AgentStack Daily

Define role-based agent crews with tasks and processes; good for quickly orchestrating researcher/writer/reviewer style teams.

Microsoft's framework for conversational multi-agent systems; agents message each other and call tools in event-driven loops.

Model agent workflows as stateful graphs with checkpoints, human-in-the-loop interrupts and multi-agent supervisors.

Lightweight Python SDK with agents, handoffs, guardrails and tracing; use handoffs to route between specialist agents.

Code-first toolkit for building, evaluating and deploying hierarchical multi-agent apps on Gemini or other models.

Open protocol for agents built on different frameworks to discover each other and delegate tasks over HTTP.

Assigns software-company roles (PM, architect, engineer) to agents that collaborate via SOPs to produce a project.

Research framework for role-playing communicative agents; useful for studying agent societies and generating data.

Enterprise-oriented orchestration library with many swarm topologies (sequential, hierarchical, mixture-of-agents).

Engineering write-up on orchestrator/subagent research: parallel subagents, effort scaling and prompt lessons.

Canonical guide to workflow patterns (prompt chaining, routing, orchestrator-workers) before reaching for full autonomy.

TypeScript agent framework with workflows, agent networks, memory and evals built in.

Type-safe Python agent framework; structured outputs and dependency injection make multi-step agents testable.

Fast Python framework for agents and agent teams with memory, knowledge and tool integrations.

The open standard for connecting LLM apps to tools, resources and prompts; start here for transports and auth.

Official collection of reference servers (filesystem, git, fetch, memory) to learn from or run directly.

Official SDK for building MCP servers and clients in TypeScript with stdio and streamable HTTP transports.

Official Python SDK including FastMCP-style decorators for quickly exposing tools.

Developer tool to connect to any MCP server and interactively test tools, resources and prompts.

Pythonic high-level framework for MCP servers and clients with auth, proxying and composition.

GitHub's official server exposing repos, issues, PRs and Actions to agents.

Microsoft's server that lets agents drive a browser via accessibility snapshots instead of screenshots.

Official community registry for discovering published MCP servers.

Hub for finding, hosting and installing MCP servers into clients.

MCP server that injects up-to-date, version-specific library docs into coding agents' context.

Guide to building and deploying remote MCP servers with OAuth on Cloudflare Workers.

Claude tool that operates a desktop via screenshots, mouse and keyboard; docs cover the reference container.

Docs for the computer-use tool in the Responses API, with a loop for executing actions in your environment.

Open-source library that makes websites accessible to agents; popular for browser automation tasks.

Browserbase's framework mixing Playwright code with natural-language act/extract/observe steps.

Hosted headless browsers for agents with sessions, stealth and live view.

Automates browser workflows with LLMs and computer vision; robust to layout changes.

Open-source process automation that learns from recorded human demonstrations.

ByteDance's native GUI agent app built on the UI-TARS vision-language model.

Secure cloud Linux desktops for running computer-use agents in isolation.

Open-source browser API for AI agents with session management and proxies.

Benchmark of real desktop tasks for evaluating multimodal computer-use agents.

Anthropic's agentic coding CLI; works in your terminal with subagents, hooks, MCP and skills.

Lightweight coding agent that runs locally in your terminal with sandboxed execution.

AI code editor with background/cloud agents, rules and MCP support.

Terminal pair-programmer that edits files in your git repo and commits changes.

Autonomous coding agent for VS Code that plans, edits and runs commands with approval.

Open platform for software-development agents (formerly OpenDevin) that can run in a sandbox.

Google's open-source terminal agent bringing Gemini to your shell with MCP support.

Assign an issue to Copilot and it opens a PR from an Actions-powered environment.

Open-source IDE extensions and CLI for custom coding assistants and agents.

VS Code agent fork of Cline with custom modes for architect/code/debug roles.

Princeton/Stanford agent that turns LMs into software engineers resolving GitHub issues.

Block's extensible local agent that automates engineering tasks via MCP extensions.

Open-source terminal coding agent supporting many model providers.

Anthropic's tips: CLAUDE.md, plan-first, test-driven loops and running multiple instances.

Package instructions, scripts and resources as folders that Claude loads on demand.

Public repo of example and document-handling skills you can copy and adapt.

Run shell commands at lifecycle events (pre/post tool use, stop) for deterministic guardrails.

Define specialized subagents with their own prompts and tool permissions for delegation.

Save reusable prompts as custom commands checked into your repo.

Run Claude Code in CI to respond to @claude mentions and automate routine PR work.

Open, simple format for giving coding agents project instructions across tools.

Persistent project/user rules that shape Cursor agent behavior.

Workflow automation with AI agent nodes; schedule recurring agent routines with hundreds of integrations.

How Codex reads AGENTS.md files to follow repo conventions.

Memory layer that extracts and retrieves user/agent facts across sessions.

Stateful agents with self-editing tiered memory, from the MemGPT research.

Temporal knowledge graph for agent memory that tracks how facts change over time.

LangChain library for long-term memory extraction and prompt optimization in agents.

Builds knowledge graphs plus vectors from your data as agent memory.

Reference knowledge-graph memory server any MCP client can use.

Claude API tool for storing and retrieving information in a file directory across conversations.

Guide to curating context: compaction, structured notes and sub-agent architectures.

Open-source embedding database commonly used for agent retrieval memory.

Benchmark of real GitHub issues for evaluating coding agents.

UK AISI framework for LLM and agent evaluations with sandboxed tools.

Framework and registry for evaluating LLMs and LLM systems.

CLI for testing prompts, agents and RAG with assertions and red-teaming.

Pytest-like LLM evaluation framework with agentic metrics like task completion.

Open-source LLM observability: traces, evals and prompt management for agents.

Open-source tracing and evaluation for LLM apps built on OpenTelemetry.

Sierra benchmark for tool-agent-user interaction in realistic domains.

Benchmark for agents completing tasks in real terminal environments.

Eval and observability platform for iterating on AI products.

Evaluation toolkit for RAG and agent pipelines.

Practical guidance on designing graders and tasks for agent evaluation.

Cognition's autonomous AI software engineer.

Build and deploy apps from prompts in the browser.

Prompt-to-full-stack web app builder in the browser.

Vercel's agent for generating UI and full apps.

API for agents that act on the web.

Web search API built for AI agents.

Search and extract API optimized for LLM agents.

Turns websites into LLM-ready markdown/data.

AI agents that act across Zapier's app integrations.

Visual automation platform with AI agents.

Build and run teams of AI agents for GTM work.

Data enrichment and AI research agents for outbound.

Autonomous AI SDR and phone agents.

Framework for document agents and RAG.

Tracing, evals and monitoring for LLM apps.

Weights & Biases toolkit for tracing and evaluating LLM apps.

Open-source LLM gateway and observability.

Secure cloud sandboxes for running agent code.