Alfred Black is a self-hosted AI agent for solo business owners and consultants who need help with inbox triage, follow-ups, and keeping track of ongoing work. It runs continuously on a Linux server through Docker, with a web dashboard and conversations through Telegram, Slack, email, or web chat.
It groups related messages, documents, people, and tasks into ongoing concerns called Matters. Each Matter has an updated summary, so a contract discussion or client relationship has a current record instead of scattered threads. Incoming meeting transcripts can become linked records and tasks. Background workers flag contradictory notes, repair broken links, and connect related material in an Obsidian-compatible Markdown vault that you can read and edit yourself.
Its autonomy depends on permissions you grant. Alfred records its actions, requests for approval, and decisions to suppress notifications. It can propose broader permission based on patterns in your decisions, but it can't approve that permission itself. You remain responsible for supervision when you self-host.
The vault and databases stay on your server. Model requests go to your chosen external provider, with OpenAI Codex as the default; this isn't a fully offline system. Composio connects services such as Gmail, Notion, and Linear and holds their integration credentials on its servers. The full platform needs at least 16 GB of RAM. A separate managed service at alfred.black handles supervision, quality checks, and repairs for clients.
Claim this page and we'll verify you by hand. Alfred Black gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Alfred Black?Promote it
Something wrong or outdated on this page?
2.5KUpdated 23 hours agoMIT
Windows · Linux · Docker · Web#Agent Skills#Code execution#Guardrails
Bitterbot is a local-first personal AI agent for people who want an assistant that remembers ongoing projects and preferences across conversations. It runs on your own device or server, with a browser dashboard for chatting, reviewing memory activity and managing skills. It's open source under the MIT license.
326Updated 6 months agoMIT
macOS · Windows · Linux · Docker#Code execution#Guardrails#Hybrid search
250.6KUpdated 1 hour agoMIT
macOS · Windows · Linux · Android · Docker#Agent Skills#Code execution#Multi-agent workflows
922Updated 5 months agoMIT
macOS · Windows · Linux · Docker · Web#llama.cpp backend#LM Studio integration#MLX
117Updated 5 days ago
Docker · Web#Guardrails#Human approval#Hybrid search
AlexClaw is a self-hosted personal AI agent for one operator who wants to monitor information sources and automate recurring tasks on their own infrastructure. Built on Elixir/OTP and available through Docker, it collects RSS feeds, web pages, GitHub activity and API data into a searchable knowledge base. It has no multi-user access control.
906Updated 2 days agoAGPL-3.0
macOS · Windows#Agent Skills#Code execution#Git integration
Clawlet is a self-hosted personal AI agent for people who want an assistant on their own machine or server, with searchable memory across conversations. Written in Go, it ships as a standalone binary with no separate runtime dependency. It supports macOS on Apple Silicon and Docker deployment, and it's open source under the MIT license.
Hermes Agent is a self-hosted AI agent from Nous Research for people who want an assistant that remembers past work and develops reusable skills. It creates skills after complex tasks, revises them through use, and searches earlier conversations to recover context across sessions. The project is open source under the MIT license.
Eclaire is a self-hosted AI assistant for notes, documents, photos, bookmarks and tasks. You can ask questions about saved material, inspect the sources behind an answer and ask the assistant to create notes or update tasks. Scheduled automations handle recurring requests such as a weekly task summary.
MyAgents is a desktop AI agent workspace for people who want AI to act on their files and handle ongoing tasks through a graphical interface. It runs on macOS 13 or later and Windows 10 or later, with Apple Silicon and Intel support on Mac. The app is open source under AGPL-3.0.