Report Date: 2026-02-23
Analysis Window: 30 days
Languages Tracked: python, typescript, rust, go, javascript
Top N: 50
Overview
根据过去30天的数据，GitHub AI领域的趋势明确地集中在AI Agent技术上。Agent类项目在数量、热度和综合评分上均占据主导地位，而开发语言则主要由Python和TypeScript平分秋色，显示出AI应用层创新的强劲势头。
Top 50 Repositories
| Rank | Repository | Category | Language | Heat_7 | Heat_30 | Score |
|---|---|---|---|---|---|---|
| 1 | openclaw | typescript | 0 | 212,331 | 707 | |
| 2 | skills | agent | python | 0 | 24,420 | 81 |
| 3 | shannon | agent | typescript | 0 | 20,478 | 68 |
| 4 | claude-mem | agent | typescript | 0 | 15,583 | 305 |
| 5 | pi-mono | agent | typescript | 2,432 | 12,595 | 146 |
| 6 | langextract | llm | python | 0 | 10,163 | 33 |
| 7 | PageIndex | rag | python | 0 | 9,582 | 31 |
| 8 | dexter | agent | typescript | 0 | 7,737 | 25 |
| 9 | codex | agent | rust | 1,087 | 4,946 | 63 |
| 10 | memU | agent | python | 0 | 4,918 | 16 |
| 11 | chrome-devtools-mcp | agent | typescript | 1,107 | 4,596 | 62 |
| 12 | BitNet | llm | python | 0 | 2,844 | 9 |
| 13 | kimi-cli | agent | python | 0 | 2,725 | 9 |
| 14 | supermemory | typescript | 0 | 2,428 | 8 | |
| 15 | litellm | llm | python | 0 | 2,356 | 7 |
| 16 | AstrBot | agent | python | 0 | 2,311 | 7 |
| 17 | ext-apps | typescript | 0 | 1,200 | 4 | |
| 18 | superset | agent | typescript | 0 | 1,154 | 3 |
| 19 | vibetunnel | agent | typescript | 0 | 998 | 3 |
| 20 | RD-Agent | python | 0 | 977 | 3 | |
| 21 | meeting-minutes | rust | 0 | 583 | 1 | |
| 22 | skills | agent | javascript | 0 | 556 | 1 |
| 23 | screenpipe | rust | 0 | 547 | 1 | |
| 24 | agent-deck | llm | go | 192 | 463 | 9 |
| 25 | pentagi | agent | go | 5,565 | 0 | 1,185 |
| 26 | GitNexus | agent | typescript | 0 | 0 | 254 |
| 27 | agents | agent | typescript | 441 | 0 | 173 |
| 28 | claude-code-telegram | llm | python | 0 | 0 | 137 |
| 29 | OpenBB | agent | python | 0 | 0 | 112 |
| 30 | strix | python | 0 | 0 | 87 | |
| 31 | rowboat | typescript | 1,866 | 0 | 79 | |
| 32 | gemini-cli | agent | typescript | 0 | 0 | 79 |
| 33 | evals | llm | python | 0 | 0 | 55 |
| 34 | gh-aw | agent | go | 980 | 0 | 42 |
| 35 | UltraRAG | rag | python | 0 | 0 | 40 |
| 36 | SillyTavern | llm | javascript | 295 | 0 | 36 |
| 37 | posthog | python | 482 | 0 | 35 | |
| 38 | lobehub | agent | typescript | 0 | 0 | 33 |
| 39 | LocalAI | infra | go | 0 | 0 | 29 |
| 40 | agno | agent | python | 0 | 0 | 25 |
| 41 | composio | agent | typescript | 593 | 0 | 25 |
| 42 | trigger.dev | agent | typescript | 0 | 0 | 25 |
| 43 | qdrant | rust | 212 | 0 | 17 | |
| 44 | ai-dev-kit | agent | python | 327 | 0 | 14 |
| 45 | nofx | go | 0 | 0 | 12 | |
| 46 | keploy | agent | go | 0 | 0 | 12 |
| 47 | axonhub | llm | go | 0 | 0 | 10 |
| 48 | ultimatevocalremovergui | python | 0 | 0 | 9 | |
| 49 | rig | llm | rust | 0 | 0 | 8 |
| 50 | worktrunk | agent | rust | 182 | 0 | 7 |
Category Breakdown
(12 projects)
未分类项目数量可观（12个），平均热度中等，其中包含一些个人AI助手和通用工具，反映了AI技术应用的广泛性。
Average Heat_7: 213
Average Score: 80
- openclaw - Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
- supermemory - Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
- ext-apps - Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers
- RD-Agent - Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi...
