Agent ZeroAgent FrameworksAgent Zero is an open-source, MIT-licensed AI agent that works in its own Dockerized Linux workspace with a terminal, browser and desktop apps.Open sourceSelf-hostedViews · 7 daysTop 3%
Agent Frameworks
Frameworks and tools for building AI agents and multi-agent workflows.
43 results in Agent Frameworks
Active Pro listings from this category appear first. Your sort applies within Pro and Free results.
Agent ZeroAgent FrameworksAgent Zero is an open-source, MIT-licensed AI agent that works in its own Dockerized Linux workspace with a terminal, browser and desktop apps.Open sourceSelf-hosted7 views19,771 stars
Views · 7 daysTop 29%
ArchonAI Coding Assistants & Agent ToolingArchon is an open source, self-hosted workflow engine that runs AI coding agents such as Claude Code and Codex from YAML workflows in isolated git worktrees.Open sourceSelf-hostedViews · 7 daysTop 5%
Views · 7 daysTop 16%
BotpressLLM App Platforms & RAGBotpress is a cloud platform for building AI chat agents in a visual Studio or in TypeScript, then deploying them to web, WhatsApp, Slack, Teams and more. Its GitHub repository holds the open-source Hub integrations, SDK, CLI and API clients.Open sourceWeb platformFreemiumViews · 7 daysNo views in 7 days
Browser UseBrowser Automation & ScrapingMIT-licensed Python agent that drives Chromium over CDP with your choice of model: click, type, extract, custom tools and structured output. Includes a CLI and MCP server; Browser Use Cloud adds paid stealth browsers and a hosted agent API.Open sourceSelf-hostedFreemiumViews · 7 daysNo views in 7 days
ByteChefWorkflow AutomationByteChef is an Apache 2.0 platform for visual workflow automation and AI agents, with 250+ connectors, MCP and A2A support, Docker and Kubernetes self-hosting, a managed cloud and an Enterprise embedded edition.Open sourceSelf-hostedFreemiumViews · 7 daysNo views in 7 days
Views · 7 daysNo views in 7 days
Views · 7 daysTop 29%
CrewAIAgent FrameworksCrewAI is an MIT-licensed open-source Python framework for orchestrating multi-agent AI workflows; CrewAI Enterprise adds a hosted runtime with a free Basic tier and custom-priced governance features.Open sourceSelf-hostedViews · 7 daysTop 29%
DifyLLM App Platforms & RAGDify by LangGenius combines a visual workflow builder, knowledge pipelines, sandboxed agents, model management and app APIs. It runs as Dify Cloud or self-hosted with Docker Compose under a modified Apache 2.0 license.Open sourceSelf-hostedFreemiumViews · 7 daysTop 29%
EigentAI Assistants & ChatApache 2.0 desktop app built on the CAMEL framework for Windows, macOS and Linux. Run one agent or a coordinated Workforce with your own API keys, local models, MCP servers, Skills and scheduled Automations.Open sourceSelf-hostedFreemiumViews · 7 daysTop 10%
ForgeCodeAI Coding Assistants & Agent ToolingForgeCode is an Apache-2.0 terminal coding agent in Rust. It edits files and runs commands with your own model provider, adds a Zsh colon-prefix plugin, saved conversations, skills and MCP, plus an optional hosted factory.Open sourceSoftwareFreemiumViews · 7 daysTop 29%
gooseAI Coding Assistants & Agent ToolingApache-2.0 AI agent written in Rust, with a desktop app, a CLI and an ACP server. It works with 15+ model providers or built-in local inference, connects to MCP extensions and runs reusable recipes. Originally from Block, now hosted by AAIF.Open sourceSelf-hostedViews · 7 daysTop 7%
Hermes AgentAgent FrameworksMIT-licensed agent from Nous Research that runs in a terminal, desktop app, browser or chat apps. It keeps curated memory, writes and refines its own skills, schedules jobs and works with OpenRouter, Anthropic, OpenAI, local or Nous Portal models.Open sourceSelf-hostedFreemiumViews · 7 daysTop 3%
IronClawAI Assistants & ChatIronClaw is a MIT or Apache-2.0 Rust AI assistant from NEAR AI. It keeps credentials out of the model, runs tools in WASM sandboxes, and offers a local WebUI, routines, memory and MCP, or paid hosted instances.Open sourceSelf-hostedFreemiumViews · 7 daysTop 10%
Kortix CompanyOSAgent FrameworksSource-available platform for running AI agents across a company: event-triggered agents, 3,000+ connectors, per-session cloud computers, approvals and audit, from Kortix Cloud or a self-hosted Docker Compose stack.CommercialSelf-hostedFreemiumViews · 7 daysNo views in 7 days
LangChainAgent FrameworksLangChain is an MIT-licensed open-source framework (Python/JS) for building LLM applications and agents via LangGraph; LangSmith adds optional hosted tracing, evaluation and deployment.Open sourceSelf-hostedViews · 7 daysTop 29%
LangflowLLM App Platforms & RAGLangflow is an MIT-licensed platform for composing AI agents and retrieval workflows from Python components on a visual canvas. Flows run in the Playground, through a REST API or as MCP tools, from Desktop, Docker or a pip install.Open sourceSelf-hostedViews · 7 daysTop 29%
LeonAI Assistants & ChatLeon is an open-source personal AI assistant that runs from source on your own Linux, macOS or Windows machine. Its 2.0 Developer Preview adds an agent loop with toolkits, layered memory, llama.cpp or cloud models and optional local voice.Open sourceSelf-hostedViews · 7 daysTop 16%
