Agent Skills & Prompts

Git-native AI agent session capture and reasoning traceability

Checkpoints by Entire captures the full reasoning context behind AI-generated code directly in Git. Entire records transcripts, prompts, files touched, token usage, and tool calls alongside every commit. Session metadata lives on a separate branch keeping your history clean, with rewind capabilities to restore any previous agent checkpoint when things go sideways.

Source-available LLM app development platform

Source-available LLM application development platform combining a visual no-code canvas with backend capabilities for building AI workflows, RAG pipelines, and agent systems from prototype to production. Integrates hundreds of models from dozens of providers, with PDF/PPT ingestion, ReAct agents with 50+ tool integrations, and multi-step orchestration. Used by both technical and non-technical teams to ship GenAI apps like chatbots and Q&A systems.

Context compression for LLM apps and coding agents

Headroom is an Apache-2.0 context compression layer for LLM apps and coding agents. It compresses tool output, logs, files, RAG chunks, and agent history through a local library, proxy, wrapper, or MCP server, with retrieval hooks for bringing originals back when needed. Treat its savings numbers as Headroom-reported benchmarks, not independent aicoolies measurements.

Knowledge graph-powered RAG framework from HKU

LightRAG is a research-backed RAG framework from Hong Kong University that combines knowledge graph structures with vector search for more contextual retrieval. Published at EMNLP 2025, it extracts entities and relationships from documents to build a structured knowledge graph, then uses dual-level retrieval across both graph and vector representations with five query modes: naive, local, global, hybrid, and mix.

24/7 local screen & audio recording for AI agents

Screenpipe is an open-source Rust platform that records your screen and microphone 24/7 locally, then lets AI agents automate tasks based on what you've done. It uses event-driven capture with OS accessibility trees for efficient text extraction, stores everything in local SQLite, and exposes a REST API plus MCP server for AI integration with Claude, Cursor, and Ollama.

Cross-agent messaging for CLI coding agents

agmsg is an MIT-licensed Bash and SQLite messaging layer for CLI coding agents. It lets Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Antigravity, OpenCode, Hermes, and other terminal agents exchange messages through a shared local database instead of relying on a human copy-paste relay. It is intentionally not MCP, not a broker, and not a subagent framework.

MCP, ACP and Skills support for building production coding agents — interactive or automated.

fast-agent is an Apache-licensed Python framework for building and running LLM agents with full MCP (Model Context Protocol) and ACP support. It ships with an interactive shell mode, Skills management, and multi-model routing — making it a practical platform for coding agents, workflow automation, and agent evaluation across Claude, Codex, HuggingFace, and local models.

Lightweight multi-modal agent framework

Fast, lightweight Python framework for building multi-modal AI agents, formerly known as Phidata. Includes built-in memory, knowledge bases, tools, and reasoning capabilities with 40K+ GitHub stars. Designed for developers who want to build production-ready agents quickly with minimal boilerplate, supporting structured outputs and multi-agent coordination out of the box.

Tool infrastructure for AI agents

Composio connects AI agents to 1,000+ app toolkits with managed auth, delegated user connections, sessions, tool search, MCP gateway support, CLI workflows, and sandboxed workbench execution. It targets developers building Claude, Codex, Cursor, LangChain, CrewAI, OpenAI Agents SDK, and custom agent workflows that need authenticated business actions without hand-rolling every API integration.

High-performance open-source web crawler optimized for AI pipelines

Crawl4AI is an open-source Python web crawler built for AI and data-pipeline use cases. It produces LLM-ready Markdown, supports structured extraction, Playwright/browser automation, deep/adaptive crawling, proxy/security controls, anti-bot fallback patterns, and multiple output formats. With 68K+ GitHub stars and Apache-2.0 licensing, it is a strong local/self-hosted option for RAG datasets and agent data collection.

Official remote MCP server for design-to-code and write-to-canvas Figma workflows.

Figma MCP Server is Figma’s official remote Model Context Protocol surface for design-to-code agents. It gives supported clients structured design context, variables, components, selected-frame code context, Code Connect mappings, and beta write-to-canvas tools for creating or updating native Figma frames from an MCP client while keeping the workflow tied to Figma files.

Rust-native multi-agent orchestration for production

GraphBit is a Rust-native, multi-agent orchestration framework built for production. It targets the gap between Python-first frameworks like LangGraph and the operational expectations of enterprise systems — predictable memory, low latency, deterministic concurrency, and the ability to embed an agent runtime in services that already run Rust without dragging in a Python interpreter.

