OpenCode is an open-source AI coding agent designed to help developers plan, implement, and refactor code from a terminal-first workflow, with options to use it as a desktop app or IDE extension. It can connect to multiple model providers (or use included free models), apply changes across a codebase, and support common developer flows like asking questions, adding features, making edits, and undoing changes. OpenCode also integrates with GitHub workflows: you can mention a command in issues or pull requests to have it execute tasks inside a GitHub Actions runner.

OpenCode

opencode

Open-source AI coding agent for terminal, desktop, and IDEs—plans changes, edits code, and can run tasks in GitHub via comments.

Agent S is an open-source framework for building and running “computer use” GUI agents that can autonomously operate a computer through an Agent-Computer Interface. It’s designed to let an LLM plan and execute multi-step tasks by observing the screen and taking actions (e.g., clicking, typing, navigating) on supported platforms (Linux, macOS, Windows). The project provides a CLI to run the agent, supports multiple model providers (including OpenAI, Anthropic, Gemini, OpenRouter, and vLLM), and recommends pairing a main LLM with a separate grounding model for UI understanding. Agent S also includes evaluation assets and reports results on established computer-use benchmarks such as OSWorld.

Agent S

agent-s

Open-source GUI agent framework that lets an LLM use your computer like a human via an Agent-Computer Interface.

PubNub MCP Server is a CLI-based Model Context Protocol (MCP) server that connects MCP-compatible AI assistants (like Cursor, VS Code, Claude Code, Codex, and others) to PubNub’s SDK documentation and PubNub account/API resources. It helps agents retrieve SDK and Chat SDK documentation across many languages, manage PubNub apps and keysets (including enabling features like persistence, files, presence, and app context), and perform real-time operations such as publish/subscribe, signals, presence, and user/channel objects. The server supports dynamic mode (keys provided per tool call) and fixed mode (publish/subscribe keys set via environment variables) and can be installed via npm or run via Docker, with authentication typically provided using a PubNub API key.

PubNub MCP Server

pubnub-mcp-server

MCP server that lets AI coding assistants access PubNub docs and manage apps/keysets, plus messaging, presence, and channel/user objects.

Desktop Commander MCP is an open-source Model Context Protocol (MCP) server that gives AI clients controlled access to your local development environment. It enables running terminal commands with streaming output and interactive process/session management, plus full filesystem operations like reading/writing files, creating directories, and recursive search. It includes diff-based “surgical” edits and pattern-based replacements, powered by ripgrep for fast repo-wide search. The tool also adds native Excel support (read/write/edit/search) and PDF tooling (extract text, create PDFs from markdown, and modify PDFs), along with comprehensive audit logging of tool calls for traceability.

Desktop Commander MCP

desktop-commander-mcp

MCP server that lets AI run terminal commands, manage processes, and search/edit files (diff-based) with Excel/PDF support and audit logs.

FLAMEHAVEN FileSearch is an open-source, self-hosted RAG document search engine you can run locally (Docker or Python). It supports multi-format ingestion (PDF, DOCX, TXT, MD) and provides keyword, semantic, and hybrid search modes (with typo correction). Results include source attribution, and the API includes production features like API-key authentication with permissions, rate limiting, audit logging, batch search, and an admin dashboard. It integrates with Google Gemini (via GEMINI_API_KEY) and supports a lightweight local store plus optional components such as Redis caching and Postgres/pgvector for higher-performance deployments.

FLAMEHAVEN FileSearch

flamehaven-filesearch

Self-hosted RAG file search engine (FastAPI) with keyword/semantic/hybrid modes, citations, API keys, and Docker quickstart.

AniFun AI is a web-based anime creation platform that helps users generate anime-style images, manga pages, and short anime-style videos using AI. It offers tools like text-to-anime image generation, photo-to-anime conversion, anime-to-real transformations, manga page generation with layouts, and image-to-video workflows. The product emphasizes fast creation with no complicated setup, plus a broad suite of creator-focused utilities (filters, sketch tools, upscalers, extenders, and more) to move from an idea to shareable anime content quickly.

AniFun AI

anifun-ai

Free anime creation platform for generating anime art, manga pages, and anime-style videos from text or images—no setup required.

