{"id":34091766,"url":"https://github.com/josharsh/aa-kit","last_synced_at":"2026-04-07T06:31:44.764Z","repository":{"id":306699628,"uuid":"1015891793","full_name":"josharsh/aa-kit","owner":"josharsh","description":" AA Kit is a Python framework designed to build AI agents that naturally compose into ecosystems. Every agent is simultaneously a standalone agent, an MCP server, and an MCP client - creating true interoperability across the entire AI landscape.","archived":false,"fork":false,"pushed_at":"2025-07-08T07:35:47.000Z","size":2,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-16T18:21:45.288Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/josharsh.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-07-08T07:30:04.000Z","updated_at":"2025-07-08T07:35:50.000Z","dependencies_parsed_at":"2025-07-27T05:38:12.336Z","dependency_job_id":"bda02d5c-aed3-4763-b63c-a2fa28194bfa","html_url":"https://github.com/josharsh/aa-kit","commit_stats":null,"previous_names":["josharsh/aa-kit"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/josharsh/aa-kit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josharsh%2Faa-kit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josharsh%2Faa-kit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josharsh%2Faa-kit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josharsh%2Faa-kit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/josharsh","download_url":"https://codeload.github.com/josharsh/aa-kit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josharsh%2Faa-kit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31503381,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T03:10:19.677Z","status":"ssl_error","status_checked_at":"2026-04-07T03:10:13.982Z","response_time":105,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-12-14T14:49:57.860Z","updated_at":"2026-04-07T06:31:44.759Z","avatar_url":"https://github.com/josharsh.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🤖 AA Kit: Agent As Everything\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Status-Coming%20Soon-orange?style=for-the-badge\" alt=\"Coming Soon\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/License-MIT-blue?style=for-the-badge\" alt=\"MIT License\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Python-3.8+-green?style=for-the-badge\" alt=\"Python 3.8+\" /\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ch3\u003e🚀 One Agent, Many Forms\u003c/h3\u003e\n  \u003cp\u003e\u003cem\u003eYour agent is a tool. Your agent is a server. Your agent is a function.\u003cbr/\u003e\n  With AA Kit, agents transcend categories.\u003c/em\u003e\u003c/p\u003e\n\u003c/div\u003e\n\n---\n\n## 🌟 The Philosophy\n\n\u003e **\"When you realize an agent can be a tool for another agent, and that tool is also an agent, you understand: agents are the universal primitive of AI.\"**\n\nAA Kit isn't just another agent framework—it's a paradigm shift. We believe agents shouldn't be boxed into roles like \"chatbot\" or \"assistant.\" Instead, agents are the **universal primitive** of AI systems, capable of being:\n\n- 🔧 **Tools** for other agents\n- 🌐 **Servers** via MCP protocol  \n- ⚡ **Functions** that compose naturally\n- 🏗️ **Building blocks** for AI ecosystems\n\n## ✨ What Makes AA Kit Different\n\n### 🎯 **Agent = Function**\n```python\n# Three parameters. Returns intelligence. No complexity.\nagent = Agent(\n    name=\"assistant\",\n    instruction=\"You are a helpful assistant\", \n    model=\"gpt-4\"\n)\n```\n\n### 🌐 **Agent = Server**\n```python\n# Every agent exposes itself as an MCP server instantly\nagent.serve_mcp()\n# Now available at: http://localhost:8080/mcp\n```\n\n### 🔗 **Agent = Tool**\n```python\n# Pass one agent to another as a tool\nwriter = Agent(\n    name=\"writer\",\n    instruction=\"You write articles\",\n    model=\"gpt-4\",\n    tools=[researcher_agent]  # Natural composition\n)\n```\n\n### 🚀 **Agent = Production**\nRate limits, retries, caching, circuit breakers—not added later, but built into the constructor from day one.