Production-grade browser automation with AI self-healing and Playwright code ownership

Intuned is a code-first browser automation platform that turns natural language prompts into production-ready Playwright code, deploys it, and self-heals it when target sites change. Supports TypeScript and Python with Anthropic Computer Use, OpenAI CUA, Stagehand, Browser-Use, and Gemini Computer Use integrations. Built-in stealth, captcha solving, auth session management, and scheduled runs with concurrency control. No vendor lock-in—you own the code.

Framework for LLM applications

The most widely-used framework for building LLM-powered applications, available in Python and JavaScript. Provides abstractions for chains, agents, RAG, memory, tool usage, and structured output. Integrates with 100+ LLM providers, vector stores, document loaders, and tools. LangSmith offers tracing and evaluation. LangGraph enables stateful, multi-agent workflows with cycles. 100K+ GitHub stars. The de facto standard for LLM application development despite growing alternatives like LlamaIndex.

Unified API proxy for 100+ LLMs

Drop-in OpenAI-compatible proxy supporting 100+ LLM providers with load balancing, spend tracking, rate limiting, and fallback routing. Acts as a unified gateway for all your AI model calls, letting teams switch between providers, enforce budgets, and add reliability layers without changing application code. Essential infrastructure for multi-model AI architectures.

Open-source personal AI agent for messaging apps

OpenClaw is a free, open-source AI agent framework that turns any LLM into an autonomous personal assistant accessible through messaging apps like WhatsApp, Telegram, Discord, and Signal. Running entirely on your local machine via a Node.js gateway, it connects AI models to system tools, browsers, files, and APIs for multi-step task execution with persistent memory across sessions.

Alibaba's agent framework built for the Qwen model family

Qwen-Agent is Alibaba's Apache-2.0 framework for building AI agents around the Qwen model family. It supports tool use, planning, memory, RAG, Code Interpreter, Browser Assistant, MCP extras, custom tools, and Qwen Chat backend patterns with Qwen3/Qwen3.5 examples. Best fit for teams standardizing on Qwen rather than a generic multi-agent router, with 16.5K+ GitHub stars.

Microsoft’s pytest-native red teaming framework for turning AI agent safety findings into CI tests.

RAMPART is an open-source Microsoft framework for safety and security testing of agentic AI applications. It brings red-team findings into a pytest-native workflow so teams can turn prompt injection, unsafe tool use, and behavioral boundary failures into repeatable regression tests. The strongest aicoolies angle is developer workflow: RAMPART makes agent safety part of CI/CD instead of a one-off security review.

No-code platform for building AI agent workforces

Relevance AI is a no-code platform from Sydney, Australia for building and deploying AI agent workforces that execute business workflows autonomously. Backed by a $24M Series B led by Bessemer Venture Partners, it offers 9,000+ integrations, a visual agent builder, a marketplace of pre-built agents, and multi-model support across OpenAI, Anthropic, and AWS Bedrock. Agents handle sales development, lead research, meeting prep, onboarding, and support workflows.

MCP server for controlling Windows desktops through UIAutomation

Windows-MCP is an open-source MCP server for giving AI agents structured access to Windows desktop automation. It focuses on UIAutomation, snapshots, input control, and Windows-specific app workflows, making it different from general filesystem or shell MCP servers.

Multi-agent AI framework

Python framework for orchestrating autonomous AI agents that collaborate to accomplish complex tasks. Define agents with specific roles, goals, and backstories, then organize them into crews with sequential or parallel task execution. Supports tool usage (web search, file I/O, API calls), memory, delegation between agents, and human-in-the-loop input. Works with OpenAI, Anthropic, local models, and more. 25K+ GitHub stars. Leading multi-agent framework alongside LangGraph and AutoGen.

Open-source observability for AI agents

Laminar is an open-source observability platform for AI agents providing tracing, evaluation, and analytics for LLM applications. It integrates with Vercel AI SDK, LangChain, OpenAI, and Anthropic with a single line of code. Features include OpenTelemetry-native SDKs, an extensible evaluation framework with CI/CD support, SQL access to traces and metrics, and a visual debugging timeline for agent reasoning and actions.

The LLM anti-framework for typed AI apps

Mirascope is an open-source Python and TypeScript toolkit for building LLM applications that prioritizes type safety, composability, and 100% test coverage. Positioned as the 'anti-framework,' it provides fine-grained control over LLM interactions using familiar language constructs rather than rigid abstractions, supporting all major providers through a unified interface.

Read/write MCP bridge between AI coding agents and Figma

Talk to Figma MCP is an MIT-licensed bridge from Grab that connects Cursor, Claude Code, and other MCP-capable agents to Figma through a local MCP server, WebSocket bridge, and Figma plugin. Unlike read-only context servers, it can inspect selections, create or modify nodes, update text in bulk, and automate design operations, so teams should review permissions before enabling write access.

