
Perplexity Computer
Perplexity Computer is a 2026 multi-model agent system for long-running research, coding, finance, and workflow execution across cloud and Mac-based environments.
52 tools in this category

Perplexity Computer is a 2026 multi-model agent system for long-running research, coding, finance, and workflow execution across cloud and Mac-based environments.

Gemini Spark is Google’s 2026 personal AI agent for background tasks, connected apps, and user-directed 24/7 productivity workflows.

Replit Agent is an autonomous AI developer that builds, deploys, and maintains full-stack applications directly in the browser.

Langflow is an open-source, Python-native low-code builder for AI agents, RAG apps, visual workflows, APIs, and MCP server integrations.

Flowise is an open-source visual platform for building AI agents, RAG assistants, chatbots, and LLM workflows. It is strongest when teams need a self-hostable, API-ready builder that connects models, vector databases, tools, evaluations, and human review in one canvas.

AgentGPT is Reworkd's browser-based AutoGPT-era autonomous agent demo. Its repository was archived on January 28, 2026, although the hosted site and legacy plans may remain reachable. This guide evaluates current status, goal loops, pricing, security, self-hosting, evidence quality and maintained alternatives.

BabyAGI is an open-source autonomous agent experiment by Yohei Nakajima. The original 2023 task-loop agent popularized goal-driven task creation, execution, memory, and prioritization; the current project is an experimental self-building function framework, not a production-ready AGI system.

AutoGPT is the current Significant Gravitas AI agent project and platform for building assistants, automation blocks, and autonomous-agent experiments.
LlamaIndex is an MIT-licensed Python and TypeScript framework for RAG, document agents and context-augmented LLM apps. This independent review separates the open-source framework from LlamaParse/LlamaCloud, and examines retrieval design, workflows, evaluation, privacy, cost and alternatives.
OpenAI Swarm is an experimental, educational Python framework for routines and agent handoffs, now officially replaced by the production-oriented OpenAI Agents SDK. This review explains its status, safe experiments, migration and alternatives.

MetaGPT is an open-source multi-agent framework that models a software company with roles such as product manager, architect, engineer, and reviewer. It is best for studying agent collaboration and SOP-style software generation rather than one-click production app building.

TaskWeaver is Microsoft’s open-source code-first agent framework for data analytics tasks. It translates user requests into Python code, coordinates plugins as functions, preserves chat and code execution history, supports stateful execution, containers, observability, shared memory, experiences, and vision input for the Planner role.

An AI-powered analytics platform for financial institutions to analyze market data.

An AI platform for doctors to generate differential diagnoses and clinical plans.

Harvey is a professional-class legal AI platform for leading law firms and corporate legal teams. It focuses on contract analysis, due diligence, compliance, litigation, and legal knowledge work where expert review, security, and governance matter.

OpenClaw is an open-source personal AI assistant that runs on your own devices and connects to messaging channels, voice, and local or cloud model workflows.

Mock-Agent-Tester is an unverified directory entry: no canonical repository, release, license, or official documentation could be confirmed as of August 21, 2026. This page records the evidence gap and points developers to supported agent-testing alternatives.
FlyPloy is a young light-PaaS for pasting code or uploading a ZIP and publishing an app without operating servers. This evidence-led review checks the live workflow, $14.99 Starter plan, $2.99 deployment units, legal gaps, unverified infrastructure claims and alternatives before production use.

Mastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations and evals

Saplings is a small Python library that adds MCTS, A* and greedy tree search to tool-calling agents. Version 6.2.0 remains installable, but maintenance is quiet and its license metadata conflicts with the shipped Apache-2.0 file.

Build task-oriented custom agents for your codebase that perform engineering tasks with high precision powered by intelligence and context from your data. Build agents for use cases like system design, debugging, integration testing, onboarding etc.

AutoGen is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks.

Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
Self-Operating Computer is an MIT-licensed Python framework that lets multimodal models control a desktop through screenshots, mouse and keyboard actions. This independent review examines v1.5.8, maintenance, setup, security and safer alternatives.