dsh-layered-memory
L0~L3 分层蒸馏记忆插件 for DeepSeek Harness:自动捕获对话(L0)、抽取原子记忆(L1)、整合场景块(L2)、蒸馏核心画像/团队方法论(L3),并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。
15 results
L0~L3 分层蒸馏记忆插件 for DeepSeek Harness:自动捕获对话(L0)、抽取原子记忆(L1)、整合场景块(L2)、蒸馏核心画像/团队方法论(L3),并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。
Reduce large agent tool output by what it means, not by where it was cut.
Native continuity recovery for long-running DeepSeek Harness agents
Structural code MCP server and batch CLI for compact TypeScript/JavaScript reads and hash-bound AST edits.
Adaptive Context Plane core bundle: Evidence Ledger + Governance + Context Composer + User Model (explicit)
X-ray for your DeepSeek Harness — diagnostics for what's actually loaded, why, and what it costs: per-plugin context-tax attribution, per-request token ledger, skill catalog pricing, dependency cascades.
Content-aware tool output compression for DeepSeek Harness.
Cut MCP context and API cost in DeepSeek Harness with two model-facing tools, lazy discovery, and exact-schema calls
Evidence-backed working memory for DeepSeek Harness: a cited ledger of what already worked in this workspace, built from the session log you already have
上下文工程:按层级(规则文件→规格→源码→错误输出→对话历史)主动策划 agent 看到的信息,提升输出质量。受 addyosmani/agent-skills(88k★ MIT)启发。
Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section
DSH 上下文管理插件:任务边界、项目帧、自动判别与上下文优化(开发中,R2 判别域 P8–P14b1 已施工)
Tiered micro-clear layer for DeepSeek Harness compaction: clears whitelisted re-runnable tool results to placeholders before the official summarization tier, freeing context with no model call.
Local-first continuity plugin for Codex and DeepSeek Harness that preserves source-aware task invariants across lossy context transitions.
Memory plugin with built-in governance for DeepSeek Harness