ZeroZen

<p align="center"> <picture> <img src="https://raw.githubusercontent.com/CelestoAI/agentor/main/assets/CelestoAI.png" alt="project logo" width="500px"/> </picture> </p> <div align="center"> [](https://pypi.org/project/agentor/) [](https://github.com/CelestoAI/agentor/actions/workflows/test.yml)  [](https://opensource.org/licenses/Apache-2.0) <a href="https://discord.gg/KNb5UkrAmm"> <img src="https://img.shields.io/static/v1?label=Chat%20on&message=Discord&color=blue&logo=Discord&style=flat-square" alt="Discord"> </a> </div> <p align="center"> Fastest way to build and deploy long-running AI agents—with durability, observability, and security. </p> <p align="center"> <a href="https://docs.celesto.ai">Docs</a> | <a href="https://github.com/CelestoAI/agentor/tree/main/examples">Examples</a> </p> ## Features | Feature | Description | Docs |---------------------------|------------------------------------------|-----------------------| | 🚀 MCP & tool security | The only **full FastAPI compatible** MCP Server with decorator API | [Link](https://docs.celesto.ai/agentor/tools/LiteMCP) | 🦾 Agent-to-agent | Multi-agent communication | [Link](https://docs.celesto.ai/agentor/agent-to-agent) | 📊 Observability | Agent tracing and monitoring | [Link](https://celesto.ai) | 💾 Durable runs | Persist, resume, and fork agent runs | [Durable runs docs](https://docs.celesto.ai/agentor) | 🔍 Tool Search API | Reduced tool context bloat | [Link](https://docs.celesto.ai/agentor/tools/tool-search) ## 🚅 Quick Start ### Installation The recommended method of installing `agentor` is with pip from PyPI. ```bash pip install agentor ``` This installs the v0.1.0 line, built on Agentor's own agent engine — durable, forkable runs included. Tools with heavy or vendor-specific dependencies ship as extras, so the base install stays small: ```bash pip install "agentor[google]" # GmailTool, CalendarTool pip install "agentor[all]" # every optional tool ``` Available extras: `google`, `exa`, `git`, `github`, `slack`, `postgres`, `scrapegraph`, `all`. <details> <summary>More ways...</summary> You can also install the latest bleeding edge version (could be unstable) of `agentor`, should you feel motivated enough, as follows: ```bash pip install git+https://github.com/celestoai/agentor@main ``` </details> ## Build and Serve an Agent Build an Agent, connect external tools or MCP Server and serve as an API in just a few lines of code: ```python from agentor.tools import GetWeatherTool from agentor import Agentor agent = Agentor( name="Weather Agent", model="gpt-5-mini", # Use any LLM provider - gemini/gemini-2.5-pro or anthropic/claude-3.5 tools=[GetWeatherTool()] ) result = agent.run("What is the weather in London?") # Run the Agent print(result) # Serve Agent with a single line of code agent.serve() ``` ### Any OpenAI-compatible provider Point `base_url` at any provider that speaks OpenAI's `/chat/completions` — OpenRouter, Groq, Together, Fireworks, DeepSeek, vLLM, Ollama, or Anthropic's and Gemini's compatible endpoints — with no extra dependency: ```python agent = Agentor( name="Assistant", model="openrouter/auto", base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"], ) ``` Run the following command to query the Agent server: ```bash curl -X 'POST' \ 'http://localhost:8000/chat' \ -H 'accept: application/json' \ -H 'Content-Type: application/json' \ -d '{ "input": "What is the weather in London?" }' ``` `agent.serve()` gives you an ordinary ASGI app, so host it wherever you already run Python services. ## Durable Runs Give the agent a store and every run becomes an append-only event log that survives process death. Resume an interrupted run, or fork any persisted run — even a completed one — into a new, independent run that keeps the full trace, the model's reasoning included when the provider returns it: ```python from agentor import Agentor from agentor.engine.store import FileStore agent = Agentor(name="Assistant", model="gpt-5-mini", store=FileStore("runs")) result = agent.run("Draft a launch plan") # persisted under result.run_id # Interrupted mid-run? agent.resume(result.run_id) picks up where it left off. fork = agent.fork(result.run_id, "Make it punchier") # fork.run_id is a new run; parent untouched ``` `fork` and `resume` have async twins, `afork` and `aresume`. ## Tracing Tracing is **off unless you ask for it**. A trace carries prompts, tool arguments, tool results, and the model's reasoning when a provider returns it — so nothing leaves your process by default. Turn it on for an agent: ```python agent = Agentor(name="Assistant", enable_tracing=True) # needs