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 |
● RustCraft Anything: understand how any software works, and craft your own.
|
+2176.5/日 確定(7日) | ⭐ 31,431 | 9.0日 | ||
| 2 |
● JavaScript在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费,不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap.
|
+1345.2/日 確定(7日) | ⭐ 72,843 | 31.0日 | ||
| 3 |
● Dartdsh-go — DeepSeek Harness 装进口袋:手机本机运行,也能遥控你的电脑。
|
+1234.6/日 暫定 | ⭐ 21,810 | 6.0日 | ||
| 4 |
● TypeScriptDeepSeek Harness: Everything is a Plugin.
|
+881.4/日 確定(7日) | ⭐ 280,508 | 69.8日 | ||
| 5 |
● PythonAuto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for LLM and agent workflows.
|
+835.3/日 確定(7日) | ⭐ 12,564 | 37.0日 | ||
| 6 |
● JavaScriptA Claude skill that turns vibecoded, AI-looking UI into a designed interface
|
+714.0/日 暫定 | ⭐ 15,672 | 6.0日 | ||
| 7 |
● GoEvery agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
|
+706.1/日 確定(7日) | ⭐ 36,109 | 28.1日 | ||
| 8 |
● PythonDebloat any Android or Google TV over Wi-Fi and get an Apple TV-style home.
|
+601.3/日 確定(7日) | ⭐ 57,444 | 22.1日 | ||
| 9 |
● JavaScriptThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
|
+579.1/日 確定(7日) | ⭐ 302,472 | 69.8日 | ||
| 10 |
● 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.
|
+537.6/日 確定(7日) | ⭐ 147,295 | 69.8日 | ||
| 11 |
● TypeScriptTowards a More Autonomous Agent System
|
+493.0/日 確定(7日) | ⭐ 23,023 | 9.0日 | ||
| 12 |
● C++Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
|
+438.8/日 確定(7日) | ⭐ 43,915 | 40.1日 | ||
| 13 |
● PythonSwitch games running natively on iPhone, iPad and Mac: an NSP folder becomes an unsigned IPA (NSO rewriter, Horizon HLE host, NVN→Metal)
|
+349.8/日 確定(7日) | ⭐ 15,326 | 13.1日 | ||
| 14 |
● CYour GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
|
+289.7/日 確定(7日) | ⭐ 19,243 | 13.1日 | ||
| 15 |
● RustSolidCraft: an open-source parametric 3D CAD application built in pure Rust. Desktop, web, and automation through MCP.
|
+278.4/日 確定(7日) | ⭐ 16,155 | 13.1日 | ||
| 16 |
● RustPhotoCraft: An open-source, photo editor written by scratch in pure Rust
|
+252.5/日 確定(7日) | ⭐ 79,197 | 37.0日 | ||
| 17 |
● JavaScriptAn agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D effects.
|
+248.8/日 確定(7日) | ⭐ 27,131 | 28.1日 | ||
| 18 |
● PythonA curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表
|
+241.7/日 確定(7日) | ⭐ 24,582 | 69.8日 | ||
| 19 |
● HTML高性价比人生指南: 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。
|
+238.0/日 確定(7日) | ⭐ 75,583 | 54.9日 | ||
| 20 |
● PythonHindsight: Agent Memory That Learns
|
+228.5/日 確定(7日) | ⭐ 60,898 | 69.8日 | ||
| 21 |
● Kotlin给国产电视的一块干净桌面:参照 tvOS 设计的开源 Android TV 桌面,没有广告,开机自动接管。A tvOS-style launcher for Xiaomi, TCL and other China-market TVs.
|
+226.8/日 確定(7日) | ⭐ 11,670 | 13.1日 | ||
| 22 |
● 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.
|
+218.4/日 確定(7日) | ⭐ 12,116 | 69.8日 | ||
| 23 |
● 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.
|
+215.6/日 確定(7日) | ⭐ 92,552 | 69.8日 | ||
| 24 |
● TypeScriptThe IDE you know, rebuilt in Rust. IntelliJ IDEA–style keymap, tool windows and search-everywhere in a fast native app: editor, code insight, debugger, Git, terminal, database and HTTP clients for 60+ languages.