Microsoft's conversational multi-agent framework

AutoGen is an open-source programming framework from Microsoft Research for building AI agents and facilitating cooperation among multiple agents to solve complex tasks through multi-turn conversations. Pioneered conversable agents that interact, use tools, and involve humans in the loop for multi-agent workflows. v0.4 features a redesigned async event-driven architecture with stronger observability, flexible collaboration patterns, and reusable components.

Self-evolution engine for AI agents with auditable updates

Evolver is an open-source self-evolution engine for AI agents that turns run logs into auditable, reviewable updates via its Genome Evolution Protocol. Instead of ad hoc prompt tweaking, teams collect traces and Evolver proposes versioned diffs to prompts, tools and workflows that engineers can approve, reject or roll back like code.

Sandboxes for coding agents — Linux VMs, Git, and deploys in one box

Freestyle is YC-backed sandbox infrastructure built for AI coding agents, shipping secure Linux VMs with nested virtualization, Git servers, and one-click web deploys. It lets agents run real workloads, branch repos, and deploy apps under short-lived identities while billing only for active compute. Used in production by vly.ai, Rork, and Vibeflow.

Scalable browser infrastructure for AI agents

Hyperbrowser is a cloud browser platform for AI agents and automation, providing managed Chrome sessions through Playwright, Puppeteer, CDP, REST, Python, and Node.js SDKs. Docs cover Stagehand, stealth/proxy options, ad blocking, recordings, scraping APIs, and credit pricing without promising universal CAPTCHA or anti-bot bypass.

LLM application observability and evaluation platform

LangSmith is LangChain's platform for debugging, testing, evaluating, and monitoring LLM applications in production. Provides detailed tracing of every step in LLM chains and agent workflows, dataset management for regression testing, prompt versioning, and automated evaluation with custom metrics. Features an annotation queue for human feedback, online monitoring dashboards, and integration with LangChain, LangGraph, and any LLM framework via the Python/JS SDK. Essential for production LLM ops.

Browser automation with AI vision — no XPath or DOM parsing needed

Skyvern automates browser-based workflows using LLMs and computer vision instead of brittle XPath or CSS selectors. It understands web pages visually, navigating forms, clicking buttons, and extracting data like a human would. Achieved 85.85% success rate on WebVoyager benchmark and SOTA on WRITE tasks for RPA. 21,000+ GitHub stars, AGPL-3.0 licensed. Skyvern Cloud offers managed usage-based hosting for teams that prefer not to self-host the infrastructure.

Official Slack MCP server for approved workspace search, messaging, canvas, and user-context actions.

Slack MCP Server is Slack’s official remote MCP layer for giving approved AI clients workspace context and controlled actions. It lets agents search messages, files, users, and channels, draft or send messages, read threads, manage canvases, and authenticate through Slack OAuth while workspace admins approve integrations and normal Slack rate limits still apply.

Evaluation framework for RAG pipelines

RAGAS is an Apache-2.0 open-source evaluation framework with 14K+ GitHub stars that provides standardized metrics for assessing RAG pipeline quality. It measures faithfulness, answer relevancy, context precision, and context recall to identify whether retrieval, generation, or both are failing. It is framework-agnostic, supports LLM-as-judge evaluation, and its README discloses minimal anonymized Open Analytics with a RAGAS_DO_NOT_TRACK opt-out.

Drag-and-drop LLM flow builder

Open-source protocol for connecting AI models to external tools and data sources, created by Anthropic. Provides a standardized way for LLMs to interact with APIs, databases, and local files through a universal client-server architecture. Rapidly adopted across the AI ecosystem as the standard interface between AI assistants and the tools they need to be useful.

Self-evolving local computer agent with a reusable skill tree

GenericAgent is a minimal, self-evolving autonomous agent from a 3.3K-line seed and ~3K core loop that gives LLMs system-level control of a local computer. It writes files, runs shell commands, browses the web, and uses keyboard/mouse/screen/mobile tools, while skill crystallization saves successful runs into a reusable skill tree that cuts token cost on repeats.

Prompt registry, observability, and evaluation workflows for LLM applications.

PromptLayer is a prompt management, observability, and evaluation platform for LLM applications. Teams use its Prompt Registry, visual editor, request logs, Tables, evaluations, Tool Registry, and Skill Collections to version prompts, replay requests, compare variants, run datasets, and ship prompt changes without redeploying code. Pricing starts with Free $0 for 5 users and 2.5K requests/month, Pro $49/month, Team $500/month, and Enterprise custom.

MCP server registry and hosting

Registry and management platform for Model Context Protocol (MCP) servers that helps teams securely discover, install, deploy, and connect MCP servers for AI assistants. Smithery combines a searchable catalog, CLI setup, hosted deployments, namespaces, connection APIs, and scoped service-token flows for clients such as Claude, Cursor, Windsurf, and Codex.

