Skip to main content

Standalone three-line LLM streaming-halt guard — model-free, zero dependencies

Project description

Director-AI Lite

director-ai-lite is a standalone, dependency-free LLM streaming-halt guard: it stops a token stream before a hallucination finishes generating. It installs with zero heavy dependencies (standard library only) and does not require the full director-ai package.

pip install director-ai-lite
from director_ai_lite import guard

result = guard(
    token_stream,
    facts={"capital": "Paris is the capital of France."},
    prompt="What is the capital of France?",
)

print(result.output)       # surviving text (halted tokens removed)
print(result.halted)       # True if the stream was stopped
print(result.halt_reason)  # why it was stopped

How it works

The default path is model-free: each accumulated prefix is scored by a grounding heuristic (content-word overlap against the supplied facts) and the same calibrated coherence combination the full package uses in its no-model path. The stream hard-halts on the first token whose coherence drops below threshold (default 0.5). With no facts, scoring stays neutral and nothing is halted.

Because the grounding heuristic and the coherence calibration match the full package, you can upgrade to model-backed (NLI/RAG) scoring without changing the call site.

Upgrade to model-backed scoring

pip install "director-ai-lite[full]"

Then pass the full package's scorer to StreamGuard:

from director_ai_lite import StreamGuard

guard = StreamGuard(facts=..., scorer=my_nli_scorer)  # any review(prompt, text) scorer

Tiers

Director-Lite is the free, standalone entry point. The wider product ladder:

Tier What it is
Director-Lite Free. This package — standalone, model-free streaming halt, zero dependencies.
Director-AI The full runtime — model-backed NLI/RAG scoring, REST/gRPC server, framework integrations, sealed evidence packets, tamper-evident audit.
Director-AI Pro Production-tier licence and support on top of the full runtime.
Director-AI Full The complete advanced + labs capability set.
Director-Class AI Enterprise: managed/on-prem deployment, domain tuning, evidence reviews, SLA, procurement support.

Support development

Director-Lite is free forever, including in production. If it helps you, you can sponsor development via GitHub Sponsors — entirely optional, and it keeps the free tier moving.

License

Apache-2.0.

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

director_ai_lite-3.16.0.tar.gz (7.6 kB view details)

Uploaded Source

Built Distribution

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

director_ai_lite-3.16.0-py3-none-any.whl (7.4 kB view details)

Uploaded Python 3

File details

Details for the file director_ai_lite-3.16.0.tar.gz.

File metadata

  • Download URL: director_ai_lite-3.16.0.tar.gz
  • Upload date:
  • Size: 7.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for director_ai_lite-3.16.0.tar.gz
Algorithm Hash digest
SHA256 d2f0859df28469bdff611038cb1679c72fe1ac57b8d23d3144de676721d51896
MD5 57dc39e02e400ecea1697fefa13edc8b
BLAKE2b-256 cd0bedbf60120a2f4ac7fb74c1caa5feda9a4bb947a8331685e6aeb2324d5837

See more details on using hashes here.

Provenance

The following attestation bundles were made for director_ai_lite-3.16.0.tar.gz:

Publisher: publish-lite.yml on anulum/director-ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file director_ai_lite-3.16.0-py3-none-any.whl.

File metadata

File hashes

Hashes for director_ai_lite-3.16.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9975d7c0b5165fbc2616ce81b8f6f64ef55ef15156ce3b7b8c6c8b2171e853dd
MD5 5d2ec7d15c7c87c9dc744326776a7cf0
BLAKE2b-256 e6b501edcd1aa4b664753228618823ae4dc1ceb0439ee231ee8941e913c6f479

See more details on using hashes here.

Provenance

The following attestation bundles were made for director_ai_lite-3.16.0-py3-none-any.whl:

Publisher: publish-lite.yml on anulum/director-ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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