AI・開発ツール・基盤技術の GitHub 新着観測&Star日速分析
sonar.jsonl| # | リポジトリ | 日速 | Star数 | 推移 | 観測日数 | タグ |
|---|---|---|---|---|---|---|
| 1 |
● TypeScriptDeepSeek Harness: Everything is a Plugin.
|
+1363.4/日 確定(7日) | ⭐ 230,221 | 14.9日 | ||
| 2 |
● JavaScriptThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
|
+917.0/日 確定(7日) | ⭐ 263,012 | 14.9日 | ||
| 3 |
● TypeScriptAI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
|
+453.0/日 確定(7日) | ⭐ 107,375 | 14.9日 | ||
| 4 |
● PythonTurn 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.
|
+373.2/日 確定(7日) | ⭐ 119,672 | 14.9日 | ||
| 5 |
● TypeScriptDSHDesktop:DeepSeek Harness Desktop / DeepSeek Harness 桌面版
|
+334.8/日 確定(7日) | ⭐ 7,717 | 9.2日 | ||
| 6 |
● 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」。
|
+293.3/日 確定(7日) | ⭐ 27,794 | 14.9日 | ||
| 7 |
● TypeScriptSketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts.
|
+206.7/日 確定(7日) | ⭐ 7,598 | 12.2日 | ||
| 8 |
● PythonSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
|
+198.5/日 確定(7日) | ⭐ 38,107 | 14.9日 | ||
| 9 |
● TypeScriptGraphs 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.
|
+178.1/日 確定(7日) | ⭐ 83,333 | 14.9日 | ||
| 10 |
● CPre-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
|
+139.1/日 確定(7日) | ⭐ 71,508 | 14.9日 | ||
| 11 |
● PowerShellReverse 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
|
+137.3/日 確定(7日) | ⭐ 36,569 | 14.9日 | ||
| 12 |
● PythonA curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表
|
+132.6/日 確定(7日) | ⭐ 16,304 | 14.9日 | ||
| 13 |
● CHigh-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.
|
+120.0/日 確定(7日) | ⭐ 43,835 | 14.9日 | ||
| 14 |
● TypeScript🌊 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
|
+104.3/日 確定(7日) | ⭐ 72,872 | 8.2日 | ||
| 15 |
● PythonA privacy-first app that strips AI watermarks from content you own.
|
+91.1/日 確定(7日) | ⭐ 22,389 | 14.9日 | ||
| 16 |
● TypeScriptTencentDB 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.
|
+90.4/日 確定(7日) | ⭐ 27,007 | 14.9日 | ||
| 17 |
● PythonBash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
|
+90.3/日 確定(7日) | ⭐ 77,211 | 14.9日 | ||
| 18 |
● PythonHindsight: Agent Memory That Learns
|
+70.2/日 確定(7日) | ⭐ 23,967 | 14.9日 | ||
| 19 |
● TypeScriptOpen-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.
|
+64.8/日 確定(7日) | ⭐ 5,181 | 14.9日 | ||
| 20 |
● TypeScriptDeepSeek Harness (DSH) Web Plugin Aggregation Ecosystem · Everything is a plugin, distributed via the Creative Workshop
|
+55.4/日 確定(7日) | ⭐ 7,810 | 14.9日 | ||
| 21 |
● HTMLOpen-source ThreeUI Community catalog with live interactive components and complete Community source.
|
+51.7/日 確定(7日) | ⭐ 5,971 | 14.9日 | ||
| 22 |
● TypeScriptThere 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.
|
+43.7/日 確定(7日) | ⭐ 72,781 | 14.9日 | ||
| 23 |
● PythonThe batteries-included agent harness.
|
+35.2/日 確定(7日) | ⭐ 29,580 | 14.9日 | ||
| 24 |
● RustSpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
|
+31.5/日 確定(7日) | ⭐ 26,902 | 14.9日 | ||
| 25 |
A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos.
|
+29.4/日 確定(7日) | ⭐ 5,350 | 14.9日 | ||
| 26 |
● PythonBuild Real-Time Knowledge Graphs for AI Agents
|
+28.0/日 確定(7日) | ⭐ 31,015 | 9.2日 | ||
| 27 |
● TypeScriptGitNexus: 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
|
+27.6/日 確定(7日) | ⭐ 47,453 | 14.9日 | ||
| 28 |
● PythonOpen-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)
|
+19.2/日 確定(7日) | ⭐ 47,045 | 14.9日 | ||
| 29 |
● TypeScriptComposio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
|
+16.5/日 確定(7日) | ⭐ 30,254 | 14.9日 | ||
| 30 |
● TypeScriptBuild your personal knowledge base with Trilium Notes
|
+15.4/日 確定(7日) | ⭐ 37,908 | 14.9日 | ||
| 31 |
● TypeScriptThe fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.
|
+15.0/日 確定(7日) | ⭐ 40,628 | 14.9日 | ||
| 32 |
● PythonA framework for few-shot evaluation of language models.
