personal AI / local-first agent orchestration with memory and deep research
OpenHuman is a local-first personal AI superintelligence that combines persistent memory, multi-agent orchestration, and deep research.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
When you need an MIT-licensed Python agent harness with sandboxing, memory, and research, equivalent to seed's orchestration.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
When you want a Python/MIT second-brain agent with local file intelligence and workflow automation instead of Rust/GPL.
Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
When you want to build your own personal AI on a local database/AI gateway infrastructure rather than use a full assistant.
Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
When you need a lightweight, MIT-licensed TypeScript deep research tool without the full personal AI layer.
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.
When you want a fully local Python research report writer and don't need memory/orchestration.
Fully local web research and report writing assistant
When you need a model-agnostic deep research service exposed via SSE or MCP.
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
When you want a research agent built on the OpenAI Agents SDK rather than seed's own stack.
An implementation of iterative deep research using the OpenAI Agents SDK
When you need citation-backed reports with credibility scoring from a LangGraph/LangChain system.
Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search
When you want a local-first research platform with verifiable multi-step workflows and cloud/self-hosted LLM switching.
Cerno is a local-first research platform that leverages agentic AI to break down complex queries into verifiable, multi-step workflows. Switch seamlessly between cloud LLMs and self-hosted models, track every reasoning step, and optimize cost and tokens—all while keeping your data on your machine.
When you want a research framework implementing progressive search and cross-evaluation.
A deep research framework based on progressive search and cross-evaluation.
When you need a mature deep research agent that works with any LLM provider and web search.
An autonomous agent that conducts deep research on any data using any LLM providers
When you want a leading Apache-2.0 deep research agent from Alibaba with strong model support.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
When you want an archived LangChain reference implementation for deep research.
When you need a research agent optimized for high-accuracy browse-and-complete tasks.
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.
When your deep research must reason over private/corporate data using vector search.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
When you want a simpler, transparent implementation of OpenAI-style deep research for learning or light use.
Deeper Seeker is an simpler OSS version of OpenAI's latest Deep Research feature in ChatGPT.It is an agentic research tool to reason , create multi step tasks , synthesize data from multiple online resources and create neat reports
When you need an autonomous scientific research agent focused on innovation and production use.
[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat
When you need to orchestrate coding-agent fleets and automate CI fixes, not personal assistance.
Agent IDE that enables you to manage fleets of coding agents. It comes with an agentic orchestrator that plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.
When you just need a local GPU-accelerated memory system for Claude Code, without a full agent stack.
Give your AI agent a brain that remembers. Local memory system for Claude Code — 100% private, GPU-accelerated, zero cloud dependency.
When you need persistent, private memory for existing AI tools (Cursor, Claude Code, etc.) rather than a complete assistant.
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
When you want an LLM-maintained knowledge base inside Obsidian for memory, accepting the single-tool scope.
LLM-maintained personal knowledge base for Obsidian. Based on Andrej Karpathy's LLM Wiki pattern.
These projects were analysed and named openhuman among their alternatives. The relationship is not symmetric — how openhuman rates them is a separate judgement, made when openhuman is analysed in its own right.
calls openhuman “personal AI platform with memory and agent orchestration including deep research; choose for integrated personal AI.”
An autonomous agent that conducts deep research on any data using any LLM providers
calls openhuman “broader personal AI with memory and agent orchestration; choose it if you want deep research alongside life-logging and multi-agent workflows.”
Tongyi Deep Research, the Leading Open-source Deep Research Agent
calls openhuman “personal AI superintelligence app with deep-research capability, not a swap-in library”
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.