local autonomous agentic AI assistants
AgenticSeek is a fully local, voice-enabled autonomous AI agent that browses the web, writes and runs code, and plans complex tasks using local models, positioned as a private no-API alternative to Manus AI.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
a terminal-native persistent agent, choose if you prefer a lightweight CLI over a voice-enabled local app
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
a desktop multi-agent team client, choose for commander-style orchestration rather than local-first voice
Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.
a local-first agent hub/orchestrator, choose if you want per-task orchestrators with any model
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
a multi-model agent harness, choose for messaging channels and lightweight extensibility rather than local Manus-style app
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)
an enterprise agent/KB platform, choose for deploying branded assistants rather than a personal local agent
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
an all-in-one AI server with agents, voice, RAG, choose if you want a broad self-hosted platform instead of a dedicated agent app
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
a general autonomous task-solving agent, choose when API models are acceptable and local-only/voice is not required
An Autonomous LLM Agent for Complex Task Solving
a self-hosted private AI platform with document analysis and agent builder, choose for enterprise knowledge assistants
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
specialized in autonomous software development, choose for coding-focused automation rather than general tasks
Develop software autonomously.
agentic data assistant, choose for database/data workflows instead of general web/coding agent
open-source agentic AI data assistant for the next generation of AI + Data products.
focused on deep research over private data, choose for research-only workloads
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
an autonomous financial research agent, choose for finance-focused deep research rather than general assistance
An autonomous agent for deep financial research
These projects were analysed and named agenticSeek among their alternatives. The relationship is not symmetric — how agenticSeek rates them is a separate judgement, made when agenticSeek is analysed in its own right.
calls agenticSeek “Fully local Manus-like autonomous agent that browses and codes; choose if you want a broader agent.”
Fully local web research and report writing assistant
calls agenticSeek “Use when you want a fully local autonomous agent that browses and codes without API costs.”
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
calls agenticSeek “when you want a fully local, GUI-based autonomous agent with no API costs.”
An Autonomous LLM Agent for Complex Task Solving
calls agenticSeek “Use if you want a local general-purpose autonomous agent app that can browse the web and code.”
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.