A CLI for the open agent skills ecosystem that allows users to install and manage reusable instruction sets to extend the capabilities of AI coding agents.

AI Job Search is an open‑source, Claude‑Code‑driven CLI framework that automates the full job‑search funnel: it scrapes Danish (and some international) job boards, ranks postings against a structured fit rubric, drafts LaTeX CVs and cover letters, runs a reviewer LLM, verifies PDFs, checks ATS readability, tracks outcomes, and can sync to Notion or Gmail. Prerequisites include Claude Code, Python 3.10+, Bun, and a full LaTeX distribution. The repo provides detailed command definitions, portal‑scraper agents, and utilities for interview prep, skill‑gap analysis, and reporting.

An open-source AI job search system that runs in AI coding CLIs to evaluate job offers, tailor CVs, and track applications through an agentic pipeline.

A library of agent skills for CAD, CAE, and CAM that enables AI agents to generate 3D models, robot description files, and fabrication-ready G-code from plain-language requests.

Free Claude Code (FCC) is an open‑source gateway that lets you run many AI coding assistants (Claude Code, Codex, Pi, etc.) through a single locally‑hosted server. It aggregates 50+ free‑tier or low‑cost LLM providers, offers automatic fallback, token‑saving optimisations, browser‑based code sessions, voice‑to‑code, and integrates with VS Code, JetBrains, Discord, Telegram and local model servers (LM Studio, Ollama, llama.cpp). Install via a one‑line script, configure providers in the Admin UI, then launch agents with `fcc‑claude`, `fcc‑codex`, etc.

A cross-platform manager for AI coding agents and CLI tools that provides a unified interface to configure and configure and switch between tools like Claude Code, Codex, and Gemini CLI.

A collection of implementation examples and specifications for Claude Skills, allowing users to dynamically load instructions and resources to perform specialized, repeatable tasks.

An independent auditing framework for AI agents that evaluates operational assurance and business KPI alignment through a graded scorecard system.

A local API traffic capture tool for AI coding agents that attributes token costs to specific request components like system prompts and tool schemas.

A Lean 4 formalization of mathematical proofs demonstrating finite-time blowup for the Navier-Stokes and Euler equations, addressing the Millennium Prize Problem.

A collection of 11 AI skills for Claude Code and Codex that automate LinkedIn content creation, engagement, and humanization of AI-generated text.

A software factory framework that turns AI coding agents into a virtual engineering team with specialized roles for product planning, architectural review, QA, and security audits.

AI‑Agent‑Book is a multilingual open‑source textbook on building LLM‑based AI agents, paired with 109 runnable Python experiments covering everything from prompt engineering to multi‑agent collaboration.

MCP for Blender is an open‑source bridge that lets LLMs (Claude, Codex, Cursor, etc.) control Blender via a socket‑based server (the MCP server) and a Blender add‑on. Install `uv`, configure the LLM client with a short JSON snippet, install the add‑on, and then you can ask the AI to create, edit, or inspect 3‑D scenes, run Python code, and pull assets from Poly Haven, Sketchfab, Poly Pizza, or AI‑generated model services. Safe‑mode can sandbox Python execution, and the server can run locally, via Docker, or with `pipx`. The project is packaged on PyPI and supported through a Discord community.

Atlas is a macOS‑first desktop app that adds source‑control‑style checkpoints to LLM coding agents. It records every agent session (prompts, tool calls, reasoning) in a local SQLite store, links those sessions to Git commits, and shares a semantic memory index across agents. Users can run Claude Code, Codex, Atlas’s native agent, or any ACP‑compatible agent side‑by‑side, with `@`‑mentions for files, notes, papers, etc. All data stays on the device by default; syncing and analytics are optional. The app includes a CodeMirror editor, terminal, knowledge‑base markdown notes, web view, and a dashboard, and is built with Tauri (Rust + web UI) and Bun.

OpenViking is an open‑source context database that presents an LLM agent’s memories, resources and skills as a virtual filesystem (`viking://`). Each entry is pre‑processed into three layers (abstract, overview, full detail) so the agent only loads what it needs, dramatically reducing token usage and latency while keeping retrieval paths observable. It ships with a Python server, a CLI (`ov`), a web Studio demo, and ready‑made integrations for many popular agents (Claude Code, Codex, LangChain, etc.). Install via `pip install openviking`, run `openviking-server init` to configure providers, then start the service and use `ov` commands to add resources, browse, and search. Benchmarks show 30‑90 % token savings and accuracy jumps to ~80 % on memory‑heavy tasks. The core is AGPL‑v3; a managed SaaS version is also offered by Volcano Engine.

A modular, node-based AI engine for visual professionals to create complex workflows for generating images, video, audio, and 3D models with precise parameter control.

A tool that converts local WeChat chat histories into a searchable personal intelligence hub for tracking business opportunities, commitments, and daily summaries.

An agent distribution that allows a user to manage a crew of autonomous coding agents through a single supervisor agent, enabling parallel task execution with isolated worktrees.

Graphify is a Python CLI that builds a local, LLM‑free knowledge graph of a codebase (and optional docs/media) using Tree‑sitter. The graph can be visualised, queried, and integrated with many AI coding assistants (Claude, Copilot, Cursor, Gemini, etc.) to answer questions, trace connections, or explain symbols without grepping files.