|
+10.8/日 確定(7日) | ⭐ 14,031 | 14.9日 | ||
| 33 |
● TypeScriptFastGPT 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.
|
+8.8/日 確定(7日) | ⭐ 29,694 | 14.9日 | ||
| 34 |
● TypeScript🌱 a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites
|
+8.4/日 確定(7日) | ⭐ 13,269 | 14.9日 | ||
| 35 |
● RustA modern static site generator by the Material for MkDocs team
|
+7.4/日 確定(7日) | ⭐ 5,739 | 14.9日 | ||
| 36 |
● PythonA 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.
|
+7.2/日 確定(7日) | ⭐ 18,011 | 14.9日 | ||
| 37 |
● PythonCurated 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.
|
+5.9/日 確定(7日) | ⭐ 1,241 | 14.9日 | ||
| 38 |
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
|
+5.3/日 確定(7日) | ⭐ 3,651 | 14.9日 | ||
| 39 |
● RustA fast static site generator in a single binary with everything built-in. https://www.getzola.org
|
+5.2/日 確定(7日) | ⭐ 17,457 | 14.9日 | ||
| 40 |
● RustXERJ 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.
|
+4.8/日 確定(7日) | ⭐ 1,940 | 14.9日 | ||
| 41 |
● PythonLocal-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.
|
+4.6/日 確定(7日) | ⭐ 386 | 14.9日 | ||
| 42 |
● JavaScriptdsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).
|
+3.9/日 確定(7日) | ⭐ 7,198 | 14.9日 | ||
| 43 |
● TypeScriptVite & Vue powered static site generator.
|
+3.8/日 確定(7日) | ⭐ 18,335 | 14.9日 | ||
| 44 |
● JavaScriptA Git-based CMS for Static Site Generators
|
+3.1/日 確定(7日) | ⭐ 19,393 | 14.9日 | ||
| 45 |
● JavaScriptA library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.
|
+3.1/日 確定(7日) | ⭐ 3,145 | 8.2日 | ||
| 46 |
● PythonOne framework to evaluate any VLA model on any robot simulation benchmark.
|
+2.7/日 確定(7日) | ⭐ 616 | 14.9日 | ||
| 47 |
● PythonLossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message
|
+2.5/日 確定(7日) | ⭐ 1,140 | 14.9日 | ||
| 48 |
● ShellAgent-native executable language for AI-native development: Agents build programs; humans govern verifiable semantic graphs.
|
+2.4/日 確定(7日) | ⭐ 94 | 14.9日 | ||
| 49 |
● Go⚡️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
|
+2.1/日 確定(7日) | ⭐ 5,628 | 14.9日 | ||
| 50 |
● TypeScript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
|
+2.0/日 確定(7日) | ⭐ 266 | 12.2日 | ||
| 51 |
● CCodeGraph 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.
|
+1.7/日 確定(7日) | ⭐ 97 | 14.9日 | ||
| 52 |
● PythonAwesome 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。
|
+1.3/日 確定(7日) | ⭐ 1,222 | 14.9日 | ||
| 53 |
● TypeScript
|
+1.1/日 確定(7日) | ⭐ 2,503 | 14.9日 | ||
| 54 |
● PythonEvaluation harness for Apodex-1.0 on public deep-research benchmarks.
|
+1.1/日 確定(7日) | ⭐ 443 | 14.9日 | ||
| 55 |
● TypeScriptA compile step for knowledge bases. Gives your agent a concept graph of your content — under 20s to index, 8ms queries on device.
|
+0.6/日 確定(7日) | ⭐ 63 | 14.9日 | ||
| 56 |
● TypeScriptThe data primitive for the agent loop.
|
+0.3/日 確定(7日) | ⭐ 1,694 | 14.9日 | ||
| 57 |
● PythonAuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.
|
+0.3/日 確定(7日) | ⭐ 1,170 | 14.9日 | ||
| 58 |
● ShellRanked list of awesome digital gardens / second brains
|
+0.3/日 確定(7日) | ⭐ 593 | 14.9日 | ||
| 59 |
● TypeScript🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers
|
+0.3/日 確定(7日) | ⭐ 245 | 14.9日 | ||
| 60 |
● GoFast, efficient, and scalable distributed map/reduce system, DAG execution, in memory or on disk, written in pure Go, runs standalone or distributedly.
|
+0.1/日 確定(7日) | ⭐ 3,565 | 14.9日 | ||
| 61 |
● PythonRAPTOR autonomous looping multi-altitude security vulnerability hunt — Claude Code skill
|
+0.1/日 確定(7日) | ⭐ 218 | 14.9日 | ||
| 62 |
● PythonCompound 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.
|
+0.1/日 確定(7日) | ⭐ 37 | 14.9日 | ||
| 63 |
● PythonClaw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
|
+0.0/日 確定(7日) | ⭐ 773 | 14.9日 | ||
| 64 |
● Svelte🌸 Joy of Code is a digital garden growing curious minds
|
+0.0/日 確定(7日) | ⭐ 513 | 12.2日 | ||
| 65 |
● HTMLBuild your own personal Digital Garden effortlessly with this Hugo theme
|
+0.0/日 確定(7日) | ⭐ 298 | 14.9日 | ||
| 66 |
● TypeScriptDigital garden built using Astro, Obsidian, and other goodies.
