PaperJury is a Claude Code (or Codex) plugin that uses LLM agents to perform a structured, pre‑submission review of LaTeX/Markdown papers. It runs a “review → adjudication → edit → re‑check” loop, classifying each comment as safe‑to‑fix, author‑required, or invalid. Three modes (direct‑edit, review, auto) let users request specific changes, run a mock peer‑review, or let the system operate unattended with safety guards. The tool includes deterministic scripts for LaTeX compilation, compliance checks, and a ledger of decisions. Benchmarks on 12 papers show a 0.656 F1 issue‑detection score and a 4× drop in unsafe edits. Installation is via the Claude Code marketplace or a simple git clone; a full “dog‑food” sample with before/after PDFs is provided.

AURA is an open‑source platform that lets you run AI‑driven SRE agents inside your own infrastructure. It provides a configurable, multi‑agent runtime that can call tools, query observability systems, and execute safe actions—all while keeping data and model usage under your control.

An open-source Python toolkit for speaker diarization that uses pretrained PyTorch models to identify who spoke when in audio recordings.

Hunter Community Edition is an open‑source, Docker‑compose‑deployed financial AI agent platform. With a single LLM API key it provides real‑time market data (32+ sources), 23 pre‑built analysis SKILLs, a local “investment thesis” memory, and plug‑and‑play model compatibility (DeepSeek, Claude, Qwen, etc.). Everything runs on the user’s machine—data, chat history, and thesis stay on local disk—while remaining extensible via custom Markdown SKILLs or user‑provided MCP data services.

Skills Hub is a Tauri‑based desktop app that centralises AI‑coding “skills” (prompt/agent bundles) and syncs them via symlinks or copies to the global or project‑level skill folders of many AI coding tools (Cursor, Claude Code, Codex, etc.). It offers explore‑install, tagging, bulk actions, a recycle bin, automatic Git‑based device sync, and scheduled updates, all configurable through a multilingual UI.

A browser extension that adds real-time voice-over translation and AI subtitles to videos across various websites, allowing users to watch foreign content in their native language.

Agent Vault is an open‑source HTTP proxy that stores secrets and injects them into outbound requests for AI agents, preventing the agents from ever seeing real credentials. It offers a management UI, CLI, per‑agent tokens, pluggable secret back‑ends (including Infisical), egress filtering, request logging, and optional PostgreSQL scaling. Deployable as a single binary or Docker image, it integrates via standard `HTTPS_PROXY` environment variables and is aimed at securing remote‑coding, all‑purpose, custom, and sandboxed AI agents.

Memorix is a Node.js library that adds a local‑first, searchable memory store to any AI coding assistant. It persists facts, design rationales, and Git‑derived insights in a SQLite database, exposing them via MCP, a CLI, and an optional web UI. By installing a single `memorix setup --agent <name>` command, dozens of agents (Claude Code, Codex, Copilot CLI, Cursor, Gemini CLI, etc.) can share the same project‑scoped memory, enabling smoother handoffs, better context retention, and multi‑agent orchestration.

Microsoft / skills is a genuine open‑source toolbox that equips AI coding agents (e.g., GitHub Copilot) with ready‑made, Azure‑specific “skills” – code snippets, templates, and MCP server scaffolding – so the agents can generate correct Azure SDK calls, manage Foundry resources, and follow governance patterns. Install via `npx skills add microsoft/skills`, pick only the needed skills (≈175 across Python, .NET, TypeScript, Java, Rust), and use the provided `AGENTS.md` and MCP configs to build custom agents for backend, frontend, infrastructure, or planning tasks.

ClawGod is a GPL‑licensed wrapper that extracts the official Claude Code binary, applies a set of patches to unlock hidden commands, remove safety restrictions, and add custom behaviour, then runs the patched CLI under Bun. It auto‑updates, offers per‑feature toggles, and works on macOS, Linux, and Windows.

NOFX is an open‑source, self‑hosted trading terminal that lets large language models generate crypto‑perpetual trades. A Go runtime enforces strict risk limits, stores every model‑generated reasoning, and supports nine exchanges. Users fund an on‑chain AI fee wallet, start “Autopilot” to let the model trade automatically, and can compare multiple traders on a public leaderboard. Installation is available via a one‑click script, Docker, Railway, or manual build.