Dify is an open-source LLM app development platform that combines AI workflows, RAG pipelines, and agent capabilities into a unified visual interface for rapid prototyping and production.

A high-capability coding agent with deep IDE, debugger, and OS integration that allows LLMs to perform complex software engineering tasks with high precision.

A Chrome extension that converts selected web content into editable office files like spreadsheets, slide decks, and HTML sites using user-provided AI models.

An open-source SEO tool that integrates with AI agents via MCP, providing a pay-as-you-go alternative to traditional SEO suites for keyword research and site audits.

Agent Orchestrator is a cross‑platform desktop app that lets you run multiple LLM‑based coding agents as isolated Git‑backed workers, coordinate them via a project‑level orchestrator, and monitor everything on a live Kanban board.

An AI-powered code review CLI tool that combines deterministic engineering with an agentic workflow to provide high-precision, line-level feedback on Git diffs and full files.

FrontierAgent is an open‑source, terminal‑based runtime that lets you run autonomous ReAct agents or parallel Agent‑Team workflows. It provides a sandboxed filesystem, live TUI task board, asynchronous user interventions, and a built‑in benchmark harness for research‑grade long‑horizon tasks. Install with `uv`, point it at any OpenAI‑compatible model endpoint (including the free Apodex‑1.1 service), and run either `--mode react` for a single agent or `--mode agent_team` for coordinated parallel agents. The project is Apache‑2.0 licensed.

A multi-agent tool that turns codebases and knowledge bases into interactive knowledge graphs, helping developers visualize architecture and business logic.

A high-performance CLI proxy that compresses bash output for AI agents, reducing input tokens by up to 90% through smart filtering and grouping.

An open-source web scraping API that converts websites into LLM-ready markdown or structured JSON, featuring an anti-detect browser and ML-powered proxy selection.

A multi-agent orchestration configuration for Codex that uses GPT-6 Astra as the root manager and reviewer, and GPT-5.6 Luna for execution subagents.

Failproof AI is a Node.js/TypeScript library that hooks into 12 popular LLM‑coding and chat agents, records every model and tool call, and applies 39 built‑in safety policies (e.g., block API‑key leaks, sudo, rm‑rf, destructive SQL). Users can add custom policies in JavaScript, view full execution traces on a local dashboard (localhost:8020), run offline audits, and optionally use a hosted/self‑hosted service for fleet‑wide observability and alerts.

An AI-driven pipeline that converts topics or documents into narrated motion-graphics explainer videos by using AI agents to write Remotion code.

A service and agent skill for stripping AI provenance marks and watermarks from text and files across multiple vendors and formats.

DeerFlow is an open-source super agent harness that orchestrates sub-agents, memory, and sandboxes to perform deep research and complex task execution.

Paseo is a self‑hosted platform that lets you run and manage multiple AI coding agents (Claude Code, Codex, Copilot, OpenCode, Pi) from a single interface—desktop, mobile, web, or CLI—while keeping everything on your own hardware.

A self-learning browser infrastructure for AI agents that remembers website navigation to reduce token costs and increase automation reliability.

A long-term memory runtime for AI agents that uses Markdown files as the source of truth and a local index for ranked retrieval, enabling persistence across sessions.

GenOffice is an open‑source, cross‑platform desktop Office suite (Docs, Sheets, Slides, PDF, HTML, Markdown) that edits real `.docx`, `.xlsx`, `.pptx` and other formats. It embeds an AI agent that can modify documents directly—producing tracked changes, live formulas, new slides, etc.—and all edits are reversible. The suite works locally; only AI calls go over the network, and you can plug in any major LLM provider or your own endpoint. Installers are provided for macOS, Windows and Linux.

A proxy server that provides unified OpenAI, Gemini, and Claude compatible API interfaces for various AI providers, allowing CLI tools to access models using existing subscriptions via OAuth.

HiThink‑Tech / Financial‑API is a commercial A‑share market‑data platform (REST, MCP, CLI, Python SDK) that supplies real‑time quotes, historical K‑lines, financial statements, valuation ratios, fund/futures data and bulk market dumps. It is designed for AI agents, quantitative researchers and developers, with a unified Skill that lets LLM‑powered tools automatically choose the best access method. The service uses a single API key, stores large results locally (DuckDB), and is MIT‑licensed.

A cybersecurity skills router that provides AI agents with structured methodologies and tool routing for reverse engineering, penetration testing, and CTF challenges.

A personal memory infrastructure that allows different AI agents to share a structured memory of user preferences and project history, ensuring task continuity across tools.

An open SDK for integrating audio recording, speech recognition, and speech synthesis into AI hardware like recording cards and smart mice.

A self-hosted platform for running AI agent harnesses locally via Docker, providing secure isolation and support for multiple model providers without cloud accounts.

A multi-agent prediction engine that creates high-fidelity digital sandboxes to simulate and predict the outcomes of real-world events or fictional scenarios.

A set of agent skills that enable AI agents to research top-grossing mobile apps and build high-fidelity, simulator-verified Expo and React Native screens.

A Python CLI and agent skill that transforms a single base image into game-ready transparent sprite atlases or animation loops using AI generation pipelines.