返回目录

GITHUB TOPIC

token-optimization

7个项目包含此标签

7 个项目

GitHub Topic 精确匹配

Agent 与会话

Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.

已验证
agentagent-memoryagent-middlewareawesome-list
Agent 与会话

Context folding for DeepSeek Harness (DSH): wrap work in named tasks, fold finished spans into short summaries, recall originals on demand.

已验证
agent-memoryai-agentscoding-agentcompaction
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

dsh-dcp

chiro2001

DeepSeek Harness 动态上下文管理插件(Dynamic Context Pruning for dsh),对标 opencode-dcp

已验证
context-managementcontext-pruningdeepseekdeepseek-harness
Agent 与会话

context-guardian

LuminariSoftwares

Compaction for local models that actually fires and never bricks the session. OpenAI-compatible proxy + DeepSeek Harness engine.

已验证
ai-agentsai-toolcoding-assistantcompaction
安全与治理

tool-guardian

LuminariSoftwares

Your MCP servers for ~300 tokens instead of ~28,000. MCP server + native DeepSeek Harness bundle.

已验证
ai-agentsai-toolcoding-assistantcontext-management
开发工具

One MCP tool instead of every schema you own — a lazy capability broker that cuts resident tool context by a measured 94.4%. Search, inspect, enable and call MCP servers and skills on demand.

已验证
ai-agentsbenchmarkcontext-windowdeepseek