Skip to main content

Discord-facing knowledge fetch & index agent for the Jetson AI Lab community — fetches and indexes Jetson AI Lab docs/sources and answers members' questions on Discord.

Project description

jetson-ai-lab-cli

Discord-facing knowledge fetch & index agent for the Jetson AI Lab community — fetches and indexes Jetson AI Lab docs/sources and answers members' questions on Discord.

Status: the read side is real, the rest is still scaffold. The agent can scan the Jetson AI Lab Discord read-only today (see below); indexing what it reads and answering members' questions are not built yet.

What you get

  • A read-only Jetson AI Lab Discord scanner — the jetson-discord-scan skill, the first slice of the agent's actual job. See Jetson AI Lab Discord.
  • An agent-first CLI cited from teken (afi-cli) — the runtime package has no third-party dependencies.
  • A mesh identityculture.yaml (suffix + backend) and the matching prompt file (CLAUDE.md for backend: claude).
  • The canonical guildmaster skill kit (11 skills) under .claude/skills/, vendored cite-don't-import. See docs/skill-sources.md.
  • A build + deploy baseline — pytest, lint, the agent-first rubric gate, and PyPI Trusted Publishing wired into GitHub Actions.

Quickstart

uv sync
uv run pytest -n auto                 # run the test suite
uv run jetson-ai-lab-cli whoami  # identity from culture.yaml
uv run jetson-ai-lab-cli learn   # self-teaching prompt (add --json)
uv run teken cli doctor . --strict    # the agent-first rubric gate CI runs

CLI

Verb What it does
whoami Report this agent's nick, version, backend, and model from culture.yaml.
learn Print a structured self-teaching prompt.
explain <path> Markdown docs for any noun/verb path.
overview Read-only descriptive snapshot of the agent.
doctor Check the agent-identity invariants (prompt-file-present, backend-consistency).
cli overview Describe the CLI surface itself.

Every command supports --json. Results go to stdout, errors/diagnostics to stderr (never mixed). Exit codes: 0 success, 1 user error, 2 environment error, 3+ reserved.

Jetson AI Lab Discord (read-only)

The agent's intended job starts at the Jetson AI Lab Research Group Discord — a hands-on community running modern AI on NVIDIA edge hardware. At a glance:

Concept map of the Jetson AI Lab Research Group: a central hub "run LLMs, VLMs and robotics on NVIDIA edge hardware" surrounded by six branches — hardware platforms (Orin, Thor, DGX Spark), workloads (LLMs, VLMs, VLAs, speech, agents), software and tooling (JetPack 7.2/CUDA SBSA, vLLM/SGLang, jetson-containers, Isaac), what members do (benchmark, share container recipes, troubleshoot, quantize), physical AI and robotics (sim-to-real, robot arms, drones, VLA inference), and community and cadence (monthly meeting, talks, NVIDIA presence, news feeds).

The jetson-discord-scan skill gives it a read-only window into that server. It wraps the read verbs of the sibling discord-bot-cli — it never posts, reacts, or creates threads — and it scans public channels only (private / role-gated channels are always excluded).

S=.claude/skills/jetson-discord-scan/scripts/scan.sh

bash $S doctor                              # token present + guild readable?
bash $S active --since 30 --top 15          # public channels active in the last month, by traffic
bash $S channels                            # public channel map (each tagged "public": true)
bash $S read <channel_id> --limit 50        # recent messages of one channel

Needs a read-scoped bot token in DISCORD_BOT_TOKEN and discord-bot-cli with its [discord] extra. Results are JSON on stdout; errors/diagnostics on stderr. A committed public-only channel-map snapshot lives at data/channels.json.

Make it your own

  1. Rename the package jlab/ and the jetson-ai-lab-cli CLI/dist name throughout pyproject.toml, the package, tests/, and sonar-project.properties.
  2. Edit culture.yaml with your suffix and backend.
  3. Rewrite CLAUDE.md for your agent and run /init.
  4. Re-vendor only the skills you need from guildmaster (see docs/skill-sources.md).

See CLAUDE.md for the full conventions (version-bump-every-PR, the cicd PR lane, deploy setup).

License

MIT — see LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

jetson_ai_lab-0.2.0.tar.gz (112.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

jetson_ai_lab-0.2.0-py3-none-any.whl (19.7 kB view details)

Uploaded Python 3

File details

Details for the file jetson_ai_lab-0.2.0.tar.gz.

File metadata

  • Download URL: jetson_ai_lab-0.2.0.tar.gz
  • Upload date:
  • Size: 112.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.22 {"installer":{"name":"uv","version":"0.11.22","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for jetson_ai_lab-0.2.0.tar.gz
Algorithm Hash digest
SHA256 66dbca26896252698ca59e93886cf93b5088602942dbcb099005a237153d63b1
MD5 61882133e7c701571859705507f912af
BLAKE2b-256 72947a41a68088e3259fd0775cf3a305a36dca1c86a7a584e9374d84ba6ac6f9

See more details on using hashes here.

File details

Details for the file jetson_ai_lab-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: jetson_ai_lab-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 19.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.22 {"installer":{"name":"uv","version":"0.11.22","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for jetson_ai_lab-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a903f1de8980c8e3080dfb323901b6f7949347f6c57f6b883714b4d6c67657a7
MD5 1326608295809e7ae3963f1c3e6b7e66
BLAKE2b-256 b14d4695f7c140e8c305bde3fcd3509f9097ee6c8db2f34067288d606e753c8e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page