AI · GitHub repo
AgenticSeek
Open-source, fully local autonomous AI agent that browses and writes code
AgenticSeek is an open-source autonomous agent designed as a private, local alternative to services like Manus AI. It runs on personal hardware using local LLM providers such as Ollama or LM Studio, autonomously planning tasks, scraping the web, and executing code. Because data does not leave your machine, it avoids recurring cloud subscription fees and keeps browsing and files private.
What it's for
- Execute multi-step web research queries hands-free using local SearXNG instances
- Generate, debug, and run code in languages like Python or Go on local files
- Organize and batch rename local files across local folders without cloud exposure
- Control autonomous task execution using voice trigger commands in CLI mode
Features
- Fully local execution with zero cloud dependencies
- Autonomous web browsing using headless browsers and SearXNG integration
- Support for local reasoning LLMs via Ollama, LM Studio, or OpenAI-compatible APIs
- Multi-agent task decomposition and automatic agent routing
- Local file reading, writing, and code execution
- Experimental hands-free speech-to-text and voice command support in CLI mode
- Docker-based deployment for quick setup of frontend, backend, and search services
Pricing
Open source. Free and open source (GPL-3.0); runs locally on your own hardware.
Details
- Type
- GitHub repo
- Category
- AI
- Topic
- Autonomous Agents
- Open source
- Yes
- Platforms
- Linux, macOS, Windows, Command line, Self-hosted
- For
- Developers and privacy-focused users wanting an autonomous personal AI agent without cloud subscription fees.
- Alternative to
- Manus AI, Devin, AutoGPT
- Tags
- ai agents, autonomous agents, local ai, deepseek, ollama, task automation
Why it was saved
- @simplifyinAI: Removes the need for APIs, cloud services, or the ~$200/month Manus subscription; all data stays on your device.
Compare
Related
Open-source, self-hosted AI agent with persistent memory and messaging integrations.
Open-source platform and framework for building autonomous AI agents
A Python multi-agent pattern pairing Opus orchestration with Haiku worker instances.
Open-source long-horizon agent harness with Docker sandboxes, memory, and sub-agents
All-in-one AI workspace with autonomous agent tools for content, research, and analysis.
Open vision-to-action foundation model for generalist autonomous game playing
Updated