Category

Agentic capability

Planners, tool-use, browser, computer-use.

35 listings

Every Agentic capability listing on ai-supply is a free, open-source AI capability that we scan and grade A–D for security before it appears here — so you can adopt with confidence, not just a star count. This category spans 13 Agents, 6 Skills, 5 MCP servers, 3 Connectors, 3 Guardrails, 2 Workflows, 2 Plugins and 1 Template.

Security posture: 12 of 35 scanned rated safe · avg score 85/100.

Agentic capability leaderboard →How we grade security →Security findings →All categories →

Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.

! B · 75⟳ 2y agoshellnetworkfs

◇خادم MCP

MCP TypeScript SDK

Official TypeScript/JavaScript SDK for building MCP servers and clients — the Node.js foundation for the Model Context Protocol.

! B · 88⟳ 4mo agoshellnetworkfs

⌬سير عمل

Langflow — Visual Agent & Workflow Builder

Low-code visual builder for LLM-powered agents and multi-step AI workflows with 100+ pre-built components.

✓ A · 100⟳ 5d agosecretsshellnetwork

High-performance, model-agnostic Python framework for building, running, and managing production AI agents at scale.

✓ A · 100⟳ 3d agoshellnetworkfs

OpenAI Agents SDK

OpenAI's lightweight Python framework for building multi-agent systems with handoffs, tracing, and guardrails.

! B · 75⟳ 11d agoshellnetworkfs

Pioneering autonomous task-management AI that uses GPT-4 and vector memory to self-generate and prioritize tasks.

! B · 88⟳ 5mo agoshellnetworkfs

Run large language models locally with a single command. OpenAI-compatible API for Llama, Mistral, Gemma, and more.

! B · 75⟳ 3d agonetworkfs

The leading framework for building LLM-powered applications and agents with chains, tools, memory, and retrieval.

! B · 75⟳ 5d agoshellnetworkfs

E2B Code Interpreter SDK

Secure cloud sandboxes for running AI-generated code — spin up a Python/JS interpreter in 150ms from your agent.

! B · 88⟳ 4d agoshellnetworkfs

◇خادم MCP

MCP Reference Servers

Official reference MCP servers: filesystem, git, fetch, memory, and more — the fastest way to give agents real-world tool access.

! B · 88⟳ 18d agoshellnetworkfs

Unified API gateway for 100+ LLM providers — call OpenAI, Anthropic, Gemini, Cohere, and local models with a single consistent interface.

! B · 88⟳ 9d agoshellnetworkfs

CLI scaffolder for full-stack LlamaIndex RAG and agentic apps — Next.js, FastAPI, or Express in one command.

! B · 75⟳ 1y ago

Microsoft's autonomous R&D agent for iterative hypothesis generation, experimentation, and quantitative research automation.

✓ A · 100⟳ 8mo agoshellnetworkfs

Cross-browser automation library for agents: control Chromium, Firefox, and WebKit with a single reliable API.

✓ A · 95⟳ 1mo agoshellinstall-hooknetwork

CAMEL — Communicative Agents for Multi-Agent LLMs

First multi-agent framework based on role-playing LLM societies; supports 20+ agent types, tool use, RAG, and multi-modal tasks.

! B · 75⟳ 4mo agoshellnetworkfs

Connect AI agents to the web: Browser Use lets LLMs browse, interact, and extract from any website autonomously.

✓ A · 100⟳ 11d agoshellinstall-hooknetwork

Griptape — Modular Python Agent Framework

Modular Python framework for building AI agents with chain-of-thought reasoning, tool use, memory, and structured workflows.

! B · 88⟳ 14d agoshellnetworkfs

Stanford's framework for programming — not prompting — LLMs: compile, optimize, and auto-tune modular AI systems.

! B · 75⟳ 2mo agoshellnetworkfs

Intelligent memory layer for AI agents — automatically extracts, stores, and retrieves relevant context across sessions.

! B · 75⟳ 3d agoshellinstall-hooknetwork

Official MIT-licensed Python SDK for the Model Context Protocol — build MCP servers and clients with full spec compliance.

! B · 88⟳ 1mo agoshellnetworkfs

Semantic Kernel

Microsoft's open-source SDK for building AI agents and skills in C#, Python, and Java — composable, enterprise-ready, and model-agnostic.

✓ A · 100⟳ 21d agoinstall-hooknetwork

LLM-powered multiagent persona simulation for synthetic UX research, focus groups, and business scenario testing.

✓ A · 100⟳ 4mo ago

AgentOps — AI Agent Observability & Monitoring SDK

Python SDK for AI agent monitoring, LLM cost tracking, session replay, and benchmarking across all major agent frameworks.

! B · 75⟳ 11mo agoshellnetworkfs

⛨ضابط أمان

Guaranteed structured generation from LLMs: enforce JSON, regex, grammar, or Pydantic schemas at the token level.

! B · 88⟳ 8d agoguards:4

Pydantic's type-safe agent framework: build production agents with structured I/O, dependency injection, and full observability.

✓ A · 100⟳ 3d agoshellinstall-hooknetwork

XAgent — Autonomous LLM Agent for Complex Tasks

Autonomous agent by OpenBMB with outer/inner loop planning, tool execution, and a human-in-the-loop GUI for long-horizon tasks.

! D · 0⟳ 2y agoshellnetworkfs

⛨ضابط أمان

Structured outputs for LLMs using Pydantic — patches any OpenAI-compatible client to return validated Python objects.

! B · 75⟳ 1mo agoguards:4

TaskWeaver — Code-First Data Analytics Agent

Microsoft's code-first agent framework that converts user requests into executable Python snippets for complex data analytics tasks.

! B · 75⟳ 2y agoshellnetworkfs

◇خادم MCP

Persistent local Markdown-based memory so your AI assistant remembers across sessions.

! B · 88⟳ 1mo agoshellinstall-hooknetwork

◇خادم MCP

Apache-2.0 Python framework for building MCP servers fast — decorator-based, zero boilerplate, typed tool definitions.

✓ A · 100⟳ 19d agoshellnetworkfs

⛨ضابط أمان

Validate, fix, and filter LLM outputs — define structured schemas and safety rules, then automatically retry when outputs fail validation.

! B · 88⟳ 1mo agoguards:6

◇خادم MCP

Microsoft's official MCP server that gives AI agents deterministic browser control via Playwright's accessibility tree.

✓ A · 100⟳ 19d agoshellnetworkfs

Makes your AI agent think like the laziest senior dev — the best code is the code you never wrote (YAGNI-first).

✓ A · 100⟳ 29d agoshellnetworkfs

Self-Operating Computer Framework

Framework that lets a multimodal model view the screen and control mouse and keyboard to complete tasks on a computer.

! B · 75⟳ 1y agoshellfs

⌬سير عمل

Crawl a website from a single URL and generate one consolidated knowledge file to power a custom GPT or RAG assistant.

✓ A · 100⟳ 1y agosecretsinstall-hooknetwork