Skip to main content

NVIDIA-NeMo/labs-OO-Agents

最近记录的来源活动
SkillsMP 收录数据更新
已收集 skills
19
GitHub 星标
2,315
GitHub Forks
318

用 AI 助手安装

复制这段 Prompt,发给你正在使用的 AI 助手。

正在加载仓库 README…

已展示 19 / 19 个已收集 Skill。

职业分类
未分类
描述

Reactive input for NOOA agents — Channel/QueueManager for queued and event-mode input, race() turn dispatch, spawn() background jobs with JobHandle, the bundled producers (monitor a shell command, cron ticks, one-shot timers, file tails), and Atom's…

原文语言:英语

更新
职业分类
未分类
描述

Let NOOA agents extend themselves — persistent skills the agent writes — code packages it hot-reloads or SKILL.md text instructions (SkillWriting / self.skill_writing, LibraryManager), in-cell helper functions and standalone @strategy sub-calls…

原文语言:英语

更新
职业分类
未分类
描述

Give a NOOA agent capabilities — methods as tools, built-in tools (ShellTools, TodoManager), MCP servers, agent skills (Skill/TextSkill/SkillRegistry), and multimodal media. Use when adding tools or external integrations to an agent, wiring MCP, or packaging…

原文语言:英语

更新
职业分类
未分类
描述

Render and refine the system prompt of a nooa agent. Use when the user wants to inspect, debug, or improve an agent's prompt, context blocks, or tool documentation.

原文语言:英语

更新
职业分类
未分类
描述

Run NOOA Connect headlessly as an agent to discover interfaces, propose model settings, check chat or native decision routes and media, and save registry aliases with the user's permission. Canonical guide for Connect stages, JSON reports, bounded checks,…

原文语言:英语

更新
职业分类
未分类
描述

Author agents with NVIDIA-labs Object Oriented Agents (NOOA). Use when writing or modifying an Agent subclass, agentic methods (ellipsis bodies), docstring prompts, structured output contracts, strategy selection (CodeAct/Predict), visibility control,…

原文语言:英语

更新
职业分类
未分类
描述

Attach images, audio, video, and PDFs to NOOA agents. Use typed parameters or CodeAct show(), configure media_inputs, and troubleshoot text-only notices, URLs, MIME types, and size limits.

原文语言:英语

更新
职业分类
未分类
描述

Understand and troubleshoot NOOA registry settings, aliases, credentials, reply budgets, reasoning levels, caching and reasoning replay. For permission and running Connect headlessly to onboard or edit models, use the nooa-connect skill.

原文语言:英语

更新
职业分类
未分类
描述

Advanced tuning of NOOA strategies — CodeAct prefill, loop guards, text-only recovery callbacks, truncation, code restrictions, execution internals, and PredictStrategy tuning. Use when configuring CodeActConfig or PredictConfig beyond defaults, handling…

原文语言:英语

更新
职业分类
未分类
描述

Solve an interactive grid game iteratively — observe, hypothesize, experiment, record knowledge, and submit action sequences until every level is won.

原文语言:英语

更新
职业分类
软件质量保证分析师与测试员
描述

Explore and debug agent execution traces. Use when the user asks to analyze a trace, debug an agent run, investigate errors in a trace, or when they paste a trace-explorer prompt from the viewer UI.

原文语言:英语

更新
职业分类
软件开发工程师
描述

Intercept and observe NOOA execution — middleware via event_manager.intercept() (guardrails, input/output transforms, blocking), event observers via event_manager.on() (react to Task/Error/LLMResponse/turn events), and the InstrumentationHooks protocol for…

原文语言:英语

更新
职业分类
软件开发工程师
描述

Manage what a NOOA agent sees and remembers — context blocks, event history and queries, history summarization, and persistent memory/storage. Use when pinning information into the system prompt, querying past events, bounding context growth in long…

原文语言:英语

更新
职业分类
其他计算机职业
描述

How to manage context blocks (system prompt sections) in NOOA. Use when configuring what appears in an agent's LLM prompt — adding, overriding, suppressing, or positioning blocks. Covers the unified Context API, well-known framework keys, and the…

原文语言:英语

更新
职业分类
软件开发工程师
描述

Make NOOA agent types render useful documentation for the LLM — doc(), spec(), hidden, Annotated field descriptions, and pformat/pprint tuning. Use when designing Pydantic models/dataclasses the LLM will see, controlling what appears in doc(self), hiding…

原文语言:英语

更新
职业分类
网络与计算机系统管理员
描述

Capture execution traces from NOOA. Use when instrumenting an agent run, writing traces to JSONL files, sending traces to the viewer or an OTLP/Langfuse/Phoenix backend, controlling which methods are traced, or when traces are mysteriously missing.

原文语言:英语

更新
职业分类
软件质量保证分析师与测试员
描述

Analyze NOOA execution traces programmatically with the trace-explorer CLI and Python API. Use when debugging why an agent run failed, inspecting LLM turns and code executions, diffing two runs, aggregating errors across an eval experiment, or root-causing…

原文语言:英语

更新
职业分类
软件开发工程师
描述

Run and use the NOOA trace viewer — the web UI + OTLP receiver for browsing agent traces and eval results. Use when starting the viewer, importing/exporting/deleting traces, querying the viewer's REST API, or wiring an agent run so traces show up at…

原文语言:英语

更新
职业分类
软件开发工程师
描述

Solve an interactive grid game by learning a compressed world model (encode state to a latent z, learn a predict function), planning action sequences by search over it, and recording hypotheses, plans and knowledge to memory.

原文语言:英语

更新
已展示 19 / 19 个已收集 Skill。