46 lines
1.4 KiB
Markdown
46 lines
1.4 KiB
Markdown
# AGENTS.md
|
|
|
|
**Last Updated:** April 9, 2026
|
|
|
|
## Research/Analysis Folder for forgecode
|
|
|
|
This is the research and analysis folder for the **forgecode** coding harness.
|
|
|
|
### Folder Structure
|
|
|
|
```
|
|
forgecode/
|
|
repo/ - antinomyhq/forgecode source code
|
|
feedback/
|
|
localllm/ - Community feedback and performance data for local models
|
|
frontier/ - Community feedback and performance data for frontier models
|
|
```
|
|
|
|
### What's Inside
|
|
|
|
- **repo/**: The forgecode repository (AI pair programmer with sub-agents)
|
|
- **feedback/localllm/**: Feedback, benchmark results, and observations from using forgecode with smaller/local LLMs
|
|
- **feedback/frontier/**: Feedback, benchmark results, and observations from using forgecode with frontier models
|
|
|
|
### Feedback Format
|
|
|
|
Each feedback file should include:
|
|
- Model used (name, size, provider)
|
|
- Benchmark results or task performance
|
|
- Issues encountered
|
|
- What worked well
|
|
- **Source reference**: URL or site where the feedback came from (community posts, Discord, GitHub issues, etc.)
|
|
|
|
### Research Focus
|
|
|
|
This folder collects data on:
|
|
- Tool handling and capabilities
|
|
- Skills system effectiveness
|
|
- Prompt engineering strategies
|
|
- Context management
|
|
- Performance on benchmarks (terminal-bench, etc.)
|
|
|
|
### Goal
|
|
|
|
Extract best practices specifically for smaller/local models and document what works vs. what doesn't for the forgecode harness.
|