Back to catalog

GITHUB TOPIC

context-engineering

35projects include this topic

The "context-engineering" topic on GitHub groups 35 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by book-to-skill with 30.1k GitHub stars. book-to-skill — Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.

{count} projects

Exact GitHub Topic match

DSH PluginsSkill

book-to-skill

virgiliojr94

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

Structure check pending
agent-skillsai-agentsbook-to-skillcontext-engineering
DSH PluginsSkill

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.

Structure check pending
agent-skillsautonomous-agentsclaudeclaude-code
DSH PluginsSkill

Vibe-Skills

foryourhealth111-pixel

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

Structure check pending
agent-frameworkagent-skillsagentic-codingai-agents
DSH PluginsSkill

An open-source method and skill set created at Google for spec-driven development with LLMs

Structure check pending
agent-skillsai-agentsantigravityclaude-code
Agents & sessionsPlugin

memory-eternal

EternalNight996

Your AI forgets every session. Give it a memory it can trust: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor and any MCP client, with an immutable audit log and a token ledger. Open source, self-hosted, no cloud.

Structure check pending
agent-memoryai-memoryaudit-logclaude-code
Agents & sessionsPlugin

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

Structure check pending
agent-harnessagent-memoryai-agentai-tools
Agents & sessionsPlugin

dsh-engram

kenz1117

Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, provenance audit, SM-2 review. Zero external services, zero API keys.

Structure check pending
agentagent-memoryawesome-dsh-plugincontext-engineering
InterfaceSkill

hedgehog

skyf0xx

HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven, BMAD-METHOD plan, so Claude Code, Cursor & Gemini CLI stay locked to it. A CLI-enforced state machine for agentic coding. Now builds DeepSeek DSH Plugins. DeepSeek Harness, DSH Plugin, AI coding, BMAD method. AI Copywriting

Structure check pending
agent-skillsagentic-codingai-agentsai-assisted-development
Agents & sessionsSkill

Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.

Structure check pending
agent-handoffagent-skillsclaude-codecodex
Development toolsPlugin

toolshrink

unclecode

Cut large agent tool output by what it means, not by where it was cut. 13 content-aware reducers + DeepSeek Harness plugin.

Structure check pending
ai-agentsclaude-codecontext-engineeringdeepseek-harness
Agents & sessionsPlugin

Give DeepSeek Harness cross-session long-term memory: the AI automatically remembers who you are, your projects and preferences, new sessions come with the background, personal and work memories are automatically kept separate without interfering, zero-config and seamless | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.

Structure check pending
agent-memoryai-agentcontext-engineeringcordis-plugin
Agents & sessionsPlugin

AgentNavi

CoaseEdge

The navigation of AI Agent.

Structure check pending
agent-memoryai-agentclaude-codecodex
OperationsPlugin

dsh-fast

PerryLink

Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.

Structure check pending
context-engineeringcordisdeepseekdeepseek-harness
Models & MCPPlugin

dsh-mcp-lens

labmimors

DeepSeek Harness MCP tool search for large catalogs: 1,000 MCP tools behind 2 MCP-facing schemas, exact-schema calls, allow/deny controls, and a local calculator.

Structure check pending
agent-harnesscontext-engineeringcontext-optimizationcontext-reduction
Development toolsSkill

One set of instructions, skills, and reference docs for coding agents, shared by Claude Code, Codex, Gemini CLI, Cursor, and dsh (DeepSeek Harness). Every rule cites its source.

Structure check pending
agent-skillsagentsagentsmdai
Development toolsPlugin

dsh-graft-plugin

adithyanraj03

A DeepSeek Harness plugin that puts graft — a prebuilt graph of every symbol, its file:line span, and who calls what — in front of both you and the model.

Structure check pending
ai-agentscode-graphcode-indexingcode-intelligence
Agents & sessionsPlugin

Long-term memory plugin for DeepSeek Harness (DSH): layered memory library + session distillation + deep-sleep consolidation + settings panel. Memory-keeper plugin.

Structure check pending
agentagent-memoryai-assistantai-memory
Agents & sessionsSkill

Baton

kakadeka

Pass your project, not your context.

Structure check pending
ai-agentsai-memoryclaude-codeclaude-skills
Agents & sessionsPlugin

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.

Structure check pending
agent-harnessagent-orchestrationagent-planningagent-safety
Files & dataSkill

Memory and token-optimization plugin toolkit for DeepSeek Harness: cross-session knowledge graph memory + five-layer token-saving orchestration.