CELESTO_API_KEY ``` Or decide per run: ```python agent.run("public question") agent.run("contains customer data", tracing=False) # this run sends nothing agent.run("debug this", tracing=True) # trace just this one ``` `tracing=` is accepted by `run`, `arun`, `chat` and `stream_chat`. View traces at [celesto.ai/observe](https://celesto.ai/observe). ## Agent Skills Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks. Agent Skills help agents pull just the right context from simple Markdown files. The agent first sees only a skill’s name and short description. When the task matches, it loads the rest of `SKILL.md`, follows the steps, and can call a shell environment to run the commands the skill points to. - **Starts light**: discover skills by name/description only - **Loads on demand**: pull full instructions from `SKILL.md` when relevant - **Executes safely**: run skill-driven commands in an isolated shell Skill layout example: ``` example-skill/ ├── SKILL.md # required instructions + metadata ├── scripts/ # optional helpers the agent can call ├── assets/ # optional templates/resources └── references/ # optional docs or checklists ``` Using a skill to create a GIF: ```python from agentor.tools import ShellTool from agentor import Agentor agent = Agentor( name="Assistant", model="gemini/gemini-3-flash-preview", instructions="Your job is to create GIFs. Lean on the shell tool and any available skills.", skills=[".skills/slack-gif-creator"], tools=[ShellTool()], ) async for chunk in await agent.chat("produce a cat gif", stream=True): print(chunk) ``` ## Create an Agent from Markdown Bootstrap an Agent directly from a markdown file with metadata for name, tools, model, and temperature: ```markdown --- name: WeatherBot tools: [get_weather] model: gpt-4o-mini temperature: 0.3 --- You are a concise weather assistant. ``` Load it with: ```python from agentor import Agentor agent = Agentor.from_md("agent.md") result = agent.run("Weather in Paris?") ``` ## Build a custom MCP Server with LiteMCP Agentor enables you to build a custom [MCP Server](https://modelcontextprotocol.io) using LiteMCP. You can run it inside a FastAPI application or as a standalone MCP server. ```python from agentor.mcp import LiteMCP, get_token mcp = LiteMCP(name="my-server", version="1.0.0") @mcp.tool(description="Get weather for a given location") def get_weather(location: str) -> str: # *********** Control authentication *********** token = get_token() if token != "SOME_SECRET": return "Not authorized" return f"Weather in {location}: Sunny, 72°F" mcp.serve() ``` ### LiteMCP vs FastMCP **Key Difference:** LiteMCP is a native ASGI app that integrates directly with FastAPI using standard patterns. FastMCP requires mounting as a sub-application, diverging from standard FastAPI primitives. | Feature | LiteMCP | FastMCP | |---------|---------|---------| | Integration | Native ASGI | Requires mounting | | FastAPI Patterns | ✅ Standard | ⚠️ Diverges | | Built-in CORS | ✅ | ❌ | | Custom Methods | ✅ Full | ⚠️ Limited | | With Existing Backend | ✅ Easy | ⚠️ Complex | 📖 [Learn more](https://docs.celesto.ai/agentor/tools/LiteMCP) ## Agent-to-Agent (A2A) Protocol The A2A Protocol defines standard specifications for agent communication and message formatting, enabling seamless interoperability between different AI agents. **Key Features:** - **Standard Communication**: JSON-RPC based messaging with support for both streaming and non-streaming responses - **Agent Discovery**: Automatic agent card generation at `/.well-known/agent-card.json` describing agent capabilities, skills, and endpoints - **Rich Interactions**: Built-in support for tasks, status updates, and artifact sharing between agents Agentor makes it easy to serve any agent as an A2A protocol. ```python from agentor import Agentor agent = Agentor( name="Weather Agent", model="gpt-5-mini", tools=["get_weather"], ) # Serve agent with A2A protocol enabled automatically agent.serve(port=8000) # Agent card available at: http://localhost:8000/.well-known/agent-card.json ``` Any agent served with `agent.serve()` automatically becomes A2A-compatible with standardized endpoints for message sending, streaming, and task management. 📖 [Learn more](https://docs.celesto.ai/agentor/agent-to-agent) ## 🤝 Contributing We'd love your help making Agentor even better! Please read our [Contributing Guidelines](.github/CONTRIBUTING.md) and [Code of Conduct](.github/CODE_OF_CONDUCT.md). ## 📄 License Apache 2.0 License - see [LICENSE](LICENSE) for details. --- <div align="center"> Built with 🧡 in London by <a href="https://celesto.ai">Celesto AI</a> </div>