|
+0.0/日 確定(7日) | ⭐ 245 | 14.9日 | ||
| 67 |
● Go💥 Fast, Git-native framework for building knowledge bases - Static site generator for digital gardens and personal wikis
|
+0.0/日 確定(7日) | ⭐ 233 | 14.9日 | ||
| 68 |
● PythonQueue-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
|
+0.0/日 確定(7日) | ⭐ 86 | 14.9日 | ||
| 69 |
● PythonA 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.
|
+0.0/日 確定(7日) | ⭐ 52 | 14.9日 | ||
| 70 |
● PythonAn 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.
|
+0.0/日 確定(7日) | ⭐ 19 | 14.9日 | ||
| 71 |
● JavaScript🚀 Browser automation CLI with autonomous loop execution. Control Chrome via CDP, run YAML tasks, Ralph Wiggum loops.
|
+0.0/日 確定(7日) | ⭐ 12 | 12.2日 | ||
| 72 |
● TypeScriptLossless Claw — LCM (Lossless Context Management) plugin for OpenClaw
|
+-0.1/日 確定(7日) | ⭐ 4,893 | 14.9日 | ||
| 73 |
● PythonPersonal LLM engineering-maintenance evaluation harness (V4.1b, frozen). Not a public benchmark.
|
+-0.1/日 確定(7日) | ⭐ 264 | 8.2日 | ||
| 74 |
● RustDocument-driven software engineering for coding agents, with Git worktrees, execution graphs, and independent review.
|
+-0.1/日 確定(7日) | ⭐ 16 | 14.9日 | ||
| 75 |
● PythonCascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
|
+-0.7/日 確定(7日) | ⭐ 3,948 | 14.9日 | ||
| 76 |
● PythonAutonomous research system for measurable, computer-executable research.
|
+-44.3/日 確定(7日) | ⭐ 6,246 | 14.9日 | ||
| 77 |
● Ruby:globe_with_meridians: Jekyll is a blog-aware static site generator in Ruby
|
計測待ち 計測待ち | ⭐ 51,676 | 0.0日 | ||
| 78 |
● RustOpenHuman is an open source agent harness with local-first memory, agent orchestration, and workflows
|
計測待ち 計測待ち | ⭐ 39,899 | 0.0日 | ||
| 79 |
● Pythoni. am. speed.
|
計測待ち 計測待ち | ⭐ 8,936 | 0.0日 | ||
| 80 |
● HTML按性价比排序的循证生活指南:长寿防病、急救、省钱理财、法律红线、失业与工伤、医保社保、恋爱婚育、怀孕育儿、创业与做平台合规、出国与技能。每条写明成本、收益、证据等级和原始出处,只引期刊论文与官方文件。
|
計測待ち 計測待ち | ⭐ 6,058 | 0.0日 | ||
| 81 |
● JavaScriptInstall, tune and restore DLSS 5 in your games with one click. Native RenoDX, DLSS5-Feeder for games without DLSS, OptiScaler and multipass routes; DirectX 8/9/11/12, Vulkan, OpenGL, DirectDraw and emulators. In-game F8 overlay, automatic backups, and a community page showing what works on your games and your graphics card.
|
計測待ち 計測待ち | ⭐ 5,941 | 0.0日 | ||
| 82 |
● TypeScriptChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
|
計測待ち 計測待ち | ⭐ 5,595 | 0.0日 | ||
| 83 |
● Python《深入理解 AI Infra:量化分析与系统设计》(李博杰 著)开源书稿:从硬件约束和模型架构出发,量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
|
計測待ち 計測待ち | ⭐ 4,558 | 0.0日 | ||
| 84 |
● RustSpotify, native and fast. One lightweight Rust app for your whole library, local playback, and Spotify Connect on Linux, macOS, and Windows.
|
計測待ち 計測待ち | ⭐ 4,434 | 0.0日 | ||
| 85 |
● TypeScriptClaude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
|
計測待ち 計測待ち | ⭐ 4,338 | 0.0日 | ||
| 86 |
● TeX
|
計測待ち 計測待ち | ⭐ 4,211 | 0.0日 | ||
| 87 |
● TypeScript我的第二大脑 second brain,我的数字花园 digital garden,用obsidian双链笔记软件写作而成
|
計測待ち 計測待ち | ⭐ 2,461 | 0.0日 | ||
| 88 |
A curated list of awesome Public Zettelkastens 🗄️ / Second Brains 🧠 / Digital Gardens 🌱
|
計測待ち 計測待ち | ⭐ 1,841 | 0.0日 | ||
| 89 |
● PythonSelf-improving AI agent harness — propose, eval, approve, ship. AHE autonomous loop + MCP + BYOK + eval suite.
|
計測待ち 計測待ち | ⭐ 158 | 0.0日 |