Structure check pending
agent-memoryagent-skillai-agentscontext-engineering
Agents & sessionsPlugin

rcs-context

ScreamingMaggot

DeepSeek Harness (DSH) 插件包:把工具输出与模型回复折叠成可展开的摘要,把会话事实沉淀成带证据的外部记忆。实测 12 个长会话把 50 MB 上下文压到 0.96 MB(52×),上下文占用中位 7.8%。兼容 DSH 0.1.5-rc.2 ~ 0.2.2-rc.2;已发布 npm 包 rcs-context:dsh plugin --profile web add rcs-context。

Structure check pending
agent-memoryauditabilitycontext-compressioncontext-engineering
Development toolsPlugin

Flagship repo for frontline AI engineering methodology: philosophy/methods/five engineering pillars/governance/sessions/boilerplates (73 assets)|AI engineering methodology: context, prompt, harness, graph & loop engineering templates (DSH-compatible)

Structure check pending
ai-agentai-agentsai-engineeringai-engineering-methodology
Agents & sessionsPlugin

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.

Structure check pending
ai-agentcoding-agentcontext-engineeringcontext-management
Development toolsSkill

superstack

debabsah

A full engineering bench for your coding agent: the work survives any session, and every done comes with proof. Runs on Claude Code, Codex CLI, Copilot CLI, Kiro CLI, and DeepSeek Harness.

Structure check pending
agent-memoryagent-skillsagentic-aiai-agents
Agents & sessionsPlugin

dsh-precedent

dshplugin-me

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. No index, no model, no capture step.

Structure check pending
agent-memorycontext-engineeringdeepseek-harnessdsh-plugin
Agents & sessionsPlugin

Markdown folder long-term memory plugin for DeepSeek Harness (dsh): one file per fact, human-editable, git-versionable

Structure check pending
context-engineeringdeepseek-harnessdsh-pluginmemory
Models & MCPSkill

🔥 Cut 91% of tokens, lose zero capability | 省 91% token · 能力零损失 — Scope DSH skill catalogs & MCP tool schemas per workspace. Measured: 36,870 → 11,658 tokens/step (−68%). Nothing deleted. | 按工作区裁剪技能目录与工具 schema,每步降 68%,一个字都不删。📮 wow.vip@foxmail.com

Structure check pending
agent-skillsai-agentsclaude-skillscontext-engineering
Development toolsPlugin

DSH (DeepSeek Harness) plugin: append one convergence line to every user message and inject it every N steps — both switchable, adjustable from the Settings page · 每条用户消息末尾追加一句收敛提示,并每 N 步注入一次,两项均可在设置页开关

Structure check pending
agent-loopai-agentcontext-engineeringcordis
Models & MCPPlugin

dsh-mcp-lens

Andrietteprotective835

Shrink massive MCP catalogs to two tools, letting DeepSeek Harness search and call 1,000+ remote APIs efficiently.

Structure check pending
ai-toolingcontext-engineeringcontext-optimizationcontext-reduction
Agents & sessionsPlugin

Token-saving interceptor for DSH tool calls: dedupe cache, executable decision graph, live session state, honest ledger.

Structure check pending
agentai-agentscontext-engineeringcordis
Agents & sessionsPlugin

oh-my-clm

DevZjQx

Pi 扩展 + DSH bridge:把当前上下文镜像成普通文件,由模型自己删除 stale block。灵感来自 Facebook Research 的 CLM harness。

Structure check pending
clmcontext-engineeringcontext-managementdeepseek-harness
Agents & sessionsPlugin

dsh-memory

jiachenleo9-create

DSH 四层自动记忆系统:会话开始自动读取记忆、长任务目标锚定防遗忘、每轮结束自动沉淀、跨工作区审计。纯 Markdown、零依赖、可审计。

Structure check pending
agent-memoryai-agentcontext-engineeringdeepseek-harness
DSH PluginsPlugin

在 DSH agent 回答之前,把「你可能已经忘了」的东西重新摆到它眼前。零第三方依赖;判断全部由可核对的规则完成,不做生成式推理(语义那几段用本机 bge-m3 算向量)。

Structure check pending
agentai-agentscontext-engineeringcordis
DSH PluginsPlugin

dsh-summary-index

TLNing260310

Non-invasive structured compaction index, deterministic anchor guard, and probe tools for DeepSeek Harness (DSH). AI-assisted alpha/demo.

Structure check pending
ai-agentcompactioncontext-engineeringdeepseek-harness
InterfacePlugin

dsh-rtk

wings1848

RTK command rewriting and tool-output compaction for the DeepSeek Harness: rewrites bash commands to their rtk equivalents and compacts the result before the model sees it.

Structure check pending
coding-agentcontext-engineeringdeepseek-harnessdsh-plugin