|
+206.7/日 暫定 | ⭐ 8,912 | 6.0日 | ||
| 25 |
● TypeScriptAI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
|
+199.9/日 確定(7日) | ⭐ 121,874 | 69.8日 | ||
| 26 |
● TypeScriptDSHDesktop:DeepSeek Harness Desktop / DeepSeek Harness 桌面版
|
+155.7/日 確定(7日) | ⭐ 18,673 | 64.1日 | ||
| 27 |
● 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」。
|
+119.2/日 確定(7日) | ⭐ 35,942 | 69.8日 | ||
| 28 |
● RustPdfCraft: An open-source PDF reader and editor written by scratch in pure Rust
|
+118.4/日 確定(7日) | ⭐ 20,627 | 31.0日 | ||
| 29 |
● Python
|
+118.2/日 確定(7日) | ⭐ 23,733 | 22.1日 | ||
| 30 |
● PythonA privacy-first app that strips AI watermarks from content you own.
|
+117.7/日 確定(7日) | ⭐ 27,367 | 69.8日 | ||
| 31 |
● TypeScriptPre-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
|
+106.4/日 確定(7日) | ⭐ 77,552 | 69.8日 | ||
| 32 |
● 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.
|
+89.3/日 確定(7日) | ⭐ 8,468 | 23.9日 | ||
| 33 |
● 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
|
+85.1/日 確定(7日) | ⭐ 81,648 | 63.1日 | ||
| 34 |
● RustFilmCraft: An open-source, nonlinear video editor written by scratch in pure Rust
|
+75.8/日 確定(7日) | ⭐ 18,216 | 31.0日 | ||
| 35 |
● PythonSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
|
+73.3/日 確定(7日) | ⭐ 42,205 | 69.8日 | ||
| 36 |
● RustAn open-source, clean-room reimplementation of Microsoft Word in pure Rust
|
+73.2/日 確定(7日) | ⭐ 17,970 | 28.1日 | ||
| 37 |
● RustSpotify, native and fast. One lightweight Rust app for your whole library, local playback, and Spotify Connect on Linux, macOS, and Windows.
|
+67.6/日 確定(7日) | ⭐ 10,304 | 54.9日 | ||
| 38 |
● PythonDeepInfer: High-performance, large-scale inference framework for DeepSeek models
|
+65.2/日 確定(7日) | ⭐ 25,970 | 22.1日 | ||
| 39 |
● 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
|
+56.3/日 確定(7日) | ⭐ 44,618 | 69.8日 | ||
| 40 |
● KotlinIndependent CarPlay receiver for compatible Android head units. Wired and wireless public preview.
|
+55.0/日 確定(7日) | ⭐ 13,759 | 34.0日 | ||
| 41 |
● CHigh-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
|
+54.9/日 確定(7日) | ⭐ 48,612 | 69.8日 | ||
| 42 |
● PythonNon-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
|
+54.7/日 確定(7日) | ⭐ 35,509 | 52.1日 | ||
| 43 |
● PythonBash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
|
+54.5/日 確定(7日) | ⭐ 80,380 | 69.8日 | ||
| 44 |
● RustLightCraft: An open-source non-destructive photo editor written by scratch in pure Rust
|
+50.0/日 確定(7日) | ⭐ 15,945 | 34.0日 | ||
| 45 |
● 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.
|
+47.8/日 確定(7日) | ⭐ 30,881 | 69.8日 | ||
| 46 |
● HTML《高性价比人生指南》全书 528 条的在线单页阅读版:手机可读、可搜索、零依赖、支持离线
|
+44.6/日 確定(7日) | ⭐ 14,605 | 43.0日 | ||
| 47 |
● TypeScriptDeepSeek Harness (DSH) Web Plugin Aggregation Ecosystem · Everything is a plugin, distributed via the Creative Workshop
|
+36.2/日 確定(7日) | ⭐ 10,402 | 69.8日 | ||
| 48 |
● PythonFastest and cheapest web agent
|
+33.8/日 確定(7日) | ⭐ 24,485 | 54.9日 | ||
| 49 |
● TypeScriptSketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts.