Claudexor is a local‑first Node.js control plane that unifies multiple AI‑coding services (Codex, Claude Code, Cursor, etc.) behind a single typed interface. It provides read‑only queries, patch‑generating write turns, best‑of‑N races with cross‑model review, credential profiles with live quota tracking, deterministic gates for protected files, and a macOS desktop app. All state lives on your machine, there is no telemetry, and the system can run remotely over SSH. The project is actively maintained (v3.10.2) and intended for developers or agents who need auditable, cost‑controlled AI‑assisted coding.

An npm plugin that adds a persistent, evidence‑driven “goal mode” to the OpenCode AI coding assistant, letting agents work on long‑running objectives with auto‑continue, safety limits, and a UI sidebar.

Open‑source MCP (Model Context Protocol) servers that let LLM‑powered tools fetch live AWS documentation, IaC guidance, and safely invoke AWS APIs. Includes managed remote servers and local binaries for docs, IaC, EKS, etc., all accessed via a stdio‑based protocol.

Code‑Graph‑RAG parses multi‑language codebases with Tree‑sitter, stores the AST‑derived structure in a Memgraph knowledge graph, and lets you query, edit and optimise the code via natural‑language prompts powered by an LLM. It supports dozens of languages, runtime trace overlay, and can run as an MCP server for tool integration.

An AI-powered subtitle generation and editing workflow that integrates multiple ASR APIs to transcribe local media and provides a professional editor for refining subtitles.

AudioMuse‑AI is an open‑source, self‑hosted application that analyses the actual audio of your music collection to create sound‑based fingerprints. Using those fingerprints it can cluster similar tracks, generate instant mood‑oriented playlists, map the library on a 2‑D visual canvas, and answer natural‑language queries. It works with Navidrome, Jellyfin, LMS, Lyrion, Emby and Plex, and can be run via Docker‑Compose, a Helm chart, or native macOS/Windows/Linux packages.

A unified C++ speech engine that provides a single binary for 119 ASR and TTS backends with zero Python dependencies.

Self‑hosted web app that photographs your clothes, uses a multimodal LLM (Ollama, OpenAI, etc.) to tag items and generate daily outfit suggestions based on weather and occasion. Docker‑compose (or K8s) deployment, PostgreSQL + Redis backend, Next.js frontend, fully internationalised and privacy‑first.

pi-claude-bridge is a Pi extension that connects the Pi terminal‑assistant to Anthropic’s Claude Code via the Agent SDK. It lets you select Claude models (Opus, Sonnet, Haiku, Fable) as Pi providers, streams responses, forwards Pi tools to Claude, and offers an optional “Ask Claude” tool for delegating sub‑tasks. Configuration is done via a JSON file, and the bridge includes session‑resume, context‑window handling, and detailed debug logs.

A compact, open-source text-to-speech synthesizer using formant synthesis to support over 100 languages with a very small memory footprint.

SkillClaw is an open‑source system that sits between LLM agents and the LLM API, automatically records interactions, extracts reusable “skills”, deduplicates them, and continuously refines them. It works with many agents (Hermes, Codex, Claude Code, QwenPaw, OpenClaw, etc.) and can share a unified skill library across devices, agents, and team members via local storage, OSS, or S3.

Codex Proxy is a local service (desktop app, lightweight “no‑node” zip, or Docker container) that converts the Codex Desktop Responses API into standard OpenAI, Anthropic, Gemini, and Ollama endpoints. After logging in with a ChatGPT account, it issues a local API key; any client that understands the usual `/v1/chat/completions` or `/v1/messages` format can call Codex, with full support for streaming, function/tool calling, structured outputs, image generation, multi‑account rotation, and TLS fingerprint spoofing.

A local Excalidraw canvas that AI agents can control via CLI, MCP, or REST, enabling programmatic creation, inspection, and version‑controlled export of diagrams.

RhinoMCP is an open‑source bridge that lets AI agents control Rhino 3D and Grasshopper via the Model Context Protocol. It exposes high‑level geometry, editing, and Grasshopper‑graph commands as plain‑language tools, enabling AI‑driven design loops.

