness > A tool where an LLM authors a task-specific harness for fast Jev decisions: code computes features, Jev makes fuzzy decisions, and the harness can be improved via rewards and full execution traces. - Magnitude: 5.1 out of 10 — Early signal - Stars: 120 total · +10 stars today, ≈ 66 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Python · Created: 2026-09-21 · Last push: 2026-09-21 - GitHub: https://github.com/TianyuCodings/JevHarness · Homepage: https://jev-harness.tianyuchen99.chatgpt.site · Page: https://gitnova.dev/en/r/TianyuCodings/JevHarness ## Useful for - Build a harness for a game agent and measure its win rate on the Eval set - Run GEPA evolution of a harness using rewards and full execution traces - Open the Pokémon Showdown battle archive to inspect the selected harness's decisions ## Why it’s here - 10 stars so far today, about 66 expected by the end of the day. - The spike has held for 2 days in a row — not a one-off blip. - The repository is 1 day old and already has 120 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - Top new repositories this week: #159. - About 9 forks a day — people are taking the code. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 8 - Issues and pull requests: 0 - Watchers: 1 - Average over the last week: 89 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 6 ## Stars per day, last 3 days (oldest → newest, today is partial) 2026-09-20 … 2026-09-22: 0, 112, 10 ## Spotted in now - Top new repositories this week: #159 ## More in this category 1. **NandhaKishorM/laya** — 9.2 · Breakout · AI agents · Python · +414 stars today, ≈ 3,562 by evening Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities. Full card: https://gitnova.dev/en/r/NandhaKishorM/laya.md 2. **zai-org/ZCode** — 8.8 · Breakout · AI agents · TypeScript · +54 stars today, ≈ 956 by evening Z.ai's coding agent workbench: an Electron desktop app, browser UI and terminal Agent CLI. The repo contains the client, backend, shared UI and the agent CLI/runtime sources. Full card: https://gitnova.dev/en/r/zai-org/ZCode.md 3. **browser-use/jev-ultrafast** — 8.6 · Peaking · AI agents · Python · +164 stars today, ≈ 1,860 by evening A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing. Full card: https://gitnova.dev/en/r/browser-use/jev-ultrafast.md 4. **jev-chat/jev-chat-jarvis** — 8.0 · Breakout · AI agents · Kotlin · +184 stars today, ≈ 1,144 by evening Android app that reads the on-screen chat via AccessibilityService, judges the other side's intent with the Jev model, and shows 3 ranked reply drafts in a translucent overlay. Replies are filled into the input box but sent manually. Full card: https://gitnova.dev/en/r/jev-chat/jev-chat-jarvis.md 5. **BuilderIO/agent-native** — 7.3 · Breakout · AI agents · TypeScript · +57 stars today, ≈ 404 by evening An open-source TypeScript framework for building agentic apps where each capability is defined once as an action, used by the agent as a tool and called by the UI from code. Aimed at developers who need agents paired with a real UI for… Full card: https://gitnova.dev/en/r/BuilderIO/agent-native.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-22 08:04 UTC, updated every 30 minutes.