# Home
## Hive Agent Framework
**Open-source framework for building, deploying, and serving powerful agentic workflows at scale.**The Hive Agent Framework makes it easy to build scalable agent-based workflows with your model of choice. The framework is Hiven designed to perform robustly with [IBM Granite](https://www.ibm.com/granite/docs/) and [Llama 3.x](https://ai.meta.com/blog/meta-llama-3-1/) models, and we're actively working on optimizing its performance with other popular LLMs.\
\
Our goal is to empower developers to adopt the latest open-source and proprietary models with minimal changes to their current agent implementation.
### Key Features
* π€ **AI agents**: Use our powerful Hive agent refined for Llama 3.1 and Granite 3.0, or build your own.
* π οΈ **Tools**: Use our built-in tools or create your own in Javascript/Python.
* π©βπ» **Code interpreter**: Run code safely in a sandbox container.
* πΎ **Memory**: Multiple strategies to optimize token spend.
* βΈοΈ **Serialization** Handle complex agentic workflows and easily pause/resume them without losing state.
* π **Instrumentation**: Use Instrumentation based on Emitter to have full visibility of your agentβs inner workings.
* ποΈ **Production-level** control with caching and error handling.
* π **API**: Integrate your agents using an OpenAI-compatible Assistants API and Python SDK.
* π₯οΈ **Chat UI**: Serve your agent to users in a delightful UI with built-in transparency, explainability, and user controls.
### Getting started
#### Installation
```shell
npm install Hive-agent-framework
```
or
```shell
yarn add Hive-agent-framework
```
#### Example
```ts
import { HiveAgent } from "Hive-agent-framework/agents/Hive/agent";
import { OllamaChatLLM } from "Hive-agent-framework/adapters/ollama/chat";
import { TokenMemory } from "Hive-agent-framework/memory/tokenMemory";
import { DuckDuckGoSearchTool } from "Hive-agent-framework/tools/search/duckDuckGoSearch";
import { OpenMeteoTool } from "Hive-agent-framework/tools/weather/openMeteo";
const llm = new OllamaChatLLM(); // default is llama3.1 (8B), it is recommended to use 70B model
const agent = new HiveAgent({
llm, // for more explore 'Hive-agent-framework/adapters'
memory: new TokenMemory({ llm }), // for more explore 'Hive-agent-framework/memory'
tools: [new DuckDuckGoSearchTool(), new OpenMeteoTool()], // for more explore 'Hive-agent-framework/tools'
});
const response = await agent
.run({ prompt: "What's the current weather in Las Vegas?" })
.observe((emitter) => {
emitter.on("update", async ({ data, update, meta }) => {
console.log(`Agent (${update.key}) π€ : `, update.value);
});
});
console.log(`Agent π€ : `, response.result.text);
```
β‘οΈ See a more advanced example.
β‘οΈ you can run this example after local installation, using the command `yarn start examples/agents/simple.ts`
#### Local Installation
1. Clone the repository `git clone git@github.com:i-am-Hive/Hive-agent-framework`.
2. Install dependencies `yarn install --immutable && yarn prepare`.
3. Create `.env` (from `.env.template`) and fill in missing values (if any).
4. Start the agent `yarn run start:Hive` (it runs `/examples/agents/Hive.ts` file).
β‘οΈ All examples can be found in the examples directory.
β‘οΈ To run an arbitrary example, use the following command `yarn start examples/agents/Hive.ts` (just pass the appropriate path to the desired example).
#### π¦ Modules
The source directory (`src`) provides numerous modules that one can use.
| Name | Description |
| -------------- | ------------------------------------------------------------------------------------------- |
| **agents** | Base classes defining the common interface for agent. |
| **llms** | Base classes defining the common interface for text inference (standard or chat). |
| **template** | Prompt Templating system based on `Mustache` with various improvements. |
| **memory** | Various types of memories to use with agent. |
| **tools** | Tools that an agent can use. |
| **cache** | Preset of different caching approaches that can be used together with tools. |
| **errors** | Error classes and helpers to catch errors fast. |
| **adapters** | Concrete implementations of given modules for different environments. |
| **logger** | Core component for logging all actions within the framework. |
| **serializer** | Core component for the ability to serialize/deserialize modules into the serialized format. |
| **version** | Constants representing the framework (e.g., latest version) |
| **emitter** | Bringing visibility to the system by emitting events. |
| **internals** | Modules used by other modules within the framework. |
To see more in-depth explanation see overview.
### Roadmap
* Hive agent performance optimization with additional models
* Examples, tutorials, and docs
* Improvements to building custom agents
* Multi-agent orchestration
[](https://github.com/i-am-Hive/Hive-agent-framework/graphs/contributors)
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://hive-4.gitbook.io/hive/home.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
