aegis
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
161 results
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
Preview, inspect, and edit real .op OpenPencil design documents inside DSH conversations — headless rendering, a read-only canvas, and a managed editor.
Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.
Task-specific React apps for DeepSeek Harness with state carried into the next Agent turn
Design I/O for coding agents: controllable UI generation via declarations (spec/domain/craft/design/components/template) and contracts (skill/evaluator). Use for product UI—console, dashboard, agent-ops, CJK-first apps.
Task-aware two-phase DeepSeek Harness preset: spec/react/weak first-request anchors (bash+read±edit/write), then the full Standard tool catalog after the first tool call.
QQ2006 skin plugin for DSH (DeepSeek Harness): visible blue-frame chrome on the live DSH 0.1.2 shell, coral-blue --dsw-alias-* / --dsw-specific-* overlay, body[data-ds-skin] mirror, zh/en locale copy, and a settings toggle (Appearance row is still the built-in trio).
Multi-Core Collaborative Novel Writing — a DeepSeek Harness (DSH) preset plugin that installs a multi-agent novel-writing mode: one conductor plus five specialized subagents (多核协同写作模式).
MCP visual manager plugin for DeepSeek Harness: inspect installed/enabled MCP servers, add/remove, enable/disable and view live connection status from the web GUI.
DSH plugin (scoped package @smanx/dsh-proxy, matching the repository): LAN reverse proxy with native Basic Auth and a settings page. Source lives in this repo's dsh-proxy/ subdirectory; this root package makes the plugin installable from the repository itself (git/github: specs install the root).
Continual self-evolution plugin for DeepSeek Harness: versioned, auditable, rollback-safe harness state (prompt notes, memories, skills, subagent specs) refined from session trajectories.
DSH (DeepSeek Harness) plugin packaging of the Project Blueprint skill — one-command AI coding conventions (AGENTS.md, docs skeleton, CI/CD, git rules, testing policy) with an autonomous discovery engine (7 languages, 15 frameworks, 70+ components, web fallback).
Visual media plugin for DeepSeek Harness: copy native image descriptions and securely normalize, inspect, and play scene-aware videos.
DSH 实时思维链锚定监控插件: we/let's/let me 指纹波段检测(spec/mixed/react) + L1温和引导/L2强制重置/L3会话重启分级干预; 左侧栏入口 + 液体毛玻璃浮层 + 变阻器式思考强度条; 独立监控进程 + JSONL 实验日志 + 离线回放/参数校准; 变阻器条可选严肃/「滑动变祖器」梗双皮肤。
Better Browser for DeepSeek Harness: drive the user's real browser through Kimi WebBridge with navigation, snapshots, interaction, screenshots, network inspection, and tab management
Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.
Browser element annotation bridge for DeepSeek Harness
四柱八字与紫微斗数排盘 Bundle for DeepSeek Harness.
Security scanner for DSH plugins: static and semantic passes over plugin source, DSH-specific attack-surface rules, npm audit, batch scanning, and an HTML report with per-finding severity and evidence.
Standalone DeepSeek Harness plugin: continual harness self-evolution. The agent persists and refines reusable prompt notes, memories, skill contracts, and subagent specs through small evidence-backed edits, with automatic refinement gates, rollback, and prompt injection.
Conversational Grafana operations for DeepSeek Harness: inspect live observability data and make safe, reviewable dashboard changes
Evidence-backed built-in capability inspector with fail-closed controls for DeepSeek Harness Web.
Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets
发现问题 → 修复交付 → 质量复查 的简单闭环插件:checkup(对抗式检查+红队验证)/ fix(根因→修复→验证)/ review(对抗式复查)三个工具,基于官方 workflow 引擎。