cagataycali/devduck
Minimalist AI agent that fixes itself when things break.
Implements hot-reloading and runtime self-modification through a single-file architecture with pluggable tools that can be added, fetched, or edited without restart. Supports 60+ built-in tools (shell, GitHub, browser control, ML inference) across multiple protocols—CLI, TUI, WebSocket, TCP, MCP, and P2P Zenoh—with unified mesh networking that connects terminal, browser, and cloud agents. Works with any LLM provider (AWS Bedrock, Anthropic, OpenAI, Ollama, etc.) via automatic model detection and includes knowledge base integration for persistent RAG across sessions.
34 stars and 1,935 monthly downloads. Available on PyPI.
Stars
34
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 06, 2026
Monthly downloads
1,935
Commits (30d)
0
Dependencies
17
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/cagataycali/devduck"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related servers
activepieces/activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation /...
flytohub/flyto-core
The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue,...
evalstate/fast-agent
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support
Klavis-AI/klavis
Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale
Azure-Samples/AI-Gateway
Labs to explore AI Models, MCP servers, and Agents with the AI Gateway powered by Azure API...