TEN Framework is an open-source modular system for building autonomous AI agents capable of reasoning, memory management, and tool usage. Designed to reflect real-world constraints, it incorporates a Thought-Emission-Norm (TEN) architecture, encouraging agents to think before acting. The framework supports open-ended planning, persistent memory storage, and tool augmentation. Developers can use TEN to experiment with agent autonomy and deploy agents that simulate complex decision-making workflows.

TEN Framework

ten-framework

An open-source framework for building autonomous AI agents that interact with the real world through tools and memory.

AgentScope is an open‑source, developer‑centric multi‑agent platform for building, orchestrating, and deploying LLM‑powered agent systems. It features explicit message passing, zero‑code drag‑and‑drop UI, built‑in tool and MCP support, distributed execution, monitoring, automatic prompt tuning, and fault tolerance.

AgentScope

agentscope

Open‑source multi‑agent framework with drag‑and‑drop UI, distributed execution, tool calls, and fault tolerance.

ChainGPT AI Agent is a fully autonomous Web3 AI assistant that monitors blockchain data, social signals, and news to deliver real‑time market insights, alerts, and educational content via X. It features fact-checking, sentiment analysis, and daily recaps to keep crypto users informed and engaged.

ChainGPT AI Agent

chaingpt-ai-agent

Autonomous Web3 agent publishing real‑time crypto insights on X (Twitter) via AI-powered analysis.

Strands Agents is an open‑source SDK from AWS for building production‑ready AI agents using a model‑driven architecture. It supports any LLM provider, rich tool integration (including MCP and AWS services), multi‑agent workflows, observability via OpenTelemetry, and deployment in local or cloud environments.

Strands Agents

strands-agents

Open‑source SDK for building and orchestrating single or multi‑agent systems with LLMs and tool integration.

MCP‑Use is an open‑source library and platform that lets developers connect any LangChain‑compatible LLM to Model Context Protocol (MCP) servers. It enables creation of AI agents with tool access—like browsing, file operations, or HTTP services—supporting multi‑server setups, dynamic tool selection, streaming output, and both hosted and self‑hosted deployment options.

MCP‑Use

mcp-use

Open‑source platform to connect LLMs with MCP servers and build custom AI agents with tool access.

ChatGPT Agent is OpenAI’s built‑in autonomous agent that can perform web browsing, form filling, code execution, file generation (e.g., PowerPoint, Excel), and API interactions via a “virtual computer.” It combines earlier tools like Operator and Deep Research to manage complex tasks end‑to‑end, asking for user approval before irreversible actions and enforcing safeguards like watch mode and restricted access. It is available to Pro, Plus, and Team users, with rollout to Enterprise and Education tiers planned later in summer 2025.

ChatGPT Agent

chatgpt-agent

An autonomous AI tool within ChatGPT that executes complex, multi‑step digital tasks using a virtual computer.

Tidio Copilot is an AI customer service agent designed to handle repetitive customer support tasks, answer questions, and resolve tickets without human intervention. Built into the Tidio customer experience platform, Copilot leverages AI to understand customer intent, provide accurate responses, and escalate only complex issues to human agents. It integrates with existing tools and provides analytics to improve performance, helping businesses streamline support workflows and enhance customer satisfaction.

Tidio Copilot

tidio-copilot

AI-powered assistant that automates customer service conversations and resolves support tickets in real time.

Dart AI is an AI-powered project management platform that automates task creation, subtask breakdowns, reporting, duplicate detection, and integrates with tools like ChatGPT, GitHub, and Slack. It offers both no-code and advanced agent-driven workflows.

Dart AI

dart-ai

An AI-native project management tool that automates workflows, tasks, and reporting.

String.com (by Pipedream) is a developer‑centric AI agent builder that translates natural‑language prompts into working code. It integrates with services like GitHub, Linear, Slack, Gmail, Google Sheets, Stripe, Snowflake, and more. Users can define agents to watch repos, send emails, process data, automate tasks, and deploy them instantly without writing boilerplate.

String.com

string-com

A prompt‑driven AI agent builder that writes, runs, edits, and deploys agents via code in seconds.

Harness AI Code Agent is an intelligent IDE extension (VS Code & JetBrains) that uses LLMs like GPT‑4 and Gemini Flash to autocomplete, refactor, test, comment, and explain code. It indexes your full codebase to enable contextual chat, semantic search, pull‑request generation, and Terraform/inline assistance.

Harness AI Code Agent

harness-ai-code-agent

An AI-powered code assistant in IDEs that generates, explains, tests, and comments code contextually.

Paige AI offers clinical-grade AI applications and foundation models built from millions of histopathology slides to support cancer detection, subtyping, biomarker discovery, and multimodal co-pilot workflows for pathologists.

Paige AI

paige-ai

AI-powered digital pathology platform for cancer detection, biomarker analysis, and diagnostic workflow automation.

Keploy is an open‑source AI test automation agent that uses eBPF to record live traffic and generate deterministic unit, integration, and API tests with mocks/stubs. It integrates with CI/CD, supports multiple languages, and uses multi‑model LLMs for test generation and self‑healing.

Keploy

keploy

An open‑source AI agent that auto‑generates and maintains unit, integration, and API tests with mocks.

Explore AI Agents