- meeting-minutes - Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetil...
- screenpipe - screenpipe turns your computer into a personal AI that knows everything you've done. record. search. automate. all local, all private, all yours.
- strix - Open-source AI hackers to find and fix your app’s vulnerabilities.
- rowboat - Open-source AI coworker, with memory
- posthog - 🦔 PostHog is an all-in-one developer platform for building successful products. We offer product analytics, web analytics, session replay, error tracking, feature flags, experimentation, surveys...
- qdrant - Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
- nofx - AI Trading OS: Multi-AI, multi-exchange trading infrastructure with Strategy Studio.
- ultimatevocalremovergui - GUI for a Vocal Remover that uses Deep Neural Networks.
agent (26 projects)
AI Agent是本周期内最活跃和最受关注的领域，项目数量（26个）和平均热度（489）遥遥领先，表明该方向的开发和创新极为活跃。
Average Heat_7: 489
Average Score: 106
- skills - Public repository for Agent Skills
- shannon - Fully autonomous AI hacker to find actual exploits in your web apps. Shannon has achieved a 96.15% success rate on the hint-free, source-aware XBOW Benchmark.
- claude-mem - A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future ...
- pi-mono - AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods
- dexter - An autonomous agent for deep financial research
- codex - Lightweight coding agent that runs in your terminal
- memU - Memory for 24/7 proactive agents like openclaw (moltbot, clawdbot).
- chrome-devtools-mcp - Chrome DevTools for coding agents
- kimi-cli - Kimi Code CLI is your next CLI agent.
- AstrBot - Agentic IM Chatbot infrastructure that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
- superset - The command center for coding agents - Run a team of Claude Code, OpenCode, Codex, or any other agents on your machine
- vibetunnel - Turn any browser into your terminal & command your agents on the go.
- skills - A collection of AI agent skills for working with Expo projects and Expo Application Services
- pentagi - ✨ Fully autonomous AI Agents system capable of performing complex penetration testing tasks
- GitNexus - GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive ...
- agents - Build and deploy AI Agents on Cloudflare
- OpenBB - Financial data platform for analysts, quants and AI agents.
- gemini-cli - An open-source AI agent that brings the power of Gemini directly into your terminal.
- gh-aw - GitHub Agentic Workflows
- lobehub - The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboratio...
- agno - The programming language for agentic software. Build, run, and manage multi-agent systems at scale.
- composio - Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
- trigger.dev - Trigger.dev – build and deploy fully‑managed AI agents and workflows
- ai-dev-kit - Databricks Toolkit for Coding Agents provided by Field Engineering
- keploy - API, Integration, E2E Testing Agent for Developers that actually work. Generate tests, mocks/stubs for your APIs!
- worktrunk - Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
llm (9 projects)
LLM相关项目依然是基础，但热度相对Agent较低。这些项目多为模型推理框架、评估工具或统一API网关，显示出市场在LLM基础上向应用层转移的趋势。
Average Heat_7: 54
Average Score: 33
- langextract - A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
- BitNet - Official inference framework for 1-bit LLMs
- litellm - Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr...
- agent-deck - Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
- claude-code-telegram - A powerful Telegram bot that provides remote access to Claude Code, enabling developers to interact with their projects from anywhere with full AI assistance and session persistence.
- evals - Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
- SillyTavern - LLM Frontend for Power Users.
- axonhub - ⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.
- rig - ⚙️🦀 Build modular and scalable LLM Applications in Rust
rag (2 projects)
RAG项目数量较少（2个），且近期热度为0，可能表明相关技术已趋于成熟或被整合进更上层的Agent框架中。
Average Heat_7: 0
Average Score: 35
- PageIndex - 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
- UltraRAG - A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
infra (1 projects)
基础架构（infra）项目仅一个上榜，热度不高，说明当前趋势更偏向于AI应用层和Agent框架，而非底层设施的革新。
Average Heat_7: 0
Average Score: 29
- LocalAI - 🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, ...
