You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+37-13Lines changed: 37 additions & 13 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,32 +1,45 @@
1
1
<divstyle="text-align: center;">
2
2
3
3

4
+
4
5
# Agentic Starter Kits
5
6
6
7
</div>
7
8
8
9
## Purpose
9
-
Production-ready agent templates to build and deploy LLM-powered agents. Run locally (e.g. with Ollama/Llama Stack) or deploy to Red Hat OpenShift. Each agent has step-by-step docs.
10
+
11
+
Production-ready agent templates to build and deploy LLM-powered agents. Run locally (e.g. with Ollama/Llama Stack) or
12
+
deploy to Red Hat OpenShift. Each agent has step-by-step docs.
10
13
11
14
## Agents
15
+
12
16
Choose an agent and follow its README for setup and deployment:
13
17
14
-
-**[LangGraph ReAct](./agents/base/langgraph_react_agent/README.md)** – General-purpose agent using a ReAct loop: it reasons and calls tools (e.g. search, math) step by step. Built with LangGraph and LangChain.
15
-
-**[LlamaIndex WebSearch](./agents/base/llamaindex_websearch_agent/README.md)** – Agent built on LlamaIndex that uses a web search tool to query the internet and use the results in its answers.
16
-
-**[OpenAI Responses](./agents/base/openai_responses_agent/README.md)** – Minimal agent with no framework: only the OpenAI Python client and an Action/Observation loop with tools. Use with OpenAI or any compatible API.
17
-
-**[LangGraph Agentic RAG](./agents/community/langgraph_agentic_rag/README.md)** – RAG agent that indexes documents in a vector store (Milvus) and retrieves relevant chunks to augment the LLM’s answers with your own data.
18
-
-**[LangGraph ReAct with Database Memory](./agents/community/langgraph_react_with_database_memory/README.md)** – ReAct agent with PostgreSQL-backed conversation memory. Full chat history is persisted in the database while a FIFO sliding window keeps only the last N messages in the LLM context. Built with LangGraph and `create_agent` middleware.
18
+
-**[LangGraph ReAct](./agents/base/langgraph_react_agent/README.md)** – General-purpose agent using a ReAct loop: it
19
+
reasons and calls tools (e.g. search, math) step by step. Built with LangGraph and LangChain.
20
+
-**[LlamaIndex WebSearch](./agents/base/llamaindex_websearch_agent/README.md)** – Agent built on LlamaIndex that uses a
21
+
web search tool to query the internet and use the results in its answers.
22
+
-**[OpenAI Responses](./agents/base/openai_responses_agent/README.md)** – Minimal agent with no framework: only the
23
+
OpenAI Python client and an Action/Observation loop with tools. Use with OpenAI or any compatible API.
24
+
-**[LangGraph Agentic RAG](./agents/community/langgraph_agentic_rag/README.md)** – RAG agent that indexes documents in
25
+
a vector store (Milvus) and retrieves relevant chunks to augment the LLM’s answers with your own data.
26
+
-**[LangGraph ReAct with Database Memory](./agents/community/langgraph_react_with_database_memory/README.md)** – ReAct
27
+
agent with PostgreSQL-backed conversation memory. Full chat history is persisted in the database while a FIFO sliding
28
+
window keeps only the last N messages in the LLM context. Built with LangGraph and `create_agent` middleware.
19
29
20
30
## Deployment Options
31
+
21
32
Agents in this repository can support two deployment modes:
22
33
23
34
### 🖥️ Local Development
35
+
24
36
- Run agents on your local machine
25
37
- Use Llama Stack server with Ollama for model serving
26
38
- Ideal for development, testing, and experimentation
27
39
- No cloud infrastructure required
28
40
29
41
### ☁️ Production Deployment
42
+
30
43
- Deploy agents to Red Hat OpenShift Cluster
31
44
- Containerized deployment with Kubernetes
32
45
- Production-grade scaling and monitoring
@@ -52,41 +65,52 @@ Agentic-Starter-Kits/
52
65
---
53
66
54
67
## How to Use This Repository
68
+
55
69
1.**Start Here**: Read this README to understand the overall structure and install core dependencies
56
70
2.**Choose an Agent**: Select an agent from the `agents/` directory based on your use case
57
71
3.**Follow Agent README**: Navigate to the agent's directory and follow its specific README for:
58
-
- Agent-specific dependencies installation
59
-
- Configuration and setup
60
-
- Local development or OpenShift deployment
61
-
- Usage examples and API endpoints
62
-
72
+
- Agent-specific dependencies installation
73
+
- Configuration and setup
74
+
- Local development or OpenShift deployment
75
+
- Usage examples and API endpoints
63
76
64
77
### Pre-requisitions to run that repo
78
+
65
79
Run this script to set up repo stuff with a use of [UV](https://docs.astral.sh/uv/) and python 3.12
0 commit comments