The GitHub Copilot app is a desktop client that lets you run Copilot‑powered AI agents in isolated local or cloud workspaces, manage multiple parallel sessions, and oversee the entire coding workflow—from picking a task to merging a PR—through visual canvases and automation tools.

xiaobei (小贝) is an AI‑powered personal assistant for Chinese self‑media operators. Built on the open‑source **openclaw** framework, it lets users create, format, and publish articles, images, and short videos across platforms (WeChat, Xiaohongshu, Douyin, Twitter, etc.) via a simple WeChat chat. It also offers trend analysis, performance monitoring, 24/7 AI customer service, market‑research search, and business‑document generation. Installation is a one‑line script that downloads a pre‑built tarball; after scanning a QR code the bot is ready. The system runs on Ubuntu/macOS/Windows, uses Alibaba Bailei large‑model APIs (or alternatives), and includes a custom anti‑detect browser stack (camoufox) for reliable automation. Optional paid “VIP Club” adds premium support and services.

A high-quality voice conversion tool focused on simplicity and performance, providing a flexible platform for voice transformations.

transcribe.cpp is an MIT‑licensed C/C++ library that runs 60+ speech‑to‑text models (Whisper, Parakeet, Granite, Voxtral, etc.) via the GGUF format on Metal, Vulkan, CUDA, HIP/ROCm, or a tinyBLAS‑accelerated CPU path. It provides a CLI, a quantization tool, conversion scripts from NVIDIA NeMo, and official Python, TypeScript, Rust, and Swift bindings. Models are hosted on Hugging Face and are numerically verified with WER tests.

pua is a multi‑platform skill that injects corporate‑style “performance‑improvement‑plan” rhetoric and a 7‑point debugging checklist into AI coding assistants (Claude Code, OpenAI Codex, Cursor, Kiro, etc.). It auto‑triggers when the model shows lazy patterns (retries, blaming the user, passive waiting) or can be invoked manually with `/pua`. The skill forces the model to exhaust solutions, verify results, and act proactively, offering language‑specific packs (Chinese, English, Japanese). Benchmarks on a handful of bugs show higher fix and verification counts, though speed gains are modest. Installation is via the respective tool’s plugin/skill system (e.g., `npx skills add tanweai/pua --skill pua-en` for Claude Code).

skillshare is a Go‑based CLI that centralises AI‑assistant prompt files (skills), agent definitions, rules and connection settings, then syncs them as symlinks or copies to dozens of AI‑CLI tools (Claude, Codex, Cursor, OpenClaw, etc.). It includes a built‑in security auditor, plugin bundling, MCP connection handling, a web dashboard, and works offline on macOS, Linux and Windows.

A community‑maintained library of Claude plugins, Markdown‑based “skills”, and test case files that enable German‑law‑specific AI assistance (drafting, analysis, document checks). Install full plugins or run single‑file prompts; all outputs are drafts and must be reviewed by a qualified lawyer.

ChatTTS is a generative text-to-speech model optimized for conversational dialogue, providing natural, expressive speech with control over laughter and pauses.

TrustGraph is an open‑source platform that converts enterprise data into an RDF/OWL‑based hypergraph, letting LLM agents query structured, provenance‑rich context instead of relying on fuzzy vector similarity. It offers data ingestion pipelines, configurable “hyperflows” for multi‑step agent work, fine‑grained workspace/collection isolation, an open LLM inference stack, and flexible deployment (Docker, Kubernetes, or SaaS). The project includes a web UI, TypeScript client libraries, and is Apache‑2.0 licensed.

SkillAlchemy is an open‑source framework that automatically builds reusable, installable agent skills from vague task briefs by mining public documentation, papers, and code. It discovers hidden requirements, extracts evidence‑backed procedures, judges their scope, and packages them for LLM agents like Claude Code or Codex. Evaluated on 87 benchmark tasks, it reaches a 55.8 % pass rate, outperforming existing automated skill creators and rivaling human‑curated skills. Install via `npx skills add agentsope/SkillAlchemy` and invoke the agent to generate a skill.

Open‑source, model‑agnostic AI research assistant that manages the full paper‑writing pipeline (survey → code → analysis → draft → slides) via a web UI, CLI, or desktop app. Uses Claude Code, Gemini, Codex or any OpenRouter model; includes 100+ built‑in “research skills”, a news feed, Git integration, and a one‑click auto‑research mode.

LLM Wiki Agent is a local, agent‑driven system that ingests PDFs, DOCX, markdown, etc., extracts entities and concepts, builds an ever‑growing inter‑linked markdown wiki, flags contradictions, and generates a visual knowledge graph—all without a server or database.

