Llama is Meta’s family of large language models, released as downloadable weights under the Meta Llama Community Licence (open weights, not an OSI licence).
CHOOSE A PRODUCT · BUILD WITH YOUR AGENT
Llama is Meta’s family of large language models, released as downloadable weights under the Meta Llama Community Licence (open weights, not an OSI licence).
Catalog categories: ai_model.
Catalogued capability areas: - General-purpose text generation and reasoning - Instruction-tuned and multimodal variants - Self-hostable weights
This summary reflects the catalog record, not a complete product specification. Verify intended users, end-to-end workflows, supported platforms, edge cases, data handling, and constraints against cited sources. Treat capability labels as research leads until that verification is complete.
4 candidate projects in the landscape. A candidate may cover all, part, or none of what Llama does — read the coverage and gaps below.
Apache-2.0 licensed model family.
True OSI-licensed alternative.
Open-weight model family.
Licence varies by variant.
Permissively licensed open models.
OLMo is fully open (data + code).
Local runner for open weights.
Runtime, not a model.
Alternative coverage
Partial. Llama is open-weight, and genuinely open-source-licensed alternatives (Mistral Apache-2.0, OLMo) exist — hence no single "pending" project.
The gap
Llama’s licence is not OSI open source and carries use restrictions; fully open model families exist but at differing capability.
This Markdown file is the coding-agent skill for Llama. Give it to your agent in your project; it guides research, reuse decisions, implementation and verification.
Give the Llama skill to your coding agent in your project. Ask it to evaluate Mistral (Apache-2.0 models) ↗ against your needs, reuse what fits, then follow the skill's build and verification instructions.
Give the product skill to your coding agent in the project where you want to build. Optional starter workspace: rae build product meta-llama --out ./meta-llama. CLI reference.
