context-blocks
Skill2.3k starsChanged 4 months agoLicence not identifiedView on GitHub
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 declarative/runtime interface.
Trending
Less talk lately.about the whole repository
Who's talking about NVIDIA-NeMo/labs-OO-Agents
- A Hacker News story“Nvidia Object-Oriented Agents: An agent is a Python class”Hacker News · Jul 27, 2026 · 4 points
- A Hacker News story“NVIDIA-labs OO Agents: Native Python Object-Oriented Agents”Hacker News · Jul 30, 2026 · 3 points
- A Hacker News story“Nvidia-Labs Object Oriented Agents”Hacker News · Aug 31, 2026 · 2 points
- A Hacker News story“NOOA – Nvidia-Labs Object Oriented Agents”Hacker News · Aug 26, 2026 · 2 points
- Frantz103/agent-os-opensource“Bump the python-dependencies group across 1 directory with 12 updates”GitHub · Nov 2, 2026
The biggest 5 of 25 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 25
Talked about on GitHub, Hacker News and Bluesky (25 times).
On GitHub · 20
- Nov 2, 2026Bump the python-dependencies group across 1 directory with 12 updates — Frantz103/agent-os-opensource0 reactions
- Oct 9, 2026Production-gated NVIDIA NOOA integration with generated-code isolation — kiongahq/agent-runtime0 reactions
- Oct 5, 2026Bump the python-dependencies group across 1 directory with 11 updates — Frantz103/agent-os-opensource0 reactions · 1 comment
- Sep 14, 2026Bump the python-dependencies group across 1 directory with 7 updates — Frantz103/agent-os-opensource0 reactions · 1 comment
- Sep 7, 2026Bump the python-dependencies group across 1 directory with 6 updates — Frantz103/agent-os-opensource0 reactions · 1 comment
15 more on GitHub
- Aug 31, 2026Bump the python-dependencies group across 1 directory with 5 updates — Frantz103/agent-os-opensource0 reactions · 1 comment
- Aug 30, 2026Bump the python-dependencies group across 1 directory with 4 updates — Frantz103/agent-os-opensource0 reactions · 1 comment
- Aug 29, 2026harness(compute): preflight and attest the effective isolated-Python workspace capability — timwhitez/avo-pi-agent0 reactions · 3 comments
- Aug 29, 2026harness(action): add bounded action batches with terminal-aware tail cancellation — timwhitez/avo-pi-agent0 reactions · 2 comments
- Aug 29, 2026harness(observation): replace repeated full-grid dumps with typed references, useful deltas, and on-demand views — timwhitez/avo-pi-agent0 reactions · 3 comments
- Aug 24, 2026Bump the python-dependencies group across 1 directory with 3 updates — Frantz103/agent-os-opensource0 reactions · 1 comment
- Aug 10, 2026epic(ai): the agent harness -- vision, prior art, and the plan to stand behind "or the agent harness itself" — routecraftjs/routecraft0 reactions · 4 comments
- Aug 9, 2026Issue 7 — [NOOA-7] 建立 eduHarness Harness Capability Conformance Test 與 Evaluation Matrix — bai-collab/eduHarness-0 reactions · 2 comments
- Aug 9, 2026Issue 6 — [NOOA-6] 建立 Host Capability Manifest 與 Adapter Layer,明確區分 eduHarness 與 Code-as-Action Runtime — bai-collab/eduHarness-0 reactions · 2 comments
- Aug 9, 2026Issue 4 — [NOOA-4] 建立 Explicit Task State,將執行狀態從聊天歷史中分離 — bai-collab/eduHarness-0 reactions · 2 comments
- Aug 9, 2026Issue 1 — [NOOA-1] 為 Skill 新增 Machine-Readable Typed I/O Contract — bai-collab/eduHarness-0 reactions · 2 comments
- Jul 28, 2026Add NVIDIA NOOA to simulation testbeds — natnew/Awesome-Multi-Agent-AI-Safety0 reactions
- Jul 27, 2026feat(experimentalist): add the tau3-bench banking benchmark suite — NVIDIA-NeMo/nemo-helixsays it tested it0 reactions · 2 comments
- Jul 26, 2026Add NOOA submission for ARC-AGI-3 — arcprize/ARC-AGI-Community-Leaderboard0 reactions · 1 comment
- Jul 24, 2026NVIDIA-labs OO Agents: Native Python Object-Oriented Agents — remyxai/outrider0 reactions
On Hacker News · 4
- Jul 27, 2026Nvidia Object-Oriented Agents: An agent is a Python class4 points
- Jul 30, 2026NVIDIA-labs OO Agents: Native Python Object-Oriented Agents3 points
- Aug 31, 2026Nvidia-Labs Object Oriented Agents2 points
- Aug 26, 2026NOOA – Nvidia-Labs Object Oriented Agents2 points
On Bluesky · 1
- Aug 12, 2026公式READMEを読むと、状態・プロンプト・型・操作をPythonクラスへ寄せる設計。`...` のメソッドだけがLLMループになり、通常のメソッドは決定的なPythonのままです。 特に、ツール結果を文字列で毎回詰め直さず、ライブオブジェクトを参照で渡す部分はかなり筋がいい!… — @mint-echosphere.bsky.social0 likes and reposts · 1 reply
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- nooa-agent-authoringSkill
- nooa-agentdocSkill
- nooa-capturing-tracesSkill
- nooa-channelsSkill
- nooa-codeact-advancedSkill
- nooa-connectSkill
- nooa-context-and-stateSkill
- nooa-mediaSkill
- nooa-middleware-hooksSkill
- nooa-model-configurationSkill
- nooa-self-extendingSkill
- nooa-tools-and-skillsSkill
- nooa-trace-explorerSkill
- nooa-trace-viewerSkill
- refine-agent-promptSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

