workflowstacks
agent-memory

Run AI Agents On-Prem with OpenAgentd

Get self-hosted AI agent OS for streaming chat and tool use. For founders needing custom AI setups.

From the repo · “Self-hosted AI agent OS — streaming chat, tool use, persistent memory, and multi-agent teams. Runs entirely on your machine.”

213 stars+1★ this week37 forksPythonGuide quality 9/10 · reviewed Jul 12Updated 10/21/2026100% free · open source
What it does

OpenAgentd provides a self-hosted AI agent operating system for streaming chat and tool use with persistent memory and multi-agent teams, allowing founders to create custom AI setups

When to use it
  • •You need a custom AI setup for your startup with full control over data and infrastructure
  • •You require a self-hosted solution for AI-powered chat and tool integration
  • •You want to leverage persistent memory and multi-agent teams for complex AI workflows
Ready-to-paste prompt
python -m openagentd.main --config openagentd/config.json --web
Heads up: Make sure you have Python 3.8 or higher installed, as OpenAgentd is built using Python and may not be compatible with lower versions
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/openagentd && curl -fsSL https://workflowstacks.com/api/skills/openagentd/claude-skill -o ~/.claude/skills/openagentd/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

15
top-level files
10
folders
63.1M
source size
Apache-2.0
license
Key files
.pre-commit-config.yaml
AGENTS.md
README.md
File tree
.agents/
.github/
appv3/
desktop/
documents/
mobile/
native/
plugins/
scripts/
web/
.env.example
.gitattributes
.gitignore
.pre-commit-config.yaml
AGENTS.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
DESIGN.md
install.ps1
install.sh
LICENSE
Makefile
NOTICE
README.md
Quick Actions
Details
Creator
lthoangg
Language
Python
Category
agent-memory
Published
4/30/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/openagentd.svg)](https://workflowstacks.com/skills/openagentd?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Related skills

More agent-memory tools founders pair with this one.

agent-memory★ 1,109
stashbase: Instant, Local Knowledge Base for Docs & AI Artifacts
Founders store documents, screenshots, and AI outputs locally, giving both them and their AI fast, persistent recall without cloud dependencies.