A multi-agent orchestration framework with advanced memory management and Gemini/MCP tool calling.
Project description
Keepit - Meta Orchestration framework for Your Agents
Keepit is a multi-agent framework that coordinates messages between users and specialized AI agents. It uses routing orchestrators, classifiers, and tool registries to delegate tasks to agents, managing conversation state via a modular memory subsystem. It also implements Model Context Protocol (MCP) tool integration.
Installation
pip install .
Features
- Agent Management: Create, register, and manage multiple AI agents.
- Orchestration: Orchestrate conversations and tasks across multiple agents.
- Memory Tools: Integrate memory tools to maintain conversation context and history.
- MCP Client: Dynamically load tools from MCP Servers over Stdio or SSE transport.
- Streaming Responses: Support for streaming responses from agents.
- Extensibility: Easily extend the framework with new agents, tools, and orchestrators.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file keepit_ai-0.1.0.tar.gz.
File metadata
- Download URL: keepit_ai-0.1.0.tar.gz
- Upload date:
- Size: 33.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fa468b4c63eac9ca46a1245576d55cb7f8e94c18eb81f5112fbca05dccedee99
|
|
| MD5 |
f146019ddc2ba3f811f333ecfd552732
|
|
| BLAKE2b-256 |
3de215645d2f7b0ab8f62683cf683a049525f1c73eb0a514fa081d14dc162f6f
|
File details
Details for the file keepit_ai-0.1.0-py3-none-any.whl.
File metadata
- Download URL: keepit_ai-0.1.0-py3-none-any.whl
- Upload date:
- Size: 46.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a593d58286a0139c39e748270c93a44e93bac4604a8eda0f71985c121d707a64
|
|
| MD5 |
98a5aafe965b0c9ea334f9a3038bf801
|
|
| BLAKE2b-256 |
469ddef9e85346171ed4cdadf3e7cc5992dfa4290899a12705d5011794af6be6
|