\n\n## 🎨 Core Features\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"33%\"\u003e\n\n### 🏗️ **Universal Composition**\nAgents compose naturally because they're all the same primitive underneath. No special interfaces or adapters needed.\n\n\u003c/td\u003e\n\u003ctd width=\"33%\"\u003e\n\n### 🌐 **MCP Native**\nEvery agent is automatically MCP-compatible. Zero configuration, instant interoperability with the entire MCP ecosystem.\n\n\u003c/td\u003e\n\u003ctd width=\"33%\"\u003e\n\n### ⚡ **Production Ready**\nBuilt-in rate limiting, retry logic, circuit breakers, and caching. Scale from prototype to production without refactoring.\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n## 📊 By The Numbers\n\n\u003cdiv align=\"center\"\u003e\n\n| **3** | **0** | **∞** | **1** |\n|-------|-------|-------|-------|\n| Lines to Production | Config for MCP | Composition Depth | Universal Protocol |\n\n\u003c/div\u003e\n\n## 🔮 Coming Soon\n\nThe open source release of AA Kit is being finalized. Here's what you can expect:\n\n### 📦 **Core Package**\n- Pure Python implementation\n- Zero external dependencies for core functionality\n- Support for OpenAI, Anthropic, and local models\n- Built-in memory backends (Redis, SQLite, PostgreSQL)\n\n### 🛠️ **Developer Experience**\n- Rich CLI with interactive agent builder\n- Hot-reloading for development\n- Comprehensive debugging tools\n- Extensive examples and tutorials\n\n### 🌐 **MCP Ecosystem**\n- Automatic server generation\n- Client connection helpers\n- Protocol validation and testing\n- Community tool registry\n\n### 📚 **Documentation**\n- Comprehensive API reference\n- Architecture deep-dives\n- Production deployment guides\n- Framework comparison analysis\n\n## 🎯 Quick Preview\n\nWhile we prepare the full release, here's a taste of the AA Kit experience:\n\n```python\nfrom aakit import Agent\n\n# Create a research agent\nresearcher = Agent(\n    name=\"researcher\",\n    instruction=\"You research topics thoroughly and provide detailed analysis\",\n    model=\"gpt-4\"\n)\n\n# Create a writer that uses the researcher\nwriter = Agent(\n    name=\"writer\", \n    instruction=\"You write engaging articles based on research\",\n    model=\"claude-3\",\n    tools=[researcher]  # Composition magic\n)\n\n# Serve both as MCP servers\nresearcher.serve_mcp(port=8080)\nwriter.serve_mcp(port=8081)\n\n# Now available to the entire MCP ecosystem!\n```\n\n## 🚀 Get Notified\n\nWant to be among the first to build with AA Kit?\n\n- ⭐ **Star this repo** to get notified when we launch\n- 🐦 **Follow us** on [Twitter](https://twitter.com/aakit_ai) for updates\n- 📧 **Join our mailing list** at [aakit.dev](https://aakit.dev)\n- 💬 **Join our Discord** for early access discussions\n\n## 🤝 Early Access\n\nInterested in contributing or getting early access? We're looking for:\n\n- 🏗️ **Framework developers** familiar with agent architectures\n- 🧪 **Beta testers** building production AI systems  \n- 📝 **Technical writers** passionate about developer experience\n- 🎨 **UI/UX designers** for our developer tools\n\nReach out at [hello@aakit.dev](mailto:hello@aakit.dev)\n\n## 🌟 The Vision\n\nAA Kit represents a fundamental shift in how we think about AI agents:\n\n\u003e **Not as isolated applications, but as composable primitives that form the building blocks of intelligent systems.**\n\nEvery agent can be:\n- A standalone application\n- A tool for other agents  \n- A server in a distributed system\n- A function in a larger computation\n\nThis isn't just code—it's a new way of architecting AI.\n\n## 📄 License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n---\n\n\u003cdiv align=\"center\"\u003e\n  \u003cstrong\u003e🤖 Agent As Everything. Everything As Agent. 🤖\u003c/strong\u003e\n  \u003cbr/\u003e\u003cbr/\u003e\n  \u003cem\u003eThe future of AI is composable.\u003c/em\u003e\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosharsh%2Faa-kit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjosharsh%2Faa-kit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosharsh%2Faa-kit/lists"}