Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.
- GitHub stars
- 31
- License
- MIT
- Added
- 2026-08-15
GitHub info
- GitHub stars
- 31
- License
- MIT
- Primary language
- TypeScript
- Last push
- Aug 20, 2026, 4:13 PM
- Maintainer
- Tyan66666
- Added
- 2026-08-15
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
Install
dsh plugin --profile web add github:Tyan66666/billion-context-dshTags
README badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/Tyan66666/billion-context-dsh)Related plugins
Memorydsh-mnemon
★ 292Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
graph-memory
★ 582Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.
dsh-memory
★ 140Local Git-backed long-term memory for DeepSeek Harness with cited context, usage-aware read tools, safe sync, previews, and rollback.