Skip to main content

Offline local-LLM layer (Ollama / OpenAI-compatible) with SQLite storage and profiles.

Project description

nerva-core

The offline local-LLM layer for the Revenant toolchain: a thin client for Ollama / OpenAI-compatible local servers, plus SQLite-backed conversation storage, model profiles, and a local memory index. Pure standard library — no third-party dependencies.

pip install nerva-core

What's in it

  • local_llm_writerChatConfig, call_model, call_model_message (native tool_calls), stream_model — for Ollama and OpenAI-compatible backends.
  • aibot_storage — SQLite conversation store (source of truth) + summaries + episodes.
  • aibot_profiles — model / style / generation profiles and role resolution.
  • aibot_memory — a local semantic-recall adapter.

Used by nerva-agent (the agent engine) and revenant-cli (the coding CLI).

License

MIT.

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

nerva_core-0.4.0.tar.gz (14.9 kB view details)

Uploaded Source

Built Distribution

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

nerva_core-0.4.0-py3-none-any.whl (15.6 kB view details)

Uploaded Python 3

File details

Details for the file nerva_core-0.4.0.tar.gz.

File metadata

  • Download URL: nerva_core-0.4.0.tar.gz
  • Upload date:
  • Size: 14.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.1

File hashes

Hashes for nerva_core-0.4.0.tar.gz
Algorithm Hash digest
SHA256 7f8ec35a4884af268f0d79a2f6b5c2eac9136a83890e9adcfce444f087dfbc1b
MD5 bd1ff3caef80a255c2df9a879bdf34b9
BLAKE2b-256 9ddb3da25947ab7c2f58632498d01338e0b9734638f7767d919b30058cf29d28

See more details on using hashes here.

File details

Details for the file nerva_core-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: nerva_core-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 15.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.1

File hashes

Hashes for nerva_core-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7e01d35cc71f9b2a63ffbee69c29e640fd4aa76a10baa4ea590a5cf5fec395aa
MD5 60d95e30ea91af0ad66e0ba4bd5f74a9
BLAKE2b-256 4b69fb5d5952f7d3fcffb626c75215ac1b5b89c7a30624c0862f7c08c49efe44

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