Agent Fusion is a local RAG semantic search engine that gives AI agents instant access to your code, documentation (Markdown, Word, PDF). Query your codebase from code agents without hallucinations. Runs 100% locally, includes a lightweight embedding model, and optional multi-agent task orchestration. Deploy with a single JAR
git clone https://github.com/krokozyab/Agent-Fusion.gitAgent Fusion is a local RAG semantic search engine that gives AI agents instant access to your code, documentation (Markdown, Word, PDF). Query your codebase from code agents without hallucinations. Runs 100% locally, includes a lightweight embedding model, and optional multi-agent task orchestration. Deploy with a single JAR
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/krokozyab/Agent-FusionCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
I'm using Agent Fusion to query my [COMPANY]'s [INDUSTRY] codebase. I need to find all functions related to [DATA] processing. Please provide the results with clear explanations and code snippets. Also, suggest any potential improvements or optimizations for these functions.
# Codebase Query Results for [DATA] Processing Functions
## Function 1: `processDataStream`
```python
def processDataStream(input_stream):
# Processes incoming data stream
# Input: Data stream object
# Output: Processed data dictionary
processed_data = {}
for data in input_stream:
processed_data[data['id']] = data['value'] * 2
return processed_data
```
## Function 2: `validateDataFormat`
```python
def validateDataFormat(data):
# Validates data format according to company standards
# Input: Data dictionary
# Output: Boolean indicating validity
required_keys = ['id', 'value', 'timestamp']
return all(key in data for key in required_keys)
```
## Recommendations:
- Consider adding error handling to `processDataStream` for malformed data
- Implement logging in both functions for better debugging
- Add unit tests to validate edge casesUnlock data insights with interactive dashboards and collaborative analytics capabilities.
IronCalc is a spreadsheet engine and ecosystem
Service Management That Turns Chaos Into Control
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power