@sashabogi/argus-mcp 2.0.2 → 2.0.3
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 +14 -3
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -242,15 +242,26 @@ You can! `search_codebase` is essentially grep. But Argus also gives you:
|
|
|
242
242
|
|
|
243
243
|
## Acknowledgments
|
|
244
244
|
|
|
245
|
-
Argus combines ideas from
|
|
245
|
+
Argus combines ideas from several projects:
|
|
246
246
|
|
|
247
247
|
### Matryoshka RLM
|
|
248
248
|
|
|
249
|
-
The core analysis engine is based on [Matryoshka](https://github.com/yogthos/Matryoshka) by Dmitri Sotnikov. It introduced **Recursive Language Models** - using an LLM to generate symbolic commands that navigate large documents. This achieves 93% token savings compared to naive approaches.
|
|
249
|
+
The core analysis engine is based on [Matryoshka](https://github.com/yogthos/Matryoshka) by [Dmitri Sotnikov (yogthos)](https://github.com/yogthos). It introduced **Recursive Language Models (RLM)** - using an LLM to generate symbolic commands via the [Nucleus DSL](https://github.com/michaelwhitford/nucleus) that navigate large documents. This achieves 93% token savings compared to naive approaches.
|
|
250
|
+
|
|
251
|
+
The approach is described in the [RLM research paper](https://arxiv.org/abs/2512.24601).
|
|
250
252
|
|
|
251
253
|
### claude-mem
|
|
252
254
|
|
|
253
|
-
The progressive disclosure architecture and Claude Code integration patterns are inspired by [claude-mem](https://github.com/thedotmack/claude-mem) by thedotmack. The idea of "search first, fetch details only when needed" dramatically reduces token usage.
|
|
255
|
+
The progressive disclosure architecture and Claude Code integration patterns are inspired by [claude-mem](https://github.com/thedotmack/claude-mem) by [thedotmack](https://github.com/thedotmack). The idea of "search first, fetch details only when needed" dramatically reduces token usage.
|
|
256
|
+
|
|
257
|
+
---
|
|
258
|
+
|
|
259
|
+
## Related Projects
|
|
260
|
+
|
|
261
|
+
- [Matryoshka RLM](https://github.com/yogthos/Matryoshka) - The original RLM implementation
|
|
262
|
+
- [Nucleus DSL](https://github.com/michaelwhitford/nucleus) - Symbolic language for document operations
|
|
263
|
+
- [claude-mem](https://github.com/thedotmack/claude-mem) - Progressive disclosure patterns for Claude Code
|
|
264
|
+
- [RLM Paper](https://arxiv.org/abs/2512.24601) - Academic research on Recursive Language Models
|
|
254
265
|
|
|
255
266
|
---
|
|
256
267
|
|
package/package.json
CHANGED