# K-Dense-AI/scientific-agent-skills > A library of 166 ready-to-use skills for AI agents covering bioinformatics, chemoinformatics, medicine, materials science and more, with access to 100+ scientific databases. Compatible with Cursor, Claude Code, Codex and the open Agent Skills standard. - Magnitude: 3.4 out of 10 — Steady - Stars: 46,261 total · +80 stars today, ≈ 153 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Python · License: MIT · Created: 2025-10-19 · Last push: 2026-09-21 - GitHub: https://github.com/K-Dense-AI/scientific-agent-skills · Homepage: https://arxiv.org/abs/2609.00065 · Page: https://gitnova.dev/en/r/K-Dense-AI/scientific-agent-skills ## Useful for - Attach skills to Claude Code or Cursor to analyze single-cell RNA-seq data - Run virtual screening and molecular docking through an agent - Build an LC-MS/MS data processing pipeline for proteomics ## Why it’s here - 80 stars so far today, about 153 expected by the end of the day. - GitHub Trending this month: #20, +12,198 stars. - About 16 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: 4,189 - Issues and pull requests: 267 - Watchers: 197 - Average over the last week: 155 per day - Usual pace: 303 per day - Stars in the last hour (measured): 12 - Latest release: v2.69.0 (2026-09-11) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-08-25 … 2026-09-23: 147, 386, 634, 1437, 1171, 1706, 1173, 772, 417, 287, 256, 333, 378, 281, 266, 234, 197, 152, 140, 175, 167, 139, 178, 122, 145, 141, 157, 163, 207, 80 ## Spotted in now - GitHub Trending this month: #20, +12,198 stars ## More in this category 1. **NandhaKishorM/laya** — 8.8 · Breakout · AI agents · Python · +1,318 stars today, ≈ 2,918 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. **google/ax** — 8.7 · Breakout · AI agents · Go · +441 stars today, ≈ 922 by evening A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and restricts network… Full card: https://gitnova.dev/en/r/google/ax.md 3. **unreallabsai/unreal-agent** — 8.6 · Breakout · AI agents · Go · +250 stars today, ≈ 589 by evening Async-first agent harness in Go: sessions with persisted forkable history, input deduplication, an LLM-turn coordinator, and asynchronous operation execution via swappable components. Full card: https://gitnova.dev/en/r/unreallabsai/unreal-agent.md 4. **jev-chat/jev-chat-jarvis** — 8.3 · Breakout · AI agents · Kotlin · +505 stars today, ≈ 1,209 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. **CopilotKit/openmuse** — 8.0 · Early signal · AI agents · TypeScript · +280 stars today, ≈ 620 by evening A personal AI agent with a browser, terminal, and files that carries out tasks on request and shows its work. Built with CopilotKit and AG-UI for iOS, Android, and web. Full card: https://gitnova.dev/en/r/CopilotKit/openmuse.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 2026-09-23 13:41 UTC, updated every 30 minutes.