Kubernetes-native framework for DevOps AI agents

kagent is a Kubernetes-native AI agent framework developed at Solo.io and accepted into the CNCF sandbox. It provides a structured environment for running DevOps-focused agents directly within Kubernetes clusters, with a dedicated kmcp toolkit for cloud-native operations. Unlike general-purpose agent frameworks, kagent targets platform engineers and SREs who need AI assistance with cluster management, troubleshooting, and infrastructure automation workflows.

Open-source toolkit for building AI SRE incident response agents

OpenSRE is Tracer Cloud’s open-source public-alpha Python toolkit for building AI SRE agents that investigate and respond to production incidents. It ships 60+ tools across observability, databases, incident management, communications, deployment and protocol integrations, plus simulation/evaluation workflows for benchmarking agent accuracy before live pager use.

Local microVM sandboxes for AI agent code execution

Microsandbox provides hardware-level isolated sandboxes for AI agents to execute code safely on local machines. Using libkrun microVMs and a 320ms bare-metal Linux/KVM homepage benchmark, it offers stronger isolation than Docker containers while staying lightweight enough for dev workstations. OCI-compatible with Python and Node.js runtimes. Apache-2.0 licensed with 6.6K+ GitHub stars.

Open-source RAG-based text-to-SQL engine

Vanna AI is an MIT-licensed text-to-SQL and SQL-agent framework with 23.6K+ GitHub stars. Its current Vanna 2.0 story adds user-aware agents, access control, audit logs, streaming UI components, and optional hosted admin features for teams that need natural-language database access without locking into one LLM or database. The original repo is now archived, so verify the current Vanna 2.0 path before adoption.

MCP server for connecting AI assistants to Supabase projects

Supabase MCP is Supabase's Apache-2.0 server for connecting AI assistants to Supabase projects. It can expose database, configuration, and project-management workflows to MCP clients such as Cursor, Claude, and Windsurf, while the official docs emphasize permission and security review before production use, SQL changes, or high-privilege database access.

OpenAI's autonomous coding agent orchestration framework

Symphony is OpenAI's open-source framework that turns project work into isolated, autonomous implementation runs. Instead of supervising coding agents line by line, teams assign tasks from project boards and Symphony dispatches agents to handle them independently. Each agent works in an isolated workspace, provides proof of work documentation including CI status and PR review feedback, and can automatically merge approved pull requests.

Next-gen multi-agent framework (AutoGen fork)

AG2 (formerly AutoGen) is an open-source multi-agent AI framework that emerged as a community-driven fork of Microsoft AutoGen, founded by original creators Chi Wang and Qingyun Wu after leaving Microsoft. Licensed Apache 2.0 under open governance, it provides an AgentOS for multi-agent conversations, tool use with any LLM, human-in-the-loop workflows, group chat orchestration, and teachable agents. AG2 Beta adds streaming, event-driven production architecture.

Open standard for guiding AI coding agents at the repository level

AGENTS.md is an open standard format adopted by 60,000+ open-source projects for providing AI coding agents with repository-level instructions. With 20,000+ GitHub stars, it has been adopted by GitHub Copilot, OpenAI Codex, Google Gemini CLI, and multiple IDEs as the de facto way to communicate project context and coding conventions to AI agents.

Autonomous scientific discovery via agentic tree search

AI Scientist v2 is Sakana AI's source-available system distributed under the AI Scientist Source Code License for fully autonomous scientific research using LLM-powered agentic tree search. It generates hypotheses, designs experiments, writes and executes code, analyzes results, and produces publishable manuscripts without human intervention. The system uses progressive exploration with backtracking to navigate the research space efficiently.

MCP servers for AWS cloud services and workflows

AWS MCP Servers is a collection of open-source MCP server implementations from AWS Labs that connect AI coding agents to AWS services. It includes servers for AWS documentation, knowledge bases, and managed cloud workflows, enabling agents to provision resources, query docs, and manage infrastructure through the Model Context Protocol.

Open-source desktop AI coworker for browsing and code execution.

Accomplish Coworker is an MIT-licensed open-source AI coworker that runs on the desktop, combining computer-use style browsing with code execution so agents can research, implement, run, and debug workflows in one local environment.

Multi-agent coordination framework

A framework for coordinating multiple AI agents working together on complex development tasks. Defines agent roles, communication patterns, task delegation strategies, and inter-agent workflows to break down large projects into manageable, parallel workstreams handled by specialized agents. Ideal for teams experimenting with multi-agent architectures where different AI models handle distinct aspects of software development.