|
+32.9/日 確定(7日) | ⭐ 10,337 | 67.1日 | ||
| 50 |
● 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.
|
+32.0/日 確定(7日) | ⭐ 74,514 | 69.8日 | ||
| 51 |
● PythonThe batteries-included agent harness.
|
+31.6/日 確定(7日) | ⭐ 31,269 | 69.8日 | ||
| 52 |
● PythonSelf-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.
|
+30.0/日 確定(7日) | ⭐ 16,446 | 22.1日 | ||
| 53 |
● PythonBuild Real-Time Knowledge Graphs for AI Agents
|
+29.8/日 確定(7日) | ⭐ 32,795 | 64.1日 | ||
| 54 |
● TypeScriptLLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。
|
+29.0/日 確定(7日) | ⭐ 21,644 | 22.1日 | ||
| 55 |
● 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
|
+27.7/日 確定(7日) | ⭐ 7,566 | 54.9日 | ||
| 56 |
● 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
|
+27.4/日 確定(7日) | ⭐ 48,519 | 69.8日 | ||
| 57 |
● TypeScriptBuild your personal knowledge base with Trilium Notes
|
+24.3/日 確定(7日) | ⭐ 38,922 | 69.8日 | ||
| 58 |
● SwiftThe Photoshop alternative for Mac
|
+24.0/日 確定(7日) | ⭐ 18,653 | 43.1日 | ||
| 59 |
● Lean
|
+20.9/日 確定(7日) | ⭐ 17,524 | 37.0日 | ||
| 60 |
● TypeScriptZ.ai's coding agent harness. Powerful, intelligent, extensible.
|
+20.6/日 確定(7日) | ⭐ 8,670 | 52.1日 | ||
| 61 |
● HTMLOpen-source ThreeUI Community catalog with live interactive components and complete Community source.
|
+18.8/日 確定(7日) | ⭐ 7,273 | 69.8日 | ||
| 62 |
A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos.
|
+18.2/日 確定(7日) | ⭐ 6,553 | 69.8日 | ||
| 63 |
● PythonJev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
|
+17.2/日 確定(7日) | ⭐ 9,978 | 49.1日 | ||
| 64 |
● RustThe fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
|
+15.8/日 確定(7日) | ⭐ 42,688 | 54.9日 | ||
| 65 |
● TypeScriptComposio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
|
+15.8/日 確定(7日) | ⭐ 31,062 | 69.8日 | ||
| 66 |
● PythonOpen-source personal 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.
|
+14.6/日 確定(7日) | ⭐ 47,919 | 69.8日 | ||
| 67 |
● 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.
|
+13.7/日 確定(7日) | ⭐ 7,969 | 54.9日 | ||
| 68 |
● Kotlin装在手机上的对话副驾:在 QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框,发不发由你。非侵入,只读屏幕,不 hook 不改包。
|
+12.8/日 確定(7日) | ⭐ 8,373 | 49.1日 | ||
| 69 |
● TypeScriptThe fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.
|
+10.2/日 確定(7日) | ⭐ 41,264 | 69.8日 | ||
| 70 |
● RustA modern static site generator by the Material for MkDocs team
|
+9.3/日 確定(7日) | ⭐ 6,170 | 69.8日 | ||
| 71 |
● RustSpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
|
+9.0/日 確定(7日) | ⭐ 27,764 | 69.8日 | ||
| 72 |
● PythonAn evaluation harness for medical/health AI agents — reproduce and cover multiple benchmarks under one scoring discipline
|
+6.9/日 確定(7日) | ⭐ 349 | 25.0日 | ||
| 73 |
● PythonA framework for few-shot evaluation of language models.
|
+6.8/日 確定(7日) | ⭐ 14,462 | 69.8日 | ||
| 74 |
● JavaScriptAgent-native executable language for AI-native development: Agents build programs; humans govern verifiable semantic graphs.