Dark Horse Projects
本周期黑马项目表现抢眼，特别是vxcontrol/pentagi，其评分极高（1185）且近期热度爆发，显示出自主AI渗透测试这一细分方向的巨大潜力。其他如openclaw/openclaw和thedotmack/claude-mem等项目也凭借高分入榜，表明市场对具有新颖应用场景的AI项目抱有浓厚兴趣。
| Repository | Score | Heat_30 | Heat_7 | Category |
|---|---|---|---|---|
| openclaw | 707 | 212,331 | 0 | |
| claude-mem | 305 | 15,583 | 0 | agent |
| pi-mono | 146 | 12,595 | 2,432 | agent |
| pentagi | 1,185 | 0 | 5,565 | agent |
| GitNexus | 254 | 0 | 0 | agent |
| agents | 173 | 0 | 441 | agent |
| claude-code-telegram | 137 | 0 | 0 | llm |
| OpenBB | 112 | 0 | 0 | agent |
Consecutive Appearances
榜单中存在大量连续上榜的项目，其中许多项目已连续5周在榜，如openclaw/openclaw、anthropics/skills和KeygraphHQ/shannon。这表明AI Agent领域的热点具有较强的持续性，核心项目已形成稳定的开发者社区和关注度。
| Repository | Weeks in Top | Category | Current Heat_7 |
|---|---|---|---|
| openclaw | 5 | 0 | |
| skills | 5 | agent | 0 |
| shannon | 5 | agent | 0 |
| claude-mem | 5 | agent | 0 |
| pi-mono | 5 | agent | 2,432 |
| langextract | 3 | llm | 0 |
| PageIndex | 5 | rag | 0 |
| dexter | 5 | agent | 0 |
| codex | 5 | agent | 1,087 |
| memU | 5 | agent | 0 |
| chrome-devtools-mcp | 2 | agent | 1,107 |
| BitNet | 5 | llm | 0 |
| kimi-cli | 5 | agent | 0 |
| ext-apps | 5 | 0 | |
| screenpipe | 2 | 0 | |
| rowboat | 2 | 1,866 | |
| gh-aw | 3 | agent | 980 |
| UltraRAG | 5 | rag | 0 |
| worktrunk | 5 | agent | 182 |
Highlighted Repositories
openclaw/openclaw
该项目作为榜首，在过去30天内积累了极高的热度，但近7天热度为0，可能意味着其爆发性增长阶段已过，目前进入稳定期。作为一个个人AI助手项目，它的高排名反映了市场对消费级、通用型AI应用的强烈需求。
vxcontrol/pentagi
作为一个评分极高的黑马项目，pentagi的出现揭示了AI Agent在网络安全等专业领域的巨大应用潜力。其近期热度的急剧飙升，表明自主执行复杂渗透测试任务的能力击中了行业痛点，是一个值得关注的新兴方向。
KeygraphHQ/shannon
此项目连续5周上榜，专注于利用AI寻找Web应用漏洞，与pentagi共同印证了AI在自动化安全领域的强劲势头。其持续的热度表明这是一个具有长期价值和稳定社区关注的方向，而不仅仅是短期热点。
ChromeDevTools/chrome-devtools-mcp
由Chrome开发工具团队推出的这个项目，专注于为AI编程助 手提供调试和观察工具，这标志着AI Agent生态正在走向成熟。开发者不仅在构建Agent，也在构建服务于Agent开发的底层工具链，这是领域发展深化的重要信号。
Methodology
Data Sources:
- GitHub Trending pages
- GitHub API stargazer timestamps
Metrics:
- Heat_7: Stars gained in last 7 days
- Heat_30: Stars gained in last 30 days
- Score: Weighted scoring combining short-term heat and sustained growth
- Formula: 0.6 × stars_1d + 0.3 × (stars_7d / 7) + 0.1 × (stars_30d / 30)
- Emphasizes recent activity (60%) while considering sustained trends (40%)
Filtering:
- Include keywords: %!s(int=30)
- Exclude keywords: %!s(int=30)
- Categories: %!s(int=30)
Ranking:
- Sort by Heat_30 (descending)
- Tie-break by Score (descending)
- Select top %!d(string=ai, llm, agent, gpt, rag, langchain, machine-learning, deep-learning, neural, transformer, embedding, vector)
Limitations:
- Trending data limited to GitHub's trending algorithm
- Star history may be incomplete for repos with >40k stars (API pagination limits)
- LLM-generated commentary is interpretive, not prescriptive
- Weekly snapshots may miss short-lived trends%!(EXTRA string=tutorial, awesome, learning, course, book, string=infra, agent, llm, rag, vision, int=50)
Generated at: 2026-02-23T00:28:25Z