Claude Code
Anthropic official command-line agent tool that lives in the terminal, understands codebases, edits files across repositories, runs tests, and executes git workflows.
SOURCE LINKED
Review profile →Deployment guide
Self-Hosted AI Agents
Compare source-linked agent tools whose directory profiles reference self-hosting or open-source deployment.
The short answer
Confirm license, model costs, hosting requirements, telemetry, and security controls at the source. This page currently surfaces 18 matching source-linked records from 220 active directory listings. Results are research leads, not endorsements or rankings.
Profiles to research
18 matchesCline (Claude Dev)
Autonomous coding agent inside VS Code capable of creating and editing files, running terminal commands, and using custom MCP tools with user confirmation.
SOURCE LINKED
Review profile →Aider AI Pair Programmer
Command line tool that pairs with you to write code with multi-model support, automatic git commits with descriptive messages, and repo map tracking.
SOURCE LINKED
Review profile →Model Context Protocol (MCP) Official Framework
Open standard that enables AI models to securely connect to external tools, databases, development servers, and context sources.
SOURCE LINKED
Review profile →LangGraph Agent Swarm Runtime
Library for building stateful, multi-actor applications with LLMs, used to create cyclical agent workflows and multi-agent teams.
SOURCE LINKED
Review profile →CrewAI Enterprise Multi-Agent Framework
Framework for orchestrating role-playing autonomous AI agents that work together to tackle complex workflows and enterprise automation.
SOURCE LINKED
Review profile →ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
SOURCE LINKED
Review profile →hermes agent
The agent that grows with you
SOURCE LINKED
Review profile →deepseek harness
DeepSeek Harness: Everything is a Plugin.
SOURCE LINKED
Review profile →AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
SOURCE LINKED
Review profile →firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
SOURCE LINKED
Review profile →langchain
The agent engineering platform.
SOURCE LINKED
Review profile →ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
SOURCE LINKED
Review profile →graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
SOURCE LINKED
Review profile →browser use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
SOURCE LINKED
Review profile →gemini cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
SOURCE LINKED
Review profile →claude mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
SOURCE LINKED
Review profile →ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
SOURCE LINKED
Review profile →Verification checklist
- Open the linked primary source and confirm the detail is still current.
- Treat an undisclosed field as unknown rather than assuming a value.
- Compare total fit, support, and constraints—not a single headline feature.
- Ask the listed organization to correct or claim its profile when details differ.
Common questions
How to use this guide
What is included in Self-Hosted AI Agents?
This guide surfaces 18 matching records from 220 active The AI Agent Market listings using published categories, tags, capabilities, and source links.
Are these listings recommendations or rankings?
No. They are research leads selected by transparent matching rules. Inclusion does not establish quality, safety, suitability, or current availability.
How should I verify a listing?
Open the linked primary source, confirm that the relevant detail is current, and ask the listed organization about pricing, eligibility, implementation, support, and constraints before deciding.