Directory
Agents & Skills
This section covers four kinds of AI add-on: AI agents, ChatGPT apps, Claude Skills and MCP servers. They extend what an AI assistant can do, and they can also reach your files, accounts or company systems. Each page explains one kind in plain language, then lists entries with their maintainer and what they can access.
Anavem lists what each entry asks for and what its official sources say. We do not label anything safe or unsafe: that decision depends on what you plan to use it for.
Browse by type
Four kinds of listing, each with its own page.
AI agents
Software that uses an AI model to carry out a multi-step task for you, not just answer a question.
ChatGPT apps
Add-ons that let ChatGPT work with another service from inside a conversation.
Claude Skills
Packaged instructions, and sometimes scripts, that teach Claude to do one kind of task the same way each time.
MCP servers
Programs that give an AI application access to outside tools and data through an open standard.
AI agents
Newest verification first. Order is editorial and never depends on commercial relationships.
An AI agent is software that uses an AI model to carry out a task for you in several steps. Instead of only answering a question, it can decide what to do next, use other tools or apps, and report back. For example, it might read a request, look something up, draft a document and ask you to approve it.
Because an agent can act, the most important question is what it is allowed to touch: your files, your email or calendar, your company systems, or the internet. Each listing below says what the maintainer states about that, and links to the official sources so you can check it yourself.
Agent Squad
Python and TypeScript framework for classifying requests, routing them to specialized agents and retaining per-agent conversation context.
By 2Fast · Verified Oct 4, 2026
Langroid
Python framework centered on Agent and Task abstractions for tool use, retrieval and multi-agent message passing.
By Langroid community · Verified Oct 4, 2026
Letta
Platform and developer tools for stateful agents that retain editable memory and identity across long-running interactions.
By Letta · Verified Oct 4, 2026
Agent Zero
General-purpose agent environment with a Linux terminal, browser, documents, projects, skills, plugins and hierarchical multi-agent delegation.
By Agent Zero community · Verified Oct 4, 2026
Browser Use
Python framework and service for agents that navigate websites through a controlled browser and callable tools.
By Browser Use · Verified Oct 4, 2026
AutoGPT Platform
Visual platform for assembling, scheduling and monitoring agents that connect reusable blocks to external services.
By Significant Gravitas · Verified Oct 4, 2026
MetaGPT
Role-based multi-agent framework that models a software team using standard operating procedures and structured artifacts.
By FoundationAgents · Verified Oct 4, 2026
CAMEL-AI
Python framework for communicative agents, role-playing systems, multi-agent workforces, tools, memory, retrieval and synthetic data generation.
By CAMEL-AI community · Verified Oct 4, 2026
BeeAI Framework
Python and TypeScript framework for agents, tools and workflows with memory, RAG, observability, MCP and A2A support.
By IBM and BeeAI community · Verified Oct 4, 2026
VoltAgent
Open-source TypeScript agent framework with tools, memory, RAG, workflows, guardrails and optional VoltOps observability.
By VoltAgent · Verified Oct 4, 2026
Mastra
TypeScript framework for agents and workflows with tools, memory, retrieval, structured output, evaluation and observability.
By Mastra · Verified Oct 4, 2026
Agno
Python framework for agents, teams and workflows with memory, knowledge, guardrails, monitoring and an AgentOS runtime.
By Agno · Verified Oct 4, 2026
Hugging Face smolagents
Minimal Python agent library with code-writing and tool-calling agents, model portability, MCP support and optional sandbox integrations.
By Hugging Face, Inc. · Verified Oct 4, 2026
Haystack Agents
Python AI orchestration framework whose Agent component runs tool loops inside composable retrieval and generation pipelines.
By deepset GmbH · Verified Oct 4, 2026
LlamaIndex Agents and Workflows
Python and TypeScript data framework with retrieval, tool-using agents and event-driven workflows for applications grounded in private data.
By LlamaIndex · Verified Oct 4, 2026
Strands Agents SDK
AWS-backed Python and TypeScript SDK for model-driven agent loops, tools, state, interventions and multi-agent patterns.
By Amazon Web Services · Verified Oct 4, 2026
Google Agent Development Kit
Code-first agent development kit from Google for tool-using agents, workflow agents, multi-agent systems and deployment across supported runtimes.
By Google LLC · Verified Oct 4, 2026
PydanticAI
Typed Python agent framework from the Pydantic team with dependency injection, validated outputs, tools, multi-agent patterns and evaluation support.
By Pydantic Services Inc. · Verified Oct 4, 2026
Microsoft Semantic Kernel
Microsoft SDK for integrating models, plugins and agent orchestration into Python, .NET and Java applications.
By Microsoft Corporation · Verified Oct 4, 2026
Microsoft Agent Framework
Microsoft framework for building Python and .NET agents, graph-based workflows and multi-agent systems with tools, state, human approval and protocol integrations.
By Microsoft Corporation · Verified Oct 4, 2026
OpenHands Agent Canvas
Open-source, self-hosted control center for coding agents. It runs the OpenHands agent or other ACP-compatible agents such as Claude Code and Codex on local, Docker, VM or cloud backends, and can run automations on a schedule or from webhooks.
By OpenHands (OpenHands organisation on GitHub) · Verified Oct 3, 2026
OpenAI Agents SDK (Python)
Open-source Python SDK from OpenAI for multi-agent workflows with tools, handoffs, guardrails, sessions, human-in-the-loop, tracing, realtime and voice agents, and sandbox agents. It supports other model providers.
By OpenAI (openai organisation on GitHub) · Verified Oct 3, 2026
CrewAI
Open-source Python framework for multi-agent workflows. Crews are teams of role-based agents; Flows are event-driven workflows. A separate commercial control plane, CrewAI AMP, adds managed deployment and observability.
By crewAI, Inc. (crewAIInc organisation on GitHub) · Verified Oct 3, 2026
LangGraph
Open-source Python framework from LangChain for building long-running, stateful agents as graphs. Its docs list durable execution, human-in-the-loop interrupts, memory and optional deployment on LangSmith.
By LangChain, Inc. (langchain-ai organisation on GitHub) · Verified Oct 3, 2026
What to check before installing
A few minutes here is cheaper than undoing a bad connection later.
- Who maintains it. Is the maintainer named, and do they link to an official website or source repository you can inspect?
- What it can access. List the files, accounts, messages or systems it asks for. Is each one really needed for the job you have in mind?
- Where your data goes. Does the data stay on your device, or is it sent to the maintainer or to other services? Read their privacy terms.
- Licence and source. Is the code published, and under which licence? A published source lets others review it.
- Last release. Has it been updated recently, and does the maintainer say how problems are reported?
- Start small. Try it with a test account or non-sensitive data first, and grant read-only access where the choice exists.
- How to remove it. Know how to revoke access and uninstall it before you depend on it.
- Does it act on its own, or does it ask for your approval before it sends, deletes, buys or publishes anything?