# なんとかソナー 📡 GitHub トレンド・日速観測データ

> 最終更新: 2026-09-19T12:32:18Z | 観測数: 76 | データ正本: sonar.jsonl

## ⚡️ 急上昇ランキング (TOP 5)

| 順位 | リポジトリ | 日速 | Star数 | 観測日数 | 言語 | タグ | 説明 |
|:---:|---|:---:|:---:|:---:|:---:|---|---|
| #1 | [deepseek-ai/deepseek-harness](https://github.com/deepseek-ai/deepseek-harness) | +1033.9/日 (確定(7日)) | ⭐ 220,497 | 7.7日 | TypeScript | - | DeepSeek Harness: Everything is a Plugin. |
| #2 | [affaan-m/ECC](https://github.com/affaan-m/ECC) | +999.0/日 (確定(7日)) | ⭐ 256,472 | 7.7日 | JavaScript | ハーネス | The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. |
| #3 | [lnkiai/m3e-canvas](https://github.com/lnkiai/m3e-canvas) | +290.6/日 (暫定) | ⭐ 6,124 | 5.1日 | TypeScript | - | Sketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts. |
| #4 | [earendil-works/pi](https://github.com/earendil-works/pi) | +289.2/日 (確定(7日)) | ⭐ 104,144 | 7.7日 | TypeScript | ループ | AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI |
| #5 | [Graphify-Labs/graphify](https://github.com/Graphify-Labs/graphify) | +282.8/日 (確定(7日)) | ⭐ 117,010 | 7.7日 | Python | ナレッジ | Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store. |

## 📋 全観測リポジトリ一覧

| # | リポジトリ | 日速 | Star数 | 観測日数 | 言語 | タグ | 説明 |
|:---:|---|:---:|:---:|:---:|:---:|---|---|
| 1 | [deepseek-ai/deepseek-harness](https://github.com/deepseek-ai/deepseek-harness) | +1033.9/日 (確定(7日)) | ⭐ 220,497 | 7.7日 | TypeScript | - | DeepSeek Harness: Everything is a Plugin. |
| 2 | [affaan-m/ECC](https://github.com/affaan-m/ECC) | +999.0/日 (確定(7日)) | ⭐ 256,472 | 7.7日 | JavaScript | ハーネス | The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. |
| 3 | [lnkiai/m3e-canvas](https://github.com/lnkiai/m3e-canvas) | +290.6/日 (暫定) | ⭐ 6,124 | 5.1日 | TypeScript | - | Sketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts. |
| 4 | [earendil-works/pi](https://github.com/earendil-works/pi) | +289.2/日 (確定(7日)) | ⭐ 104,144 | 7.7日 | TypeScript | ループ | AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI |
| 5 | [Graphify-Labs/graphify](https://github.com/Graphify-Labs/graphify) | +282.8/日 (確定(7日)) | ⭐ 117,010 | 7.7日 | Python | ナレッジ | Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store. |
| 6 | [anywhere-labs/dsh-desktop](https://github.com/anywhere-labs/dsh-desktop) | +264.2/日 (確定(7日)) | ⭐ 25,702 | 7.7日 | TypeScript | - | 为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」，桌面本身也是「插件」。 |
| 7 | [dataelement/dsh-desktop](https://github.com/dataelement/dsh-desktop) | +179.3/日 (暫定) | ⭐ 5,329 | 2.1日 | TypeScript | - | DSHDesktop：DeepSeek Harness Desktop / DeepSeek Harness 桌面版 |
| 8 | [volcengine/OpenViking](https://github.com/volcengine/OpenViking) | +147.0/日 (確定(7日)) | ⭐ 36,691 | 7.7日 | Python | 記憶 / AIコンテキスト | Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. |
| 9 | [guillaumemeyer/watermarks-remover](https://github.com/guillaumemeyer/watermarks-remover) | +142.1/日 (確定(7日)) | ⭐ 21,739 | 7.7日 | Python | - | A privacy-first app that strips AI watermarks from content you own. |
| 10 | [zhaoxuya520/reverse-skill](https://github.com/zhaoxuya520/reverse-skill) | +126.5/日 (確定(7日)) | ⭐ 35,590 | 7.7日 | PowerShell | ナレッジ | Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base  Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 \| 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端 |
| 11 | [awesome-dsh-plugin/awesome-dsh-plugin](https://github.com/awesome-dsh-plugin/awesome-dsh-plugin) | +109.9/日 (確定(7日)) | ⭐ 15,358 | 7.7日 | Python | - | A curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表 |
| 12 | [colbymchenry/codegraph](https://github.com/colbymchenry/codegraph) | +109.8/日 (確定(7日)) | ⭐ 70,516 | 7.7日 | C | ナレッジ | Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local |
