Reports / daily / Oct 18, 2026
GitHub Trending Report — October 18, 2026
Today's snapshot of what the open-source world is starring. 9 repositories made the daily trending list.
Repository of the day
akitaonrails/ai-memory — Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors AI-memory provides a centralized repository for storing the context, decisions, and architectural notes generated during AI coding sessions. Instead of losing history when switching between tools like Claude Code, Cursor, or Codex, this tool quietly observes and captures information across more than twenty supported agent harnesses. It consolidates session data into human-readable wiki pages upon completion. When a new agent is launched in the same directory, it retrieves this shared memory through search and brief context injection. This ensures continuity in complex projects without requiring developers to repeatedly re-explain architectures or past failures.
- Stars: 10,145 | Forks: 733 | Language: Rust | License: MIT
- Typical use cases: Maintaining project continuity; Onboarding new AI tools; Documenting failed approaches
- View the full repository profile or see it on GitHub
Trending today
| Rank | Repository | Language | Total stars | Stars today | Description |
|---|---|---|---|---|---|
| 1 | anthropics/claude-plugins-official | Python | 42,195 | +1,397 | Official, Anthropic-managed directory of high quality Claude Code Plugins. |
| 2 | HKUDS/CLI-Anything | Python | 54,278 | +574 | "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/ |
| 3 | K-Dense-AI/scientific-agent-skills | Python | 52,504 | +878 | Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists w |
| 4 | akitaonrails/ai-memory | Rust | 10,145 | +178 | Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors |
| 5 | android/skills | Kotlin | 8,575 | +355 | |
| 6 | stablyai/orca | TypeScript | 95,841 | +830 | Orca is the place for working with a fleet of agents (e.g. Grok Bot, Claude Code). Run any coding agent with y |
| 7 | anthropics/claude-code | TypeScript | 152,182 | +179 | Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you co |
| 8 | ruvnet/ruflo | TypeScript | 76,257 | +420 | 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and bu |
| 9 | xerj-org/xerj | Rust | 8,094 | +1,160 | XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your data without |
Star jumps detected
- akitaonrails/ai-memory gained +508 stars in the last day (trailing average: 74/day). Solution for long term memory for agent coding CLIs and to facilitate handoff between different agen
- pingdotgg/t3code gained +408 stars in the last day (trailing average: 135/day).
- xerj-org/xerj gained +347 stars in the last day. XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your da
- rtk-ai/rtk gained +310 stars in the last day (trailing average: 90/day). CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, z
- nautechsystems/nautilus_trader gained +218 stars in the last day (trailing average: 45/day). Production-grade Rust-native trading engine with deterministic event-driven architecture
- penpot/penpot gained +178 stars in the last day (trailing average: 40/day). Penpot: The open-source design platform for Product teams that need scalable collaboration.
- sickn33/agentic-awesome-skills gained +143 stars in the last day (trailing average: 41/day). AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selecti
- shy3130/tick-stock-panel gained +84 stars in the last day (trailing average: 19/day). TSP自托管、零运维的 A 股「自建策略 + 监控 + 回测」量化工作台 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源
- promptfoo/promptfoo gained +80 stars in the last day (trailing average: 25/day). Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare p
- onyx-dot-app/onyx gained +69 stars in the last day (trailing average: 17/day). Open Source AI Platform - AI Chat with advanced features that works with every LLM
New on the radar
No first-time entrants today.
Want the next one in your inbox?
One email a week: repository of the week, the biggest star gainers, and new projects worth watching.
The newsletter is not wired up yet. Subscribe to the RSS feed in the meantime — every weekly digest is published there first.