LettaAgent FrameworksLetta Code is an open-source stateful agent harness whose agents keep memory and identity over time, used from a CLI, a browser or messaging apps.Open sourceSelf-hostedViews · 7 daysNo views in 7 days
LlamaIndexAgent FrameworksLlamaIndex is an MIT-licensed open-source framework (Python/TypeScript) for RAG pipelines and data agents on top of LLMs; LlamaCloud adds hosted document parsing and extraction.Open sourceSelf-hostedViews · 7 daysTop 29%
LobeHubAgent FrameworksLobeHub is a TypeScript agent workspace with tasks, memory, pages and MCP tools. Agents answer in Slack, Discord or Telegram, can drive Claude Code or Codex on your devices, and run in LobeHub Cloud, desktop apps or a Docker Compose stack.Open sourceSelf-hostedFreemiumViews · 7 daysTop 5%
Mem0LLM App Platforms & RAGMem0 extracts facts from conversations with an LLM, stores them per user, agent or run, and returns the relevant ones through hybrid search. It ships Python and Node SDKs, a Docker server with dashboard, a CLI, an MCP server and a hosted Platform.Open sourceSelf-hostedFreemiumViews · 7 daysNo views in 7 days
nanobotAgent FrameworksMIT-licensed personal AI agent from HKUDS that runs as a local or server gateway, answers in a browser, terminal or chat apps, works with files, shell, web and MCP tools, keeps long-term memory and runs scheduled automations.Open sourceSelf-hostedViews · 7 daysTop 29%
Shortlists for Agent Frameworks
Explore collections with tools relevant to this category, grouped by deployment, source model or workload.
Self-hosted IT tools →
38 matching tools from this category
IT tools with an API →
35 matching tools from this category
Open-source IT tools →
39 matching tools from this category
How to choose agent frameworks tools
Agent frameworks give developers the building blocks for software that plans, calls tools and acts on behalf of a user: model abstraction, tool definitions, memory, retrieval and orchestration of several cooperating agents. Many also ship a runtime that executes agents as long-running services with task queues, approvals and cost tracking. They sit below finished assistants and coding agents, since you assemble the behaviour yourself rather than install a ready product.
Who uses these tools
- Developers building agentic features into products
- Platform teams running internal agent services
- Machine learning engineers designing retrieval pipelines
Capabilities to compare
- Tool calling and function definition interfaces
- Short and long term agent memory
- Multi-agent orchestration and task handoff
- Retrieval over documents and knowledge bases
- Tracing, evaluation and human approval steps
Operating considerations
- Isolation of agents that run shell commands or browsers
- Token spend multiplies quickly with multi-agent loops
- Abstractions can tie code to one framework's conventions
- Hosted runtimes may store prompts, traces and tool outputs
Selection checklist
- Build one small agent end to end with your real tools before committing to a framework.
- Check which model providers and local inference servers the framework supports without custom adapters.
- Inspect how runs are traced, so you can replay a failure and see each tool call.
- Confirm how permissions, approvals and sandboxing work before giving any agent write access to production systems.
What belongs in this category: A product fits here if its main purpose is to let developers define, run or coordinate their own agents through code, configuration or workflow files, rather than offering a finished chat or coding assistant.
Agent Frameworks on iThub in figures
iThub lists 43 tools in Agent Frameworks. 39 of 43 are open source, 38 of 43 can be self-hosted, 42 of 43 have a free, freemium or open-source pricing model and 35 of 43 offer an API.
- Tools listed
- 43
- Open source
- 39
- Self-hostable
- 38
- Free to start
- 42
- With an API
- 35
- Web app
- 28
- Desktop app
- 30
Recently added: OpenComputer, Omnara, Sugabots, Dify
Typical use cases
- Answering internal questions from company documents with retrieval
- Automating multi-step support or operations tasks with approvals
- Coordinating several specialised agents on a research workflow
- Running scheduled agents that report on systems or data
Trade-offs to model
- A thin library stays close to the model API and is easy to debug, while a full platform adds runtime features and more lock-in.
- Self-hosting the agent runtime keeps prompts and data inside your network, whereas managed runtimes remove operational work but add a data processor.
Common mistakes
- Starting with a multi-agent design when a single agent with good tools would solve the problem more cheaply.
- Giving agents broad credentials during prototyping and never narrowing them before the workflow reaches real users.
- Skipping evaluation sets, so nobody notices when a prompt or model change quietly degrades results.
Compare LangChain and LlamaIndex →Explore MCP servers →See MLOps and LLMOps tools →
Decision resources
Continue the technical evaluation
Use the resources that match your decision stage. Profile data and linked sources were refreshed through November 11, 2026.
0 tools selectedCompare selected