TestHub is an open‑source, AI‑enhanced test‑management system built with Django (backend) and Vue 3 (frontend). It covers requirement analysis, test‑case authoring, API/Web/Android automation, performance testing, and reporting, while offering LLM‑driven test generation and a chatbot assistant.

Serenity.skill is an AI‑agent plug‑in that encodes a structured “Serenity” research method for turning market hot‑topics into a short, evidence‑backed list of stocks or funds. Install by copying the folder into a Codex or Claude Code skill directory, then call it with natural‑language prompts (e.g., `$serenity‑skill 研究现在 A 股 AI 半导体产业链`). The skill generates a step‑by‑step analysis—splitting a theme into supply‑chain layers, identifying bottlenecks, pulling public filings, and ranking candidates—while explicitly stating evidence gaps and risks. It does not trade or provide live data; it merely assists the user’s research workflow. MIT licensed.

peon‑ping adds game‑style voice lines and on‑screen banners to AI coding assistants (Claude Code, Copilot, Cursor, etc.). It works on macOS, Linux, Windows, and WSL2, letting the agent announce events like task completion, errors, or permission prompts. The tool manages sound‑pack installation, volume, category toggles, visual overlay themes, remote‑dev audio relay, and optional mobile push notifications, all configurable via an interactive CLI wizard or slash commands.

ToolUniverse is a Python SDK + CLI that standardizes how large language models call scientific tools (ML models, datasets, bio‑informatics packages, etc.) via the AI‑Tool Interaction Protocol and Model Context Protocol. It ships >1 000 ready‑to‑use tools, async execution, caching, and pre‑built agent skills for drug discovery, oncology, and more, enabling rapid construction of “AI scientist” agents.

Veridrop is an open‑source Python tool that checks whether AI‑API relay/proxy services for Claude, OpenAI or Gemini are genuine, retain advertised capabilities (PDF, tool use, long context, etc.), and follow the official response specifications. It runs a suite of protocol‑specific probes, compares results against official baselines (including a cryptographic signature check for Claude), and produces a weighted score and detailed report. Available as a free web UI (veridrop.app) and as a self‑hosted CLI/FastAPI service, it is licensed under AGPL‑3.0.

GPT4Free (g4f) is an open‑source Python library (with Docker, web GUI, FastAPI API and a browser JS client) that aggregates many free or community‑run LLM and media providers behind a unified, OpenAI‑compatible interface. It lets you call chat completions, image generation, and other tools via a single client, choose providers automatically or explicitly, run locally or in containers, and even expose a JSON‑RPC “MCP” server for assistants. Licensed under GPL‑v3, it’s maintained by @xtekky and @hlohaus and aims to make powerful AI tooling accessible without vendor lock‑in.

ai‑jail is a Rust‑based tool that runs AI coding agents (like Claude) inside a Linux bubblewrap/Landlock or macOS sandbox, offering fine‑grained flags for network, GPU, filesystem, and environment access. Install via Homebrew, AUR, Cargo, Nix, or binary releases. Default settings isolate the agent with a private tmpfs home; you opt‑in to any host resources. Configuration is layered (project → user → CLI) using TOML files. GPL‑3.0‑only.

A genuine open‑source library of 103 Claude Skills covering brand, design, content, SEO, product management, growth and ops. Skills are reusable prompt‑plus‑metadata bundles that Claude can load on‑demand, enabling end‑to‑end AI‑driven workflows for building, launching and optimizing websites.

A real-time audio translation tool for Windows that captures system audio and microphone input to provide live translated subtitles via an LLM-powered overlay.

A Windows task‑bar widget that locally tracks how much of your daily/monthly quota you’ve used on AI code‑generation services (Claude Code, Codex, Google Antigravity, OpenCode Go, Cursor) and shows when the limits reset. Install via WinGet or a direct download, configure providers in a simple dashboard, and enjoy privacy‑first monitoring without any telemetry.

OntoBricks is a Databricks‑native app that converts Unity Catalog tables into a standards‑based knowledge graph. It uses LLMs to auto‑generate an OWL ontology and R2RML mappings, materialises triples inside the Lakehouse (or an external graph DB), and exposes the graph via GraphQL and the Model Context Protocol for LLM agents. The tool includes visual ontology design, automated validation, reasoning, and full governance of domain versions.