A suite of free, ad-supported AI coding and research tools providing access to multiple LLMs and specialized agents via CLI, desktop, and cloud.

A repository of reusable instruction and script packages that AI agents can use to perform specific tasks in a repeatable way.

An open-source RAG engine that combines deep document understanding with agent capabilities to create a high-precision context layer for LLMs.

An open-source project management and issue tracking system that integrates AI agents as first-class team members to collaborate on tasks.

An AI agent framework designed to automate mathematical modeling competitions, from problem analysis and coding to generating submission-ready PDF papers.

LibreTranslate is a self-hosted, open-source machine translation API that removes dependency on proprietary services like Google or Azure.

A vetted community marketplace for plugins that extend the capabilities of Claude Cowork and Claude Code.

A configuration layer for the Pi coding agent that bundles system prompts, tools, and settings into shareable "Genomes," including an engine to automatically generate them from usage history.

A collection of AI agent skills for transforming novels into short dramas, automating the pipeline from outline and character design to script and storyboard.

An AI-powered stock analysis system that automatically aggregates global market data to generate and push daily decision dashboards to messaging platforms.

A tool for distilling the cognitive frameworks and mental models of public figures into runnable AI skills for agent runtimes.

A collection of agent skills that enable AI agents to Claude Code, Codex, and Open Code to create and edit content within Obsidian vaults using specialized syntax and formats.

A deep research harness for Claude Code that uses a 16-step adversarial pipeline and a persistent source vault to produce verified, high-capacity research reports.

A runtime ablation tool that uncensors the Ternary Bonsai 2 27B model by projecting out refusal directions during inference without modifying the original quantized weights.

An open-source platform for running persistent AI teammates with their own memory, routines, and access to isolated computing environments.

An open-source Python framework for orchestrating multi-agent AI systems, combining autonomous collaborative crews with precise, event-driven workflows.

NeoHorse-1 is a family of agent-native causal language models designed as a prototype for recursive self-improvement through a routing harness and agentic post-training.

An AI-powered trading agent framework that integrates market data, quantitative analysis tools, and multi-broker execution for automated trading strategies.

A desktop workbench for AI coding that provides a visual interface for managing multi-agent teams, dynamic workflows, and model integrations.

A coding-agent skill that enables the creation of stunning, single-file HTML presentations from scratch or by converting PowerPoint files, using a visual style discovery process.

A collection of structured AI skills and theoretical guides that distill senior academic mentorship into executable LLM prompts to assist researchers with idea generation, paper writing, and peer review.

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

An open-source software factory that automates routine engineering work by coordinating AI agents to turn backlog issues into reviewed pull requests.

A comprehensive, automatically updating library of AI Agent skills aggregating official and community-curated prompt sets for diverse professional domains.

A self-hosted agent platform that lets companies deploy AI coworkers on their own infrastructure with strict governance, isolated browser environments, and full audit trails.

A framework for local-first personal AI agents that run on personal devices by default, reducing reliance on cloud APIs while optimizing for energy and latency.

An open-source AI-powered social media scheduling tool that allows users to manage, automate, and analyze posts across multiple platforms.

A Gradio-based web interface for the browser-use library that enables users to interact with AI browser agents using a variety of LLMs.

An agent organization for Claude Code that structures 172 specialized AI skills into 16 installable departments, allowing users to add professional expertise to their project instead of writing prompts.

A Zotero plugin that translates PDFs while preserving formulas and layout, supporting bilingual对照 and various LLM backends.

A tool that converts local WeChat chat histories into a searchable personal intelligence hub to track business opportunities, commitments, and key discussion themes.

A minimal AI software engineering agent that uses only bash commands to solve coding tasks, providing a high-performance, hackable alternative to complex agent frameworks.

GLiNER2 is a Python library that provides a single, locally‑run model for many information‑extraction tasks (NER, classification, JSON‑style record extraction, relation extraction, span attributes). It supports two architectures—span‑grid and boundary—via `AutoExtractor`, runs fast on CPU, offers multilingual and safety‑focused checkpoints, and includes extensive tutorials and community channels.

SkillOpt is a framework that treats agent skill documents as trainable parameters, using an optimizer model to iteratively improve them without changing model weights.

Langflow is a visual platform for building and deploying AI agents and workflows, allowing developers to design, test, and export AI logic as APIs or MCP servers.

A multiplayer agent harness for organizations that provides isolated personal workspaces and shared collaborative environments across Slack and the web.

An open-source, general-purpose AI agent available as a desktop app, CLI, and API that handles coding, research, and automation tasks.

An open-source knowledge base and career guide for AI Agent engineering and research, providing structured learning paths and interview preparation for algorithm and development roles.

A local Google Maps scraper kit that integrates with Claude to allow AI-driven extraction of structured business lead lists.

An open-source AI agent that automates Android and iOS devices using natural language to perform tasks and scrape data from apps.

An ultra-lightweight, self-hosted personal AI agent framework that combines long-term memory, MCP integrations, and scheduled automation across WebUI, terminal, and various chat apps.

A self-hosted, privacy-first fitness tracking platform that consolidates nutrition, exercise, and health data from multiple wearables into one ad-free application.

Apache Maka is a high-performance agent workspace that maintains a complete, append-only record of all agent actions to ensure task execution is measurable and reproducible.

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.

A cross-device open-source workbench that allows you to manage and monitor AI agents like Claude Code and DeepSeek Harness running on your work devices from any mobile or web client.

An open-source, agentic-first CRM where AI agents autonomously research leads, record factual evidence, and manage follow-ups instead of relying on manual human entry.

An all-in-one Agent chatbot platform that integrates LLMs and AI agents into mainstream instant messaging apps like Telegram, Slack, and Discord.

SillyTavern is a locally installed user interface that provides a unified frontend for interacting with various LLM APIs, image generation engines, and TTS models.