| 13 | [vectorize-io/hindsight](https://github.com/vectorize-io/hindsight) | +105.5/日 (確定(7日)) | ⭐ 23,466 | 7.7日 | Python | 記憶 / AIコンテキスト | Hindsight: Agent Memory That Learns |
| 14 | [DeusData/codebase-memory-mcp](https://github.com/DeusData/codebase-memory-mcp) | +94.2/日 (確定(7日)) | ⭐ 42,979 | 7.7日 | C | ナレッジ | High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies. |
| 15 | [sapientinc/PRAXIST](https://github.com/sapientinc/PRAXIST) | +83.6/日 (確定(7日)) | ⭐ 6,562 | 7.7日 | Python | - | Autonomous research system for measurable, computer-executable research. |
| 16 | [Egonex-AI/Understand-Anything](https://github.com/Egonex-AI/Understand-Anything) | +71.1/日 (確定(7日)) | ⭐ 82,063 | 7.7日 | TypeScript | ナレッジ | Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more. |
| 17 | [zhu1090093659/dsh-web](https://github.com/zhu1090093659/dsh-web) | +67.4/日 (確定(7日)) | ⭐ 7,415 | 7.7日 | TypeScript | - | DeepSeek Harness (DSH) Web Plugin Aggregation Ecosystem · Everything is a plugin, distributed via the Creative Workshop |
| 18 | [shareAI-lab/learn-claude-code](https://github.com/shareAI-lab/learn-claude-code) | +62.6/日 (確定(7日)) | ⭐ 76,567 | 7.7日 | Python | ハーネス | Bash is all you need -  A nano claude code–like 「agent harness」, built from 0 to 1 |
| 19 | [MengTo/threeui](https://github.com/MengTo/threeui) | +60.2/日 (確定(7日)) | ⭐ 5,602 | 7.7日 | HTML | - | Open-source ThreeUI Community catalog with live interactive components and complete Community source. |
| 20 | [CopilotKit/OpenBot](https://github.com/CopilotKit/OpenBot) | +58.2/日 (確定(7日)) | ⭐ 4,719 | 7.7日 | TypeScript | - | Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent. |
| 21 | [TencentCloud/TencentDB-Agent-Memory](https://github.com/TencentCloud/TencentDB-Agent-Memory) | +55.1/日 (確定(7日)) | ⭐ 26,362 | 7.7日 | TypeScript | 記憶 / AIコンテキスト | TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks. |
| 22 | [langchain-ai/deepagents](https://github.com/langchain-ai/deepagents) | +41.2/日 (確定(7日)) | ⭐ 29,329 | 7.7日 | Python | ハーネス | The batteries-included agent harness. |
| 23 | [toeverything/AFFiNE](https://github.com/toeverything/AFFiNE) | +35.3/日 (確定(7日)) | ⭐ 72,469 | 7.7日 | TypeScript | ナレッジ | There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.  |
| 24 | [abhigyanpatwari/GitNexus](https://github.com/abhigyanpatwari/GitNexus) | +30.2/日 (確定(7日)) | ⭐ 47,256 | 7.7日 | TypeScript | ナレッジ | GitNexus: The Zero-Server Code Intelligence Engine -       GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or ZIP file, and get an interactive knowledge graph with a built in Graph RAG Agent. Perfect for code exploration |
| 25 | [s1dashu/ip-as-logo-skill](https://github.com/s1dashu/ip-as-logo-skill) | +26.0/日 (確定(7日)) | ⭐ 5,140 | 7.7日 | - | - | A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos. |
| 26 | [xai-org/grok-build](https://github.com/xai-org/grok-build) | +25.9/日 (確定(7日)) | ⭐ 26,677 | 7.7日 | Rust | ハーネス | SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible. |
| 27 | [getzep/graphiti](https://github.com/getzep/graphiti) | +20.6/日 (暫定) | ⭐ 30,815 | 2.1日 | Python | ナレッジ | Build Real-Time Knowledge Graphs for AI Agents |
| 28 | [zhayujie/CowAgent](https://github.com/zhayujie/CowAgent) | +16.3/日 (確定(7日)) | ⭐ 46,908 | 7.7日 | Python | ハーネス | Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat) |
| 29 | [yjh051108/dsh-routing-suite](https://github.com/yjh051108/dsh-routing-suite) | +11.6/日 (確定(7日)) | ⭐ 7,170 | 7.7日 | JavaScript | - | dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23). |
| 30 | [TriliumNext/Trilium](https://github.com/TriliumNext/Trilium) | +10.7/日 (確定(7日)) | ⭐ 37,798 | 7.7日 | TypeScript | ナレッジ | Build your personal knowledge base with Trilium Notes |
