AgentToolDrop: newest AI agent tools

Agno: Builds Python agents, teams and workflows and serves them as an API with the AgentOS runtime

Wed, 14 Oct 2026 12:00:00 GMT

Agno is a Python SDK with three primitives (agents, teams and workflows) plus a runtime, AgentOS, that serves them through a production API with 50+ endpoints over SSE and websockets. Sessions, memory, knowledge and traces are stored in your own database, and the runtime adds human approval, OpenTelemetry tracing, JWT-based RBAC with multi-tenant isolation, cron scheduling, and interfaces for Slack, Telegram, WhatsApp, Discord, AG-UI and A2A. Starter templates deploy it with Docker to Railway, AWS, GCP, Azure, Fly, Render, Modal or Helm.

Use it when: You want to build agents and also run them as a multi-user service on your own infrastructure, with data kept in your own database.

Skip it if: You are not on Python. Agno sends a telemetry event per agent run by default (prompts, messages and outputs are not sent); set AGNO_TELEMETRY=false to turn it off.

Install with pip:

pip install -U agno openai

Agent frameworks. Open source. License: Apache-2.0.

AgentToolDrop: newest AI agent tools

Agno: Builds Python agents, teams and workflows and serves them as an API with the AgentOS runtime

Aider: Pair programs with an LLM in your terminal, editing files in your git repo and committing each change

Anthropic Agent Skills: Provides Anthropic's example Agent Skills, the document skills behind Claude, and the skills spec

Arize Phoenix: Traces LLM and agent apps over OpenTelemetry and runs evals, datasets and experiments in a local UI

AutoGen: Builds multi-agent AI apps that act autonomously or alongside humans; now in maintenance mode

Browser Use: Lets an LLM drive a real browser to complete multi-step web tasks from Python code or a CLI

ccusage: Reports token usage and costs for Claude Code, Codex and other coding agent CLIs from local data

Chrome DevTools MCP: Lets a coding agent control and inspect a live Chrome browser through DevTools

Claude Agent SDK: Embeds Claude Code's agent loop, built-in tools and context management in Python or TypeScript apps

Claude API: Gives programmatic access to Claude models and Claude Managed Agents over a REST API with official SDKs

Claude Code: Reads your codebase, edits files, runs commands and handles git work from the terminal, IDE, desktop or web

Cline: Runs an approval-based coding agent in VS Code, JetBrains, the terminal or a desktop app with any model

Cognee: Turns documents, code and conversations into a knowledge graph that agents store to and recall from

Container Use: Gives each coding agent its own container and git branch so several can work in parallel without conflicts

Context7: Pulls current, version-specific library docs and code examples into your agent's context

CrewAI: Orchestrates teams of role-based agents (Crews) and event-driven workflows (Flows) in Python

Crush: Runs a terminal coding agent from Charm that works with your choice of LLM and uses LSPs for context

Cursor: Gives you a code editor and CLI with a built-in agent that plans, edits and reviews changes across your repo

Daytona: Runs AI-generated code in hosted sandboxes with their own kernel, filesystem and network stack

DeepEval: Unit tests LLM apps and agents in a Pytest-style workflow with LLM-as-a-judge and other metrics

DSPy: Builds LM programs from typed signatures and modules, then optimizes their prompts against a metric

E2B: Runs AI-generated code in isolated cloud sandboxes you start and control from Python or JavaScript

Exa MCP Server: Gives agents Exa web search and page fetching as MCP tools, with optional multi-step research runs

FastMCP: Builds MCP servers, clients and interactive apps in Python from plain decorated functions

Fetch MCP Server: Fetches a URL and returns the page as markdown in chunks the model can page through

Filesystem MCP Server: Lets an agent read, write, edit, move and search files inside directories you allow

Firecrawl MCP Server: Lets agents search, scrape, crawl and interact with web pages through Firecrawl, returning markdown or JSON

Framelink MCP for Figma: Gives a coding agent the layout and styling data behind a Figma file, frame or group link

Gemini CLI: Brings Gemini models into the terminal to query and edit codebases, run shell commands and search the web

GitHub Copilot: Suggests code, answers questions and works on assigned tasks across your IDE, terminal and GitHub

GitHub MCP Server: Connects agents to GitHub repos, issues, pull requests, Actions runs and security alerts

Google Agent Development Kit (ADK): Builds, evaluates and deploys Python agents and graph-based workflows, optimized for Gemini

goose: Runs a general-purpose AI agent on your machine as a desktop app, CLI or embeddable API

Graphiti: Builds temporal knowledge graphs from agent conversations and data, tracking how facts change over time

Inspect: Defines and runs model and agent evaluations in Python from datasets, solvers and scorers

Instructor: Returns validated Pydantic objects from LLM calls, retrying automatically when validation fails

LangChain: Provides one interface and a large integration library for models, embeddings, vector stores and tools

Langfuse: Traces LLM calls and agent steps, then runs evals, datasets and prompt versioning on top of them

LangGraph: Orchestrates long-running, stateful agents as graphs with durable execution and human-in-the-loop

LangSmith: Traces, evaluates and monitors LLM apps and agents on LangChain's hosted platform via Python and JS SDKs

Letta: Runs stateful agents that keep memory and identity across sessions and rewrite their own memory over time

LiteLLM: Calls 100+ LLM providers in the OpenAI format, as a Python SDK or a self-hosted AI gateway

llama.cpp: Runs LLM and VLM inference locally in plain C/C++, with a CLI and an OpenAI-compatible server

LlamaIndex: Connects LLM agents to your data with connectors, indexes, query engines and event-driven workflows

LLM: Runs prompts against remote and local LLMs from the command line or Python, logging calls to SQLite

Mastra: Builds TypeScript agents and graph-based workflows with memory, RAG, evals and model routing

MCP Inspector: Tests and debugs MCP servers from a web UI, a scriptable CLI or a terminal UI

Mem0: Adds long-term user, session and agent memory to AI apps through a Python or TypeScript SDK

Model Context Protocol: Defines an open standard for connecting AI applications to tools, data sources and workflows

Ollama: Runs open models locally behind a CLI and a REST API, with an OpenAI-compatible endpoint