|
+6.4/日 確定(7日) | ⭐ 183 | 69.8日 | ||
| 75 |
● TypeScript🌱 a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites
|
+6.3/日 確定(7日) | ⭐ 13,584 | 69.8日 | ||
| 76 |
● TypeScriptChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
|
+5.9/日 確定(7日) | ⭐ 7,700 | 54.9日 | ||
| 77 |
● 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.
|
+5.3/日 確定(7日) | ⭐ 18,347 | 69.8日 | ||
| 78 |
● 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.
|
+4.8/日 確定(7日) | ⭐ 30,037 | 69.8日 | ||
| 79 |
● TypeScriptTurn meetings into live agent loops. Record, transcribe, and analyze meetings with real-time AI intelligence — before, during, and after calls.
|
+4.2/日 確定(7日) | ⭐ 2,094 | 13.1日 | ||
| 80 |
● PythonNative MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
|
+3.9/日 確定(7日) | ⭐ 7,102 | 52.1日 | ||
| 81 |
● TypeScriptVite & Vue powered static site generator.
|
+3.6/日 確定(7日) | ⭐ 18,490 | 69.8日 | ||
| 82 |
● PythonClaw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
|
+3.4/日 確定(7日) | ⭐ 931 | 69.8日 | ||
| 83 |
● TypeScriptA compile step for knowledge bases. Gives your agent a concept graph of your content — under 20s to index, 8ms queries on device.
|
+3.3/日 確定(7日) | ⭐ 157 | 69.8日 | ||
| 84 |
● Ruby:globe_with_meridians: Jekyll is a blog-aware static site generator in Ruby
|
+3.1/日 確定(7日) | ⭐ 51,773 | 54.9日 | ||
| 85 |
● 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.
|
+3.0/日 確定(7日) | ⭐ 1,478 | 69.8日 | ||
| 86 |
● RustRuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust.
|
+2.9/日 確定(7日) | ⭐ 4,694 | 49.1日 | ||
| 87 |
● RustA fast static site generator in a single binary with everything built-in. https://www.getzola.org
|
+2.8/日 確定(7日) | ⭐ 17,604 | 69.8日 | ||
| 88 |
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
|
+2.3/日 確定(7日) | ⭐ 3,828 | 69.8日 | ||
| 89 |
● JavaScriptdsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).
|
+2.2/日 確定(7日) | ⭐ 7,021 | 69.8日 | ||
| 90 |
● JavaScriptA library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.
|
+2.1/日 確定(7日) | ⭐ 3,243 | 63.1日 | ||
| 91 |
● PythonInfrastructure for continually self‑improving agents
|
+2.0/日 確定(7日) | ⭐ 7,816 | 47.0日 | ||
| 92 |
● JavaScriptA Git-based CMS for Static Site Generators
|
+1.9/日 確定(7日) | ⭐ 19,477 | 69.8日 | ||
| 93 |
● 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) | ⭐ 155 | 69.8日 | ||
| 94 |
● 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
|
+1.3/日 確定(7日) | ⭐ 5,742 | 69.8日 | ||
| 95 |
● PythonLong-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.
|
+1.2/日 確定(7日) | ⭐ 4,317 | 19.1日 | ||
| 96 |
● TypeScriptThe data primitive for the agent loop.
|
+1.1/日 確定(7日) | ⭐ 1,727 | 69.8日 | ||
| 97 |
● PythonLossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message
|
+1.0/日 確定(7日) | ⭐ 1,323 | 69.8日 | ||
| 98 |
● 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.
|
+1.0/日 確定(7日) | ⭐ 438 | 69.8日 | ||
| 99 |
● 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。
|
+0.8/日 確定(7日) | ⭐ 1,308 | 69.8日 | ||
| 100 |
● TypeScriptHierarchal Agent Loop Optimizer
|
+0.8/日 確定(7日) | ⭐ 1,213 | 16.0日 | ||
| 101 |
● Python开源、本地优先的求职 Agent:管理投递、准备面试与整理 Offer;附 Agent Loop、Harness 源码导读和动手实验。
|
+0.8/日 確定(7日) | ⭐ 766 | 19.1日 | ||
| 102 |
● PythonOne framework to evaluate any VLA model on any robot simulation benchmark.
|
+0.8/日 確定(7日) | ⭐ 679 | 69.8日 | ||
| 103 |
● PythonAutonomous research system for measurable, computer-executable research.
|
+0.7/日 確定(7日) | ⭐ 5,530 | 69.8日 | ||
| 104 |
● 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
|
+0.6/日 確定(7日) | ⭐ 283 | 67.1日 | ||
| 105 |
● PythonRAPTOR autonomous looping multi-altitude security vulnerability hunt — Claude Code skill
|
+0.6/日 確定(7日) | ⭐ 278 | 69.8日 | ||
| 106 |
● TypeScript
|
+0.4/日 確定(7日) | ⭐ 2,530 | 69.8日 | ||
| 107 |
A curated list of awesome Public Zettelkastens 🗄️ / Second Brains 🧠 / Digital Gardens 🌱
|
+0.4/日 確定(7日) | ⭐ 1,863 | 54.9日 | ||
| 108 |
● Rust100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management
|
+0.4/日 確定(7日) | ⭐ 915 | 37.0日 | ||
| 109 |
● PythonHierarchical agent loops with recursive self-organization.
|
+0.4/日 確定(7日) | ⭐ 793 | 31.0日 | ||
| 110 |
● PythonRequirement-driven evaluation harness for AI agents and LLM applications. Generate behavior-specific test cases, run them against any target (hosted models, callable wrappers, OTel-traced agents), and inspect local-first artifacts.
|
+0.4/日 確定(7日) | ⭐ 364 | 49.1日 | ||
| 111 |
● 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
|
+0.3/日 確定(7日) | ⭐ 2,466 | 54.9日 | ||
| 112 |
● PHPCTX: a tool that solves the context management gap when working with LLMs like ChatGPT or Claude. It helps developers organize and automatically collect information from their codebase into structured documents that can be easily shared with AI assistants.
|
+0.3/日 暫定 | ⭐ 343 | 3.0日 | ||
| 113 |
● PythonAuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.
|
+0.2/日 確定(7日) | ⭐ 1,181 | 69.8日 | ||
| 114 |
● ShellRanked list of awesome digital gardens / second brains
|
+0.1/日 確定(7日) | ⭐ 612 | 69.8日 | ||
| 115 |
● 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.
|
+0.1/日 確定(7日) | ⭐ 56 | 69.8日 | ||
| 116 |
● 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.
|
+0.1/日 確定(7日) | ⭐ 23 | 69.8日 | ||
| 117 |
● PythonOpen-source, self-hosted AI employees that ask before they act. 46 business roles, approval-gated autonomy, untrusted-content safeguards, sandboxed execution, Graph RAG and token budgets. Expanding across memory, voice, security and physical AI. WhatsApp, Telegram, Discord and 20 LLM providers. MIT licensed.
|
+0.1/日 確定(7日) | ⭐ 21 | 9.0日 | ||
| 118 |
● TypeScriptLossless Claw — LCM (Lossless Context Management) plugin for OpenClaw
|
+0.0/日 確定(7日) | ⭐ 4,920 | 69.8日 | ||
| 119 |
● GoFast, efficient, and scalable distributed map/reduce system, DAG execution, in memory or on disk, written in pure Go, runs standalone or distributedly.
|
+0.0/日 確定(7日) | ⭐ 3,569 | 69.8日 | ||
| 120 |
● PythonRAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.
|
+0.0/日 確定(7日) | ⭐ 961 | 47.0日 | ||
| 121 |
● Svelte🌸 Joy of Code is a digital garden growing curious minds
|
+0.0/日 確定(7日) | ⭐ 512 | 67.1日 | ||
| 122 |
● PythonEvaluation harness for Apodex-1.0 on public deep-research benchmarks.
|
+0.0/日 確定(7日) | ⭐ 464 | 69.8日 | ||
| 123 |
● HTMLBuild your own personal Digital Garden effortlessly with this Hugo theme
|
+0.0/日 確定(7日) | ⭐ 299 | 69.8日 | ||
| 124 |
● PythonPersonal LLM engineering-maintenance evaluation harness (V4.1b, frozen). Not a public benchmark.
|
+0.0/日 確定(7日) | ⭐ 259 | 63.1日 | ||
| 125 |
● TypeScript🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers
|
+0.0/日 確定(7日) | ⭐ 247 | 69.8日 | ||
| 126 |
● RustDigital garden built using Astro, Obsidian, and other goodies.
|
+0.0/日 確定(7日) | ⭐ 246 | 69.8日 | ||
| 127 |
● 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) | ⭐ 236 | 69.8日 | ||
| 128 |
● PythonSelf-improving AI agent harness — propose, eval, approve, ship. AHE autonomous loop + MCP + BYOK + eval suite.
|
+0.0/日 確定(7日) | ⭐ 159 | 54.9日 | ||
| 129 |
● 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) | ⭐ 87 | 69.8日 | ||
| 130 |
● PythonAn open-source adaptive AI framework with DAG execution, execution-history learning, prompt evolution, and multi-layer memory.
|
+0.0/日 確定(7日) | ⭐ 58 | 49.1日 | ||
| 131 |
● 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.
|
+0.0/日 確定(7日) | ⭐ 42 | 69.8日 | ||
| 132 |
● PythonBy transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure." For an AI assistant, it provides the "spatial" awareness needed to navigate deep dependencies without getting lost in large files.
|
+0.0/日 暫定 | ⭐ 37 | 3.0日 | ||
| 133 |
● TypeScriptA DeepSeek Harness (DSH) client plugin that adds an "Execution graph" tab to the conversation view. It reconstructs one session turn's activity as a vertical timeline on a React Flow canvas
|
+0.0/日 暫定 | ⭐ 21 | 3.0日 | ||
| 134 |
● TypeScriptType-safe DAG execution engine for AI workflows
|
+0.0/日 確定(7日) | ⭐ 18 | 28.1日 | ||
| 135 |
● RustDocument-driven software engineering for coding agents, with Git worktrees, execution graphs, and independent review.
|
+0.0/日 確定(7日) | ⭐ 16 | 69.8日 | ||
| 136 |
● PythonEnd-to-end retail lakehouse on Databricks: dual-path ingestion from PostgreSQL and S3, dbt-modeled galaxy schema with SCD2 history, Airflow orchestration with parallel DAG execution, CI-gated dbt tests, and a dual consumption layer via Power BI and a Genie Agent.
|
+0.0/日 確定(7日) | ⭐ 16 | 47.0日 | ||
| 137 |
● JavaScriptContext engineering and governed workflows for AI coding agents. Keep project knowledge coherent, route work to specialists, and scale from small fixes to bounded autonomous loops.
|
+0.0/日 確定(7日) | ⭐ 14 | 43.1日 | ||
| 138 |
● 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 | 67.1日 | ||
| 139 |
● JavaScriptLocal-first AI knowledge maps for turning learning sessions into source-grounded concept graphs.
|
+0.0/日 確定(7日) | ⭐ 12 | 9.0日 | ||
| 140 |
● PythonCascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
|
+-0.1/日 確定(7日) | ⭐ 3,926 | 69.8日 | ||
| 141 |
● ZigOrchestrates multi-step AI agent workflows — defines execution graphs, manages shared state, dispatches work to agents, and tracks progress with checkpoints and streaming
|
+-0.6/日 確定(7日) | ⭐ 172 | 46.0日 | ||
| 142 |
● TeX
|
+-0.7/日 確定(7日) | ⭐ 4,164 | 54.9日 | ||
| 143 |
● RustAI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
|
+-5.2/日 確定(7日) | ⭐ 19,039 | 69.8日 | ||
| 144 |
● PythonStatic site generator that supports Markdown and reST syntax. Powered by Python.
|
計測待ち 計測待ち | ⭐ 13,374 | 0.0日 | ||
| 145 |
● TypeScriptAgent harness for learning difficult things.
|
計測待ち 計測待ち | ⭐ 9,279 | 0.0日 | ||
| 146 |
● C++VERY experimental Nintendo Switch 2 emulator
|
計測待ち 計測待ち | ⭐ 8,999 | 0.0日 |