aegis
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
289 results
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI
Native local project taskboard bundle for DeepSeek Harness
Shared real browser plugin for DeepSeek Harness: install-and-use — a visible native browser the human can take over, driven by the agent over CDP. DOM-level interaction (React/Vue safe), per-task session isolation, cookie persistence (browser_auth), CAPTC
Agent-first task board for the DSH web GUI: host-authoritative task ledger with taskboard_* agent tools, project (= workspace) claim boundaries, per-task model execution in fresh sessions, optional per-task git-worktree isolation (dedicated task branches,
独立 dsh 插件:会话内初始化/接入本地王国,Territory/Binding CRUD + Task 治理闭环(Worker Claim ≠ Fact)+ Execution 生命周期 + v0.8 Persistent Governed Worker(长期 Session / Territory Affinity / Capability Gate / Execution Lease / Dispatch Evidence / Reconciliation)+ 本地 GUI 通道
Task-specific React apps for DeepSeek Harness with state carried into the next Agent turn
Run coding tasks on schedule in fresh Agent sessions, and manage automations from DeepSeek Harness Web or an Agent
Native DeepSeek Harness plugin for comparing AI Skills on the same task and choosing a winner from a local ForkProbe report.
把 DeepSeek Harness (dsh) 装进飞书/Lark 的 bot,扫码即用:dsh Web 可视化设置、流式卡片、项目工作区、并行任务、多角色 Agent、安全网守护。| Bridge DeepSeek Harness into Feishu/Lark with visual dsh Web settings, streaming cards, workspaces, parallel tasks, roles and a safety-net guardian.
把 DeepSeek Harness (dsh) 装进飞书/Lark 的 bot,扫码即用:dsh Web 可视化设置、流式卡片、项目工作区、并行任务、多角色 Agent、安全网守护。| Bridge DeepSeek Harness into Feishu/Lark with visual dsh Web settings, streaming cards, workspaces, parallel tasks, roles and a safety-net guardian.
Token-efficient assistant discipline for concise answers and task execution. Use when the user asks for direct, low-token work, or invokes this skill; includes optional file and Windows encoding utilities declared below.
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.
Live Agent Teams task, communication, subagent, and Workflow topology for DeepSeek Harness
Secure mobile gateway for DeepSeek Harness with realtime sessions, tasks, goals, commands, approvals, and file transfers
Closed-loop trajectory policy plane for DeepSeek Harness: task episodes, revision-aware verification debt, benchmark-aware stop control, adaptive effort, and scoped capability control.
Expose DeepSeek Harness agent capabilities as an MCP server, so an external MCP client (e.g. Hermes) can drive Harness to execute coding tasks. Hermes = brain, Harness = arms.
TaskPack: an open, offline task-handoff container. Task Passport is the durable state; TaskPack is the box it travels in.
在独立 DSH Session 中按计划执行编码任务,支持 Web 设置页与 Agent 双入口管理。
💗 一套给 DeepSeek Harness 的粉色 Hello Kitty 主题皮肤 + 任务完成/提问提醒插件(Sweetheart Workspace Expressive skin & Hello Kitty Task-Done Notifier)
DeepSeek Harness plugin bundle: optimize raw instructions into professional Role / Task / Context / Format prompts through the harness llm service
后台任务状态条——对话输入区上方的任务进度 UI(官方 dock 槽 + Node 轮询路由)
DSH 个人工作台:日历 + 层级任务 + AI 澄清/拆解/执行/复盘 + AI 智能排序/日报周报 + 桌面提醒
Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution — prefercmd/memory as knowledge allow/deny lists, so repeated tasks start from proven commands and save tokens