The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
- agent
- vlm
- vision
- computer-use
Repository Index
47,133 repositories indexed
1–18 of 18 · Most stars
Build and run agents you can see, understand and trust.
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
- semantic-search
- information-retrieval
- ai
- python
Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
- ai
- real-time
- voice
- voice-assistant
Open-source framework for conversational voice AI agents
A framework to enable a multimodal model to operate a computer.
- automation
- openai
- pyautogui
FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models
Reverse engineering and pentesting for Android applications
- android
- dalvik
- reverse-engineering
- dex
The Ruby AI framework.
Stop paying the multimodal tax. Your AI agent keeps every image it has seen but only sends the ones it needs: lighter chats, no endless reconnecting, no starting over. Works with Codex, Claude Code, Cline, Gemini CLI, OpenCode, WorkBuddy and more. Install once, forget it.
- codex
- codex-plugin
- context-management
- developer-tools
Scene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.
- asr
- contact-sheet
- deepseek-harness
- dsh-plugin
Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory
- agent-harness
- agentic-ai
- ai-agents
- coding-agent
AI-editable 2D modeling and playback via MCP. Parts-separated PSD input, standalone local service, and embeddable runtime.
Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.
- ai-detection
- ai-plugin
- anti-slop
- claude-code
A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.
- ai
- golang
- llm
- structured-output
⚽ Live football(soccer) scores, fixtures and standings for the competition you follow (World Cup, Premier League, LALIGA, Champions League and 12 more) in your terminal, your Claude Code and Cursor CLI statusline, and MCP clients. No API key. Independent fan project. Not affiliated with FIFA, any confederation, league or club, or Anthropic.
- claude-code
- cli
- football
- futbol
MCP server + CLI for production-grade software assets (logos, app icons, favicons, OG, illustrations) — routes across 30+ image models, zero-key first, validates before shipping.
- app-icon
- claude-code
- cli
- cursor
Financial Market Intelligence MCP Server — stock quotes, technical analysis, crypto data, and portfolio insights for AI agents