| 31 | [ComposioHQ/composio](https://github.com/ComposioHQ/composio) | +10.1/日 (確定(7日)) | ⭐ 30,136 | 7.7日 | TypeScript | 記憶 / AIコンテキスト | Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action. |
| 32 | [EleutherAI/lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) | +8.3/日 (確定(7日)) | ⭐ 13,954 | 7.7日 | Python | - | A framework for few-shot evaluation of language models. |
| 33 | [regrevia/Revia](https://github.com/regrevia/Revia) | +7.8/日 (確定(7日)) | ⭐ 77 | 7.7日 | Shell | 意味グラフ | Agent-native executable language for AI-native development: Agents build programs; humans govern verifiable semantic graphs. |
| 34 | [outline/outline](https://github.com/outline/outline) | +7.6/日 (確定(7日)) | ⭐ 40,521 | 7.7日 | TypeScript | ナレッジ | The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible. |
| 35 | [labring/FastGPT](https://github.com/labring/FastGPT) | +7.1/日 (確定(7日)) | ⭐ 29,631 | 7.7日 | TypeScript | - | FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration. |
| 36 | [xerj-org/xerj](https://github.com/xerj-org/xerj) | +6.2/日 (確定(7日)) | ⭐ 1,906 | 7.7日 | Rust | 記憶 / AIコンテキスト | XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your data without the token waste of grep and sed. One command indexes code, docs, logs and PDFs for search, RAG, security audits and agent memory, using 40x fewer tokens than grep. Elasticsearch compatible, so existing clients just work. |
| 37 | [jackyzha0/quartz](https://github.com/jackyzha0/quartz) | +5.7/日 (確定(7日)) | ⭐ 13,209 | 7.7日 | TypeScript | - | 🌱 a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites |
| 38 | [bradAGI/awesome-cli-coding-agents](https://github.com/bradAGI/awesome-cli-coding-agents) | +5.7/日 (確定(7日)) | ⭐ 1,199 | 7.7日 | Python | ループ | Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI), parallel runners, autonomous loops, and agent infrastructure.  |
| 39 | [muratcankoylan/Agent-Skills-for-Context-Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) | +5.2/日 (確定(7日)) | ⭐ 17,960 | 7.7日 | Python | 記憶 / AIコンテキスト | A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management. |
| 40 | [zensical/zensical](https://github.com/zensical/zensical) | +5.2/日 (確定(7日)) | ⭐ 5,686 | 7.7日 | Rust | 個人の情報発信 | A modern static site generator by the Material for MkDocs team |
| 41 | [Windy3f3f3f3f/how-claude-code-works](https://github.com/Windy3f3f3f3f/how-claude-code-works) | +4.1/日 (確定(7日)) | ⭐ 3,613 | 7.7日 | - | ループ | Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码：架构、Agent 循环、上下文工程、工具系统等 |
| 42 | [getzola/zola](https://github.com/getzola/zola) | +3.1/日 (確定(7日)) | ⭐ 17,420 | 7.7日 | Rust | 個人の情報発信 | A fast static site generator in a single binary with everything built-in. https://www.getzola.org |
| 43 | [decaporg/decap-cms](https://github.com/decaporg/decap-cms) | +2.8/日 (確定(7日)) | ⭐ 19,371 | 7.7日 | JavaScript | 個人の情報発信 | A Git-based CMS for Static Site Generators |
| 44 | [vuejs/vitepress](https://github.com/vuejs/vitepress) | +2.8/日 (確定(7日)) | ⭐ 18,308 | 7.7日 | TypeScript | 個人の情報発信 | Vite & Vue powered static site generator. |
| 45 | [stephenschoettler/hermes-lcm](https://github.com/stephenschoettler/hermes-lcm) | +2.3/日 (確定(7日)) | ⭐ 1,122 | 7.7日 | Python | 記憶 / AIコンテキスト | Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message |
| 46 | [IAAR-Shanghai/Awesome-AI-Memory](https://github.com/IAAR-Shanghai/Awesome-AI-Memory) | +1.8/日 (確定(7日)) | ⭐ 1,213 | 7.7日 | Python | 記憶 / AIコンテキスト, ナレッジ | Awesome AI Memory \| LLM Memory \| A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design.  Awesome-AI-Memory 是一个 集中式、持续更新的 AI 记忆知识库，系统性整理了与 大模型记忆（LLM Memory）与智能体记忆（Agent Memory） 相关的前沿研究、工程框架、系统设计、评测基准与真实应用实践。 |
