agent-swarm-kit 1.1.12 → 1.1.13
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +4 -12
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -8,20 +8,8 @@ Unleash the power of collaborative AI with `agent-swarm-kit`! This library empow
|
|
|
8
8
|
|
|
9
9
|
|
|
10
10
|
|
|
11
|
-
---
|
|
12
|
-
|
|
13
11
|
## ✨ Why Choose Agent Swarm Kit?
|
|
14
12
|
|
|
15
|
-
- **Multi-Agent Collaboration**: Orchestrate multiple AI agents, each with unique roles—like triage, sales, or refunds—working as a team.
|
|
16
|
-
- **Lightweight & Flexible**: Unlike bulky frameworks, our API is simple and delegates prompt engineering to your team.
|
|
17
|
-
- **Framework-Agnostic**: Each agent works with any AI provider—OpenAI, Ollama, LMStudio, Claude, Grok, YandexGPT, Gemini, you name it!
|
|
18
|
-
- **Robust Validation**: Built-in checks ensure tools, agents, and outputs are always on point.
|
|
19
|
-
- **Real-Time Interaction**: Supports message scheduling and WebSocket channels for dynamic user input.
|
|
20
|
-
|
|
21
|
-
---
|
|
22
|
-
|
|
23
|
-
## 🔍 Features
|
|
24
|
-
|
|
25
13
|
- **Conversation Testbed**: Includes a unit testing framework with tool and agent override capabilities, enabling developers to simulate and validate agent interactions and tool integrations in isolated environments.
|
|
26
14
|
|
|
27
15
|
- **Model Context Protocol Ready**: Seamlessly connect agents to multiple remote MCP servers, allowing integration with external tools written in various languages (e.g., C#, Python) via the reusable Model Context Protocol, originally developed for Claude Desktop.
|
|
@@ -32,6 +20,10 @@ Unleash the power of collaborative AI with `agent-swarm-kit`! This library empow
|
|
|
32
20
|
|
|
33
21
|
- **Swarm of OpenAI, Grok, and Claude in One Chat**: An agent-agnostic framework that allows a single chat to leverage multiple AI models (e.g., OpenAI, Grok, Claude) within a swarm, providing flexibility and diversity in agent capabilities.
|
|
34
22
|
|
|
23
|
+
- **Agent Schema to Markdown**: Generates Markdown documentation from agent schemas automatically in CI/CD, keeping project managers and teams updated on agent prompts, tools, and swarm structures without manual reporting. Changes are reflected instantly, streamlining communication and project tracking.
|
|
24
|
+
|
|
25
|
+
- **Redis Storage Integration**: Persists state management, RAG (Retrieval-Augmented Generation) search data, and chat history in Redis, ensuring reliable, scalable, and high-performance storage. This enables safe and consistent access to agent states, vector search results, and conversation histories across distributed systems (Microservices).
|
|
26
|
+
|
|
35
27
|
---
|
|
36
28
|
|
|
37
29
|
## 🚀 Getting Started
|