Playwright MCP is an open-source Model Context Protocol (MCP) server from Microsoft that exposes Playwright-powered browser automation as callable tools for AI agents. Instead of relying on screenshots or visually-tuned models, it provides structured page state (including accessibility snapshots) so an LLM can reliably understand and interact with live web pages—clicking, typing, waiting for selectors, navigating, and validating outcomes. It’s useful for AI-assisted web testing, agent-driven site exploration, and automations that need a real browser environment with deterministic, tool-based control.

Playwright MCP

playwright-mcp

An open-source MCP server that lets LLMs automate real browsers with Playwright using structured accessibility snapshots (no screenshots needed).

StockAgent is an open-source, LLM-driven multi-agent framework for simulating stock trading behavior in a market environment that aims to resemble real-world conditions. The system models investor-like agents reacting to information such as macroeconomics, policy changes, company fundamentals, and global events, enabling analysis of trading behaviors and profitability effects under different external-factor scenarios. The authors also position StockAgent as addressing test-set leakage concerns in agent-based trading simulations by reducing reliance on prior memorized knowledge of the evaluation data. It’s primarily a research and experimentation framework (not a live-broker trading bot) for evaluating LLMs and studying emergent trading patterns in controlled simulations.

StockAgent

stockagent

Multi-agent LLM system that simulates investor trading behavior in a realistic stock-market environment to study how external factors affect decisions and outcomes.

HIA (Health Insights Agent) is an open-source Streamlit app that lets users upload blood report PDFs and receive AI-generated, personalized health insights. It uses an agent-based architecture with a multi-model cascade via Groq for reliability, performs PDF validation and text extraction (up to 20MB), and supports secure user authentication plus session history for tracking past analyses. The project is built around a practical “report → extraction → analysis → insights” workflow and is designed to be deployable with Supabase (DB + Auth) and simple Streamlit configuration.

HIA (Health Insights Agent)

hia-health-insights-agent

Open-source AI agent that analyzes blood-report PDFs and returns personalized health insights, with authentication and analysis history.

Together Open Data Scientist is an open-source AI data analysis agent built around the ReAct (Reasoning + Acting) pattern. It automates common end-to-end data science workflows: loading and exploring datasets, running EDA, engineering features, training baseline models, creating plots, and writing a structured report. The agent can execute Python code either locally (via Docker/internal execution) or in the cloud using Together Code Interpreter (TCI), and it supports uploading a data directory for analysis. It’s positioned as experimental software—outputs should be reviewed and validated—making it most useful for exploration, learning, and fast first-pass analysis rather than unattended production analytics.

Together Open Data Scientist

together-open-data-scientist

Open-source data scientist agent that runs Python (locally or in the cloud) to explore datasets, build models, and generate detailed analysis reports using the ReAct framework.

GLM-4.6V is a next-generation multimodal large language model series from Z.ai (Zhipu AI), designed for high-fidelity visual understanding and long-context reasoning across images, video, documents, and text. It comes in two main variants: the 106B-parameter GLM-4.6V foundation model for cloud and cluster deployment, and the lightweight GLM-4.6V-Flash (9B) optimized for local and low-latency applications. With a 128k token context window, GLM-4.6V can read large PDFs, slide decks, and multi-page mixed-media documents in a single pass. Native multimodal function calling lets it use tools directly from visual inputs, closing the loop from perception to executable actions and enabling powerful agent-style workflows. Typical use cases include visual document QA, chart and layout understanding, multimodal search and analysis, converting UI screenshots into production-ready code, and generating image-rich content. The models are released with open weights under a permissive open-source license, making them suitable for research, self-hosted deployments, and integration into production systems.

GLM-4.6V

glm-4-6v

Open-source multimodal GLM from Z.ai unifying vision, text, and tool calling for long-context reasoning, search, coding, and UI-to-code.

x402 is an open, internet-native payment protocol that activates the long-reserved HTTP 402 “Payment Required” status code to handle payments directly inside web and API requests. It allows AI agents, apps, and APIs to charge and pay per request using stablecoins like USDC, removing the need for traditional API keys, subscriptions, or manual billing. Built as an open standard by Coinbase and deployed on chains such as Solana and Base, x402 supports low-cost, high-throughput micropayments suitable for agentic workflows, data APIs, model inference, and digital content. By embedding pricing, payment instructions, and proof of payment in normal HTTP flows, x402 enables fully autonomous, machine-to-machine commerce and a more granular, usage-based business model for online services.

x402 Protocol

x402-protocol

Open payment protocol that lets AI agents and APIs send instant stablecoin micropayments over HTTP using the 402 status code.

Explore AI Agents with free pricing