| 47 | [the-open-agent/openagent](https://github.com/the-open-agent/openagent) | +1.4/日 (確定(7日)) | ⭐ 5,613 | 7.7日 | Go | ループ | ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org |
| 48 | [oleeskild/obsidian-digital-garden](https://github.com/oleeskild/obsidian-digital-garden) | +1.4/日 (確定(7日)) | ⭐ 2,495 | 7.7日 | TypeScript | - | - |
| 49 | [claw-eval/claw-eval](https://github.com/claw-eval/claw-eval) | +1.3/日 (確定(7日)) | ⭐ 773 | 7.7日 | Python | ハーネス | Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans. |
| 50 | [ranxianglei/opencode-acp](https://github.com/ranxianglei/opencode-acp) | +1.2/日 (暫定) | ⭐ 252 | 5.1日 | TypeScript | 記憶 / AIコンテキスト | 稳定可用Active Context Pruning — model-driven context management for OpenCode ，200K tokens is enough. ，主动压缩上下文，20w token足以 |
| 51 | [allenai/vla-evaluation-harness](https://github.com/allenai/vla-evaluation-harness) | +1.0/日 (確定(7日)) | ⭐ 597 | 7.7日 | Python | - | One framework to evaluate any VLA model on any robot simulation benchmark. |
| 52 | [codegraph-ai/CodeGraph](https://github.com/codegraph-ai/CodeGraph) | +0.9/日 (確定(7日)) | ⭐ 85 | 7.7日 | C | 意味グラフ | CodeGraph builds a semantic graph of your codebase — functions, classes, imports, call chains — and exposes it through 42 MCP tools, 38 languages, a VS Code extension, and a persistent memory layer. AI agents get structured code understanding instead of grepping through files. |
| 53 | [durable-streams/durable-streams](https://github.com/durable-streams/durable-streams) | +0.8/日 (確定(7日)) | ⭐ 1,692 | 7.7日 | TypeScript | - | The data primitive for the agent loop. |
| 54 | [a-Fig/Accordion](https://github.com/a-Fig/Accordion) | +0.5/日 (確定(7日)) | ⭐ 243 | 7.7日 | TypeScript | 記憶 / AIコンテキスト | 🏆 AI Hackathon 2026 @ UC Berkeley  Intelligent context management for developers |
| 55 | [ApodexAI/AgentHarness](https://github.com/ApodexAI/AgentHarness) | +0.4/日 (確定(7日)) | ⭐ 435 | 7.7日 | Python | ハーネス | Evaluation harness for Apodex-1.0 on public deep-research benchmarks. |
| 56 | [Lyellr88/marm-memory](https://github.com/Lyellr88/marm-memory) | +0.4/日 (確定(7日)) | ⭐ 353 | 7.7日 | Python | 意味グラフ | Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms. |
| 57 | [chrislusf/gleam](https://github.com/chrislusf/gleam) | +0.1/日 (確定(7日)) | ⭐ 3,564 | 7.7日 | Go | 実行グラフ | Fast, efficient, and scalable distributed map/reduce system, DAG execution, in memory or on disk, written in pure Go, runs standalone or distributedly. |
| 58 | [Ricky-7-Yan/intelligent-audit-system](https://github.com/Ricky-7-Yan/intelligent-audit-system) | +0.1/日 (確定(7日)) | ⭐ 1,168 | 7.7日 | Python | ハーネス | AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery. |
| 59 | [lyz-code/best-of-digital-gardens](https://github.com/lyz-code/best-of-digital-gardens) | +0.1/日 (確定(7日)) | ⭐ 591 | 7.7日 | Shell | ナレッジ, 個人の情報発信 | Ranked list of awesome digital gardens / second brains |
| 60 | [emad-elsaid/xlog](https://github.com/emad-elsaid/xlog) | +0.1/日 (確定(7日)) | ⭐ 233 | 7.7日 | Go | ナレッジ, 個人の情報発信 | 💥 Fast, Git-native framework for building knowledge bases - Static site generator for digital gardens and personal wikis |
| 61 | [dinosn/raptor-loop-hunt](https://github.com/dinosn/raptor-loop-hunt) | +0.1/日 (確定(7日)) | ⭐ 217 | 7.7日 | Python | ループ | RAPTOR autonomous looping multi-altitude security vulnerability hunt — Claude Code skill |
| 62 | [Coral-Bricks-AI/reef](https://github.com/Coral-Bricks-AI/reef) | +0.1/日 (確定(7日)) | ⭐ 52 | 7.7日 | Python | ループ | A harness framework for building domain-specific agents, the worked finance instance that beats every frontier model on public benchmarks, and the autonomous loop coordinator that drives 100-experiment optimization runs unattended. |
| 63 | [ruvnet/ruflo](https://github.com/ruvnet/ruflo) | +0.0/日 (暫定) | ⭐ 72,128 | 1.1日 | TypeScript | ハーネス | 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated |
| 64 | [Forward-Future/loopy](https://github.com/Forward-Future/loopy) | +0.0/日 (暫定) | ⭐ 3,123 | 1.1日 | JavaScript | ループ | A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows. |
| 65 | [apvarun/digital-garden-hugo-theme](https://github.com/apvarun/digital-garden-hugo-theme) | +0.0/日 (確定(7日)) | ⭐ 298 | 7.7日 | HTML | 個人の情報発信 | Build your own personal Digital Garden effortlessly with this Hugo theme |
| 66 | [xiaobright/modeltest](https://github.com/xiaobright/modeltest) | +0.0/日 (暫定) | ⭐ 265 | 1.1日 | Python | ハーネス | Personal LLM engineering-maintenance evaluation harness (V4.1b, frozen). Not a public benchmark. |
| 67 | [iammatthias/com](https://github.com/iammatthias/com) | +0.0/日 (確定(7日)) | ⭐ 245 | 7.7日 | TypeScript | 個人の情報発信 | Digital garden built using Astro, Obsidian, and other goodies.  |
| 68 | [rodmena-limited/stabilize](https://github.com/rodmena-limited/stabilize) | +0.0/日 (確定(7日)) | ⭐ 86 | 7.7日 | Python | 実行グラフ | Queue-Based State Machine - A lightweight  workflow execution engine with DAG-based stage orchestration. Unlike simple task queues (like Celery) or advanced orchestrators (like Highway), Stabilize strikes a balance specifically optimized for high-throughput, stateful DAG execution, making it highly suitable for coordinating autonomous AI agents |
| 69 | [byenzyme/enzyme](https://github.com/byenzyme/enzyme) | +0.0/日 (確定(7日)) | ⭐ 59 | 7.7日 | TypeScript | ナレッジ, 意味グラフ | A compile step for knowledge bases. Gives your agent a concept graph of your content — under 20s to index, 8ms queries on device. |
| 70 | [procoders/superpowers-v](https://github.com/procoders/superpowers-v) | +0.0/日 (確定(7日)) | ⭐ 36 | 7.7日 | Python | ループ | Compound V — a multi-model orchestrator for Claude Code, layered on Superpowers: a deterministic router (Opus for risky work, Sonnet for the mechanical), cross-model review (Claude + Codex), 3 scouts (code · docs · domain), semantic memory, and Epic/Marathon autonomous loop mode. The pill that turns one freelancer into a squad. |
| 71 | [dialexity/dialectical-framework](https://github.com/dialexity/dialectical-framework) | +0.0/日 (確定(7日)) | ⭐ 19 | 7.7日 | Python | 意味グラフ | An open-source AI reasoning framework that uses dialectics, semantic graphs, and polarity management to drive LLMs toward objective synthesis and advanced human-AI collaborative decision-making. |
| 72 | [6ixGODD/mine](https://github.com/6ixGODD/mine) | +0.0/日 (確定(7日)) | ⭐ 17 | 7.7日 | Rust | 実行グラフ | Document-driven software engineering for coding agents, with Git worktrees, execution graphs, and independent review. |
| 73 | [vdutts7/glidercli](https://github.com/vdutts7/glidercli) | +0.0/日 (暫定) | ⭐ 12 | 5.1日 | JavaScript | ループ | 🚀 Browser automation CLI with autonomous loop execution. Control Chrome via CDP, run YAML tasks, Ralph Wiggum loops. |
| 74 | [matiadev/joy-of-code](https://github.com/matiadev/joy-of-code) | +-0.2/日 (暫定) | ⭐ 513 | 5.1日 | Svelte | 個人の情報発信 | 🌸 Joy of Code is a digital garden growing curious minds |
| 75 | [Martian-Engineering/lossless-claw](https://github.com/Martian-Engineering/lossless-claw) | +-0.4/日 (確定(7日)) | ⭐ 4,894 | 7.7日 | TypeScript | 記憶 / AIコンテキスト | Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw |
| 76 | [lemony-ai/cascadeflow](https://github.com/lemony-ai/cascadeflow) | +-1.8/日 (確定(7日)) | ⭐ 3,953 | 7.7日 | Python | ループ | Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop. |