返回目录

GITHUB TOPIC

context-compaction

7个项目包含此标签

7 个项目

GitHub Topic 精确匹配

Agent 与会话

Aggressive context compaction for local-first agents. Runs Qwen3.8‑27B on self‑hosted llama.cpp at low context, shrinking history so the live prompt stays small, fast, and private—delivering a big‑window experience without API cost or data egress. 面向本地的激进上下文压缩插件。自托管 llama.cpp 低上下文运行 Qwen3.8‑27B,不断收缩历史、保持常驻 prompt 小而快,兼顾隐私与大窗口体验,零 API 成本、数据不出本机。

已验证
context-compactioncordisdeepseekdeepseek-harness
Agent 与会话

dsh-clear-mind

john-walks-slow

Model-invocable context compaction for DeepSeek Harness: mind_map and clear_mind agent tools turn selected history into self-written checkpoints, with auditable GUI tombstones and proactive threshold reminders.

已验证
ai-agentcontext-compactiondeepseek-harnessdsh-plugin
文件与数据

dsh-jev-prune

yangyu666

Jev-judged context compaction for DeepSeek Harness: semantic tool-result pruning + deterministic receipt compaction

已验证
agentcontext-compactioncordisdeepseek-harness
Agent 与会话

Context Assembler DSH — DeepSeek Harness 上下文汇编插件:按话题块编排上下文,最大化每 token 互信息密度

已验证
context-assemblycontext-compactioncontext-compressiondeepseek-harness
开发工具

Persistent per-session task stack for DeepSeek Harness agents - focus_task / focus_complete / read_focus + /focus, zero prompt injection

已验证
agent-skillscontext-compactioncordisdeepseek-harness
开发工具

Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness.

已验证
context-compactioncordisdeepseek-harnessdsh
Agent 与会话

Context compression for DSH: visually configure summary and recent-context budgets (8k + 16k by default), keep tasks on track, and search full conversation history. Friendly to small-context models.

已验证
context-compactiondeepseek-harnessdsh-plugin