AgentDish directory
DeepSeek
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
#223
↑ +346
Alignment Whack-a-Mole
A research code repository for studying how fine-tuning can trigger verbatim recall of copyrighted books in large language models. It includes preprocessing, fine-tuning, generation, and memorization-evaluation scripts, with setup notes and example data. |
Research / Copywriting | 86 | ↑ +346 | 46 days ago | Details |
#255
↑ +101
deepclaude
A CLI proxy that lets Claude Code run against DeepSeek V4 Pro, OpenRouter, Fireworks AI, or Anthropic-compatible backends while keeping the same agent workflow. |
Developer Tools / AI Coding | 85 | ↑ +101 | 45 days ago | Details |
#458
↓ -2
DeepSeek Sparse Attention
A PyTorch reference implementation of DeepSeek Sparse Attention from the LLMs-from-scratch project, including a lightweight indexer, top-K token selection, and a GPT-style model with KV-cache support. |
Developer Tools / Machine Learning / LLM Architecture | 82 | ↓ -2 | 27 days ago | Details |
#525
↓ -1
myco
A Python-based coordination protocol and daemon for running multiple LLM sessions in parallel with shared awareness, aimed at Claude Code and other Anthropic-compatible models. |
Developer Tools / AI Dev Tooling | 80 | ↓ -1 | 29 days ago | Details |