context-management

Tianshu-harness

huiliyi37

Tianshu is a terminal coding agent runtime built on the harness project (Tui X Gui), with prefix-cache engineering optimization for DeepSeek V4 (measured steady-state hit rate of 97–99% in long sessions) and deep adaptation. It breaks out of the traditional AI coding assistant's limit of treating the LLM merely as a tool, and is built on a cognitive virtual machine (CVM), a self-awareness layer and Stigmergy self-decaying memory, making the AI a development partner with independent judgment and cognitive safeguards.

dsh-mnemon

omdsh-dev

Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with three-tier memory out of the box.

billion-context-dsh

Tyan66666

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

oh-my-dsh

gulagala001

DSH memory and context enhancement plugin: layered memory, tasks and verification, context cleanup and runtime monitoring.

AgentNavi

CoaseEdge

The navigation of AI Agent.

dsh-capability-panel

pure-craft

DeepSeek Harness plugin: see what your agent can actually reach — skills, MCP servers, system tools with true in-context state, and per-session / per-preset switches

CiteCiter

kirkchinese

Verifiable, source-bound, read-only investigations for DSH responses—without interrupting the main task.

dsh-plan-lattice

1052326311

Execution-time drift firewall for long-running DeepSeek Harness agents. Real-Harness tests: unsafe stale mutations 12/12 native -> 0/12; valid controls 7/7 both; post-SIGKILL unsafe continuation 2/2 -> 0/2.

mosaic-memory-compress

TuringCorp-net

Stateless dialogue compression that mimics human memory. LLM conversations stay bounded forever — no session management, no context overflow.

dsh-dcp

chiro2001

DeepSeek Harness dynamic context management plugin (Dynamic Context Pruning for dsh), benchmarked against opencode-dcp

dsh-plugins

HYBB-rash

Personal DeepSeek Harness plugins for Telegram, scheduling, assistant responsibilities, X feeds, and UI experiments.

dsh-asc

lmst2

This repository does not provide a project description yet.

dsh-arc-context

PlxloYzb

No project description provided for this repository yet.

dsh-price-less

54shitaimzf

Context housekeeper for DeepSeek Harness: remembers “what you're doing right now” for you, automatically curating the context sent to the model — keep what should be kept, delete what should be deleted, leave uncertain items untouched, so long AI coding sessions stay on track and every token counts.

dsh-ctm

ac0033

dsh plugin: CTM context/terminal management, turning model context into a visible, editable, scorable first-class object

dsh-context-rollover

athif23

Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable notes, verbatim recent tail, no summarization

dsh-compaction-pro

helibeiqi

High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness.

dsh-context-guard

kpl0111

Token-efficient tool-result pruning for DeepSeek Harness: compact previews, targeted recall, and long-session context control.

jev-lcm-dsh-compaction

bojansandhaus

Calibrated Jev ranking before lossless context condensation

dsh-context-zip

brunhildzhou

DSH 插件：接管 DeepSeek Harness 的会话压缩，产出结构化交接摘要、可回查分段与检索工具｜A DSH plugin that takes over session compaction.

dsh-context-window

CooperZhuang

DSH 插件：复刻 Codex 最新上下文窗口管理 — token 预算提示 / 模型可调用的 new_context / 交接式换窗替代摘要压缩 | DSH plugin reimplementing Codex's context window management: token-budget notice, model-facing new_context, handoff window reset instead of summary compaction

dsh-agent-frugality

gongyijie85

Multi-agent frugality defense plugin for DeepSeek Harness: read-ledger dedup, compaction-immune rules, completion gate, cheap-review lane.

fast-compaction-dsh

kolawong

Verdict-based context compaction for DeepSeek Harness — replaces lossy LLM summaries with fast keep/truncate/drop decisions from jev-latest; everything kept stays verbatim. Port of tamaratran/fast-jev-compaction.

prime-agent-dsh

moreWax

DeepSeek Harness context sidecar for Prime Agent

dsh-memory

navid-kianfar

Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and session context in a queryable DuckDB file, with the rule set injected into every model request — plus a full management UI in the Web Client.

dsh-context-compass

NinjaSln-labs

DeepSeek Harness session health plugin: a real-data "continue vs start new" context compass — header badge / /compass / context_compass tool / multi-session overview panel

dsh-rich-context

svgop

Agent instruction manager for DSH — edit and template the AGENTS.md files the harness actually reads (global + per-workspace)

dsh-greet-signoff

weifa860504-droid

固定开场语/收尾语 + 会话预算导航条（DeepSeek Harness Web 插件）：输入框上方六格读数（占用/花费/时长/预算档/速率/到线约还有）、预算线口径与红底横幅、上下文构成明细、本机花费台账、交接摘要落盘 HANDOFF.md、场景与文案池。改完下一轮回复即生效。

dsh-sleev

xarleyn

MOVED to @yadsh/dsh-sleev in xarleyn/dsh-plugins — Sleev integration for DeepSeek Harness with route-aware LLM telemetry and context-optimization observability