Skip to main content

ai-sherpa

Execution sherpas for AI agents built on ai-constitution.

Where ministers set policy, sherpas do the work. Each sherpa is a Python module that wraps a concrete operation: starting services, shutting down cleanly, reading plans, indexing design data, talking to NextCloud, crawling APIs, walking a new user through onboarding.

Sherpas

Sherpa Purpose Mandatory?
boot Initialize the agent stack — start services, build prompt, hand to the agent yes
exit Mechanical shutdown — set session flag, stop services in parallel, save checkpoint yes
onboarding Walk a new org through the variable registry; render templates yes (populated in M3)
scrum Read active plans, evaluate dependencies, alert on blockers optional
design Indexed design intelligence — component specs, tokens, freeform requests optional
nextcloud CRUD on NextCloud via the Pi API service optional
crawler Discover APIs/tools/services from curated sources, classify, dedup, import to Knowledge optional
scaffold Sherpa generator template — python -m ai_sherpa scaffold <new-name> n/a (tooling)

CLI

python -m ai_sherpa                       # list available sherpas
python -m ai_sherpa <name> [args...]      # run a sherpa
python -m ai_sherpa scaffold <new-name>   # generate a new sherpa from the template

Honest portability disclaimer (v0.0.1)

Most sherpas in this v0.0.1 release were lifted from raj-sadan and still reference raj-sadan's specific filesystem layout (e.g. <repo-root>/memory/journal/, gateway/*.cjs adapters). They run correctly when consumed as a git submodule from a host repo whose layout matches raj-sadan's — that's the intended consumer path right now.

A future v0.2.0 refactor will inject paths via configuration so every sherpa is fully portable in isolation. Tracked as a follow-up to RAJ-70.

Status

v0.0.1 — populated by Linear issues RAJ-60, RAJ-68, RAJ-69, RAJ-70. Onboarding sherpa is M3 (RAJ-61). Public release is M5 (RAJ-75).

See also

License

MIT.

Metadata

Release files for ai-sherpa 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ai-sherpa 0.1.2
File Size Uploaded Provenance
ai_sherpa-0.1.2.tar.gz 83.1 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for ai-sherpa 0.1.2
File Interpreter ABI Platform
ai_sherpa-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 172.3 kB

Release files / ai_sherpa-0.1.2.tar.gz

Download URL ai_sherpa-0.1.2.tar.gz
Size 83.1 kB
Tags Source
SHA-256 checksum
How to use checksums
a3147a8133b717826ae79acf254880d03bfeea88a6f400bf2cb195a9dcad613a
BLAKE2b-256 checksum
How to use checksums
e358d7307b2c80da6c102e81129a84cb14396864e19c64ceab47ac4c474e77c8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 29, 2026.

Transparency log

Release files / ai_sherpa-0.1.2-py3-none-any.whl

Download URL ai_sherpa-0.1.2-py3-none-any.whl
Size 89.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b8c970e1fda545cd1ab90a30442e83a32dc0995e41d725446ce769b575a35237
BLAKE2b-256 checksum
How to use checksums
de58e41e983900e1607722cee8bad9057159b69f233af801242e5cd1a5aff414
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 29, 2026.

Transparency log

Security for ai-sherpa 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for ai_sherpa-0.1.2.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 29, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.2 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page