なんとかソナー 📡

● 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。

● PythonHindsight: Agent Memory That Learns

● 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.

● PythonFastest and cheapest web agent

● TypeScriptDeepSeek Harness: Everything is a Plugin.

● JavaScriptThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

● PythonInfrastructure for continually self‑improving agents

● 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.

● TypeScriptAI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

● TypeScriptDSHDesktop：DeepSeek Harness Desktop / DeepSeek Harness 桌面版

● 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.

● 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

● PythonJev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

● PythonNative MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

● 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.

● 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」。

● TypeScriptChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.

● 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。

● 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.

● 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.

● TypeScriptZ.ai's coding agent harness. Powerful, intelligent, extensible.

● 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

● PythonA curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表

● TypeScriptSketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts.

● PythonSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

● 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

● PythonA privacy-first app that strips AI watermarks from content you own.

● 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.

● 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

● PythonBash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

● 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.

● 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.

● TypeScriptDeepSeek Harness (DSH) Web Plugin Aggregation Ecosystem · Everything is a plugin, distributed via the Creative Workshop

● HTMLOpen-source ThreeUI Community catalog with live interactive components and complete Community source.

● RustSpotify, native and fast. One lightweight Rust app for your whole library, local playback, and Spotify Connect on Linux, macOS, and Windows.

● 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.

A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos.

● PythonBuild Real-Time Knowledge Graphs for AI Agents

● PythonThe batteries-included agent harness.

● RustOpenHuman is the fastest, cheapest, most efficient open-source agent harness. Written in Rust

● RustSpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

● 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

● TypeScriptBuild your personal knowledge base with Trilium Notes

● 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.

● TypeScriptThe fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.

● PythonLossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message

● TypeScriptComposio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

● 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.

● 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.

● PythonA framework for few-shot evaluation of language models.

● RustA modern static site generator by the Material for MkDocs team

● 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.

● PythonCascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.

● 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

● TypeScript🌱 a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites

● 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.

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

● TypeScriptVite & Vue powered static site generator.

● 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。

● TypeScriptA compile step for knowledge bases. Gives your agent a concept graph of your content — under 20s to index, 8ms queries on device.

● 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.

● Ruby:globe_with_meridians: Jekyll is a blog-aware static site generator in Ruby

● RustRuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust.

● JavaScriptA Git-based CMS for Static Site Generators

● RustA fast static site generator in a single binary with everything built-in. https://www.getzola.org

● PythonOne framework to evaluate any VLA model on any robot simulation benchmark.

● JavaScriptA library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

● PythonEvaluation harness for Apodex-1.0 on public deep-research benchmarks.

● TypeScriptLossless Claw — LCM (Lossless Context Management) plugin for OpenClaw

● TypeScriptThe data primitive for the agent loop.

● PythonRAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.

● PythonClaw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

● 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.

A curated list of awesome Public Zettelkastens 🗄️ / Second Brains 🧠 / Digital Gardens 🌱

● 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

● 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

● ShellRanked list of awesome digital gardens / second brains

● 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

● 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.

● GoFast, efficient, and scalable distributed map/reduce system, DAG execution, in memory or on disk, written in pure Go, runs standalone or distributedly.

● PythonAuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.

● TypeScript🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers

● PythonRAPTOR autonomous looping multi-altitude security vulnerability hunt — Claude Code skill

● ShellAgent-native executable language for AI-native development: Agents build programs; humans govern verifiable semantic graphs.

● 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.

● 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.

● Svelte🌸 Joy of Code is a digital garden growing curious minds

● HTMLBuild your own personal Digital Garden effortlessly with this Hugo theme

● PythonPersonal LLM engineering-maintenance evaluation harness (V4.1b, frozen). Not a public benchmark.

● TypeScriptDigital garden built using Astro, Obsidian, and other goodies.

● Go💥 Fast, Git-native framework for building knowledge bases - Static site generator for digital gardens and personal wikis

● PythonSelf-improving AI agent harness — propose, eval, approve, ship. AHE autonomous loop + MCP + BYOK + eval suite.

● PythonAn open-source adaptive AI framework with DAG execution, execution-history learning, prompt evolution, and multi-layer memory.

● 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.

● RustDocument-driven software engineering for coding agents, with Git worktrees, execution graphs, and independent review.

● JavaScript🚀 Browser automation CLI with autonomous loop execution. Control Chrome via CDP, run YAML tasks, Ralph Wiggum loops.

● JavaScriptdsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).

● PythonAutonomous research system for measurable, computer-executable research.

● ZigOrchestrates multi-step AI agent workflows — defines execution graphs, manages shared state, dispatches work to agents, and